{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":19989,"databundleVersionId":1160143,"sourceType":"competition"},{"sourceId":11058288,"sourceType":"datasetVersion","datasetId":6889745},{"sourceId":11088581,"sourceType":"datasetVersion","datasetId":6911640}],"dockerImageVersionId":29963,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"### EDITS/REWORKS:\nV12: Corrections, enhanced readability\n\nV10: Typo correction, slight changes & additions  \n\nV9: fixed a bug in Inference (used predictions for the wrong image) --> now predictions amtch ground-truth much better","metadata":{}},{"cell_type":"markdown","source":"## Quick Intro: Dear Farmgirls, dear Farmboys..\nthis is my first object detection Kaggle competition! \nPlease feel free to give me some hints for improvements in all categories: making code more \"pythonic\", better graphics, ideas for pre & post-processing, etc.\n","metadata":{}},{"cell_type":"markdown","source":"# Competition description\nOpen up your pantry and you’re likely to find several wheat products. Indeed, your morning toast or cereal may rely upon this common grain. Its popularity as a food and crop makes wheat widely studied. To get large and accurate data about wheat fields worldwide, plant scientists use image detection of \"wheat heads\"—spikes atop the plant containing grain. These images are used to estimate the density and size of wheat heads in different varieties. Farmers can use the data to assess health and maturity when making management decisions in their fields.\nHowever, accurate wheat head detection in outdoor field images can be visually challenging. There is often overlap of dense wheat plants, and the wind can blur the photographs. Both make it difficult to identify single heads. Additionally, appearances vary due to maturity, color, genotype, and head orientation. Finally, because wheat is grown worldwide, different varieties, planting densities, patterns, and field conditions must be considered.\n\nWheat is a staple across the globe, which is why this competition must account for different growing conditions. Models developed for wheat phenotyping need to be able to generalize between environments. If successful, researchers can accurately estimate the density and size of wheat heads in different varieties. With improved detection farmers can better assess their crops, ultimately bringing cereal, toast, and other favorite dishes to your table.\n\n### What should I expect the data format to be?\nThe Global Wheat Head Dataset is led by nine research institutes from seven countries: the University of Tokyo, Institut national de recherche pour l’agriculture, l’alimentation et l’environnement, Arvalis, ETHZ, University of Saskatchewan, University of Queensland, Nanjing Agricultural University, and Rothamsted Research.\nThe Data needs to be submitted in Coco-style format: x, y, width and height.\n\n### What am I predicting?\nIn this competition, you’ll detect wheat heads from outdoor images of wheat plants, including wheat datasets from around the globe. Using worldwide data, you will focus on a generalized solution to estimate the number and size of wheat heads. To better gauge the performance for unseen genotypes, environments, and observational conditions, the training dataset covers multiple regions. You will use more than 3,000 images from Europe (France, UK, Switzerland) and North America (Canada). The test data includes about 1,000 images from Australia, Japan, and China.\n\n","metadata":{"jp-MarkdownHeadingCollapsed":true}},{"cell_type":"markdown","source":"# Faster RCNN Intro\n## Architectural overview\n![Architektur+#.PNG](attachment:Architektur+#.PNG)\n\n\n","metadata":{},"attachments":{"Architektur+#.PNG":{"image/png":"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"}}},{"cell_type":"markdown","source":"## How Faster-RCNN works:  \n\n1) **Region Proposal Network** (RPN) step 1: Run the image through a CNN to get a **Feature Map** and project Anchors or BBoxes onto this map.  \n\n2) (RPN) step 2: Keep only the best anchors (e.g. top 2000), and discard the rest. This is achieved using only anchors with IoU < 0.4 for background and > 0.7 for objects and after that  applying non-max suppression.  \n\n3) Do **Region of interest** pooling ([ROI Pooling](https://blog.deepsense.ai/region-of-interest-pooling-explained/): this leads to uniformly sized outputs which can be used for classification and BBOX regression  \n\n4) For the **Classification** task ( = is it background or object?) binary cross entropy (BCE) is used to calculate the loss.   \n\n5) The **BBOX regressor** calculates offsets based on the anchors from step 2) and the regression loss is calculated.  \n\n\nMore in depth literatur on how anchor boxes are created and how ROI pooling works in detail can be found here:\nhttps://tryolabs.com/blog/2018/01/18/faster-r-cnn-down-the-rabbit-hole-of-modern-object-detection/  \nhttps://medium.com/@smallfishbigsea/faster-r-cnn-explained-864d4fb7e3f8  \nhttps://medium.com/@whatdhack/a-deeper-look-at-how-faster-rcnn-works-84081284e1cd  \nhttps://towardsdatascience.com/fasterrcnn-explained-part-1-with-code-599c16568cff    \n\n\n## Special info about the pytroch implementation we are going to use.\n* As you can see in many [github implementations](https://github.com/pytorch/vision/blob/d2c763e14efe57e4bf3ebf916ec243ce8ce3315c/torchvision/models/detection/faster_rcnn.py#L227) and the (kinda hard to find) [official pytroch implementation](https://pytorch.org/docs/stable/_modules/torchvision/models/detection/faster_rcnn.html#fasterrcnn_resnet50_fpn), the minimum Image size for FasterRCNN is 800 and the maximum is 1333. So resizing to below 800 (most notebooks use 512 for training) before feeding it in the network is not only unnecessary computational cost, but also decreasing the information contained in the pictures.\n* Images should not be normalized during augmentation-process or in your Dataset-class. Subtracting the mean and dividing by std. deviation is automatically done in the [GeneralizedRCNNTransform](https://github.com/pytorch/vision/blob/39021408587eb252ebb842a54195d840d6d76095/torchvision/models/detection/transform.py)-Class which is used by the model itself! \n","metadata":{}},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"markdown","source":"## Importing dependencies\n<span style=\"color:darkgreen ;font-family: Impact; font-size:13;\"> from  </span> coffee  <span style=\"color:darkgreen ;font-family: Impact; font-size:13;\"> import  </span> ***** ","metadata":{}},{"cell_type":"code","source":"import os\nimport numpy as np \nimport pandas as pd \nfrom datetime import datetime\nimport time\nimport random\nfrom tqdm import tqdm_notebook as tqdm # progress bar\nimport matplotlib.pyplot as plt\n\n# torch\nimport torch\nimport torch.nn as nn\nfrom torch.utils.data import Dataset,DataLoader\nfrom torch.utils.data.sampler import SequentialSampler, RandomSampler\n\n# torchvision\nimport torchvision\nfrom torchvision.models.detection.faster_rcnn import FastRCNNPredictor, FasterRCNN\nfrom torchvision.models.detection.backbone_utils import resnet_fpn_backbone\n\n# sklearn\nfrom sklearn.model_selection import StratifiedKFold\n\n# CV\nimport cv2\n\n# Albumenatations\nimport albumentations as A\nfrom albumentations.pytorch.transforms import ToTensorV2\n\n# Glob\nfrom glob import glob\n\nimport warnings\nwarnings.filterwarnings('ignore') #Ignore \"future\" warnings and Data-Frame-Slicing warnings.","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Lets check our Hardware first\ngpu_info = !nvidia-smi\ngpu_info = '\\n'.join(gpu_info)\nif gpu_info.find('failed') >= 0:\n    print('Select the Runtime > \"Change runtime type\" menu to enable a GPU accelerator, ')\n    print('and then re-execute this cell.')\nelse:\n    print(gpu_info)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Configuration\n\n## Basic configuration for this model\n\nBelow you can change the base configuration, the impact on CV and LB score is quite high! Be careful to not choose a too high learning rate.","metadata":{}},{"cell_type":"code","source":"# original\nn_folds = 5\nseed = 2020\nnum_classes = 10\nBATCH_SIZE = 4\nLR = 0.05\n\n## Use more then 20 Epochs, we go for 20 epochs for demonstration purposes\nEPOCHS = 10\nimg_size_training = 800\n\n## Choose your optimizers:\nAdam = False\nif Adam: \n    Adam_config = {\"lr\" : 0.001, \"betas\" : (0.9, 0.999), \"eps\" : 1e-08}\nelse:\n    SGD_config = {\"lr\" : 0.001, \"momentum\" : 0.9, \"weight_decay\" : 0.001}","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Configuration for the dataset\nDIR_TRAIN = '/kaggle/input/oranges-dataset-2700/Dataset 2700/Train'\nBATCH_SIZE = 4\nEPOCHS = 10\nnum_classes = 10\nseed = 2020","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Seed Everything\n\nSeeding everything for reproducible results.","metadata":{}},{"cell_type":"code","source":"def seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = True\nseed_everything(seed)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"markdown","source":"# Preparing the Data\n\nFor creating a cross-validation strategy we use code from Alex's awesome [kernel](https://www.kaggle.com/shonenkov/training-efficientdet).\nWe will create a cross-validation split in which the folds are made by preserving the percentage of samples (= stratisfied!) for each of the following \"classes\":\n* number of boxes \n* source\n\nFor this we first check the data:","metadata":{}},{"cell_type":"code","source":"bboxes_df = pd.read_csv('/kaggle/input/oranges-dataset-2700/Dataset 2700/train2700.csv')\nbboxes_df.head()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"And then unpack the bbox coordinates into seperate columns x, y, w, h.","metadata":{}},{"cell_type":"code","source":"# get an array of arrays of all bboxes in the form [[x], [y], [w], [h]]\nbboxs = np.stack(bboxes_df['bbox'].apply(lambda x: np.fromstring(x[1:-1], sep = ',')))\n# save the values in the respective column\nfor i, column in enumerate(['x', 'y', 'w', 'h']):\n    bboxes_df[column] = bboxs[:,i]\nbboxes_df.drop(columns=['bbox'], inplace=True)\nbboxes_df.head()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# original\n# Creating stratified Folds\nskf = StratifiedKFold(n_splits = n_folds, shuffle = True, random_state = seed)\n\ndf_folds = bboxes_df[['image_id']].copy()\ndf_folds.loc[:, 'bbox_count'] = 1\n\n# get number of bboxes for each image_id\ndf_folds = df_folds.groupby('image_id').count()\n\n# add [source] column\ndf_folds.loc[:, 'source'] = bboxes_df[['image_id', 'source']].groupby('image_id').min()['source']\n\n# concat two arays of strings: source and (_bboxcount // 15) to separate into folds\ndf_folds.loc[:, 'stratify_group'] = np.char.add(\n    df_folds['source'].values.astype(str),\n    df_folds['bbox_count'].apply(lambda x: f'_{x // 15}').values.astype(str))\ndf_folds.loc[:, 'fold'] = 0\n\nfor fold_number, (train_index, val_index) in enumerate(skf.split(        \n        X = df_folds.index,\n        y = df_folds['stratify_group'])):\n    df_folds.loc[df_folds.iloc[val_index].index, 'fold'] = fold_number","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# from sklearn.model_selection import StratifiedKFold\n# import numpy as np\n# import pandas as pd\n\n# # Assuming bboxes_df is already loaded\n# skf = StratifiedKFold(n_splits=n_folds, shuffle=True, random_state=seed)\n\n# df_folds = bboxes_df[['image_id']].copy()\n# df_folds.loc[:, 'bbox_count'] = 1\n\n# # Get number of bboxes for each image_id\n# df_folds = df_folds.groupby('image_id').count()\n\n# # Add [source] column\n# df_folds.loc[:, 'source'] = bboxes_df[['image_id', 'source']].groupby('image_id').min()['source']\n\n# # Concatenate source and bbox_count (binned by 15) to create stratify groups\n# df_folds.loc[:, 'stratify_group'] = np.char.add(\n#     df_folds['source'].values.astype(str),\n#     df_folds['bbox_count'].apply(lambda x: f'_{x // 15}').values.astype(str)\n# )\n# df_folds.loc[:, 'fold'] = 0\n\n# # Split into folds\n# print(\"Creating stratified folds...\")\n# for fold_number, (train_index, val_index) in enumerate(\n#     skf.split(X=df_folds.index, y=df_folds['stratify_group'])\n# ):\n#     df_folds.loc[df_folds.iloc[val_index].index, 'fold'] = fold_number\n#     print(f\"Fold {fold_number}: {len(val_index)} images\")\n\n# # Display summary of folds\n# print(\"\\nSummary of folds:\")\n# fold_counts = df_folds['fold'].value_counts().sort_index()\n# for fold, count in fold_counts.items():\n#     print(f\"Fold {fold}: {count} images\")\n\n# # Optional: Display the first few rows of the resulting dataframe\n# print(\"\\nSample of fold assignments:\")\n# print(df_folds.head())","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Creating Dataset\n## Let's raise a glass* to create the Dataset!\n![champaign-clipart-champagne-glass-6.png](attachment:champaign-clipart-champagne-glass-6.png)\n\n*class","metadata":{},"attachments":{"champaign-clipart-champagne-glass-6.png":{"image/png":"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"}}},{"cell_type":"code","source":"DIR_TRAIN = '/kaggle/input/oranges-dataset-2700/Dataset 2700/Train'\n\nclass WheatDataset(Dataset):\n    def __init__(self, image_ids, dataframe, transforms=None):\n        self.image_ids = image_ids\n        self.df = dataframe\n        self.transforms = transforms\n        \n    def __len__(self):\n        return self.image_ids.shape[0]\n    \n    def __getitem__(self, index):\n        image_id = self.image_ids[index]\n        records = self.df[self.df['image_id'] == image_id]\n        \n        # Load and normalize image\n        image = cv2.imread(f'{DIR_TRAIN}/{image_id}.jpg', cv2.IMREAD_COLOR)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB).astype(np.float32)\n        image /= 255.0\n        \n        # Adjust bounding boxes from COCO format to Pascal VOC\n        boxes = records[['x', 'y', 'w', 'h']].values\n        boxes[:, 2] = boxes[:, 0] + boxes[:, 2]\n        boxes[:, 3] = boxes[:, 1] + boxes[:, 3]\n        \n        # Convert labels to tensor; label comes from 'class_id' in your dataset\n        labels = torch.tensor(records['class_id'].values, dtype=torch.int64)\n        \n        area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])\n        area = torch.as_tensor(area, dtype=torch.float32)\n        iscrowd = torch.zeros((records.shape[0],), dtype=torch.int64)\n        \n        target = {\n            'boxes': torch.as_tensor(boxes, dtype=torch.float32),\n            'labels': labels,\n            'image_id': torch.tensor([index]),\n            'area': area,\n            'iscrowd': iscrowd\n        }\n        \n        # Apply transformations if any\n        if self.transforms:\n            sample = {\n                'image': image,\n                'bboxes': target['boxes'],\n                'labels': labels\n            }\n            sample = self.transforms(**sample)\n            image = sample['image']\n            target['boxes'] = torch.as_tensor(sample['bboxes'], dtype=torch.float32)\n        \n        return image, target, image_id\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Augmentations\nDue to the limited size of the dataset and the fact, that Imagenet pre-trained FasterRCNNs don't know a lot about Wheathead-Detection yet, we will use a lot of different augmentations.\nBut: More augmentations are not always leading to better results. Also the augmentations need to be somewhat reasonable. So be careful to not augment every single picture multiple times: Using Albumentations ```OneOf``` method helps a lot here.\nUsing [Cutmix](https://arxiv.org/abs/1905.04899) in this competition is a very good idea to ensure good regulariazion/generalization of your network.\n\nHowever, there are always things you should not do:\n![](https://pbs.twimg.com/media/Ea4T7DxWsAEi4Ga.jpg)\n","metadata":{}},{"cell_type":"code","source":"# Albumentations for training\ndef get_train_transforms():\n    return A.Compose(\n        [\n            A.OneOf([  # Apply color-related augmentations\n                A.HueSaturationValue(hue_shift_limit=0.2, \n                                     sat_shift_limit=0.2,\n                                     val_shift_limit=0.2,\n                                     p=0.3), \n                A.RandomBrightnessContrast(brightness_limit=0.2,                                             \n                                           contrast_limit=0.2,\n                                           p=0.3),\n                A.RGBShift(r_shift_limit=20/255, \n                           g_shift_limit=20/255, \n                           b_shift_limit=10/255,\n                           p=0.3)\n            ], p=0.2),\n            \n            # Additional variations\n            A.OneOf([\n                A.RandomGamma(gamma_limit=(80, 120), p=0.3),\n                A.Blur(p=0.6),  # Blurring the image for variance\n                A.GaussNoise(var_limit=(0.01, 0.05), mean=0, p=0.05),\n                A.ToGray(p=0.05)  # Convert to grayscale with a small chance\n            ], p=0.1),\n            \n            # Flipping and rotating the image\n            A.OneOf([\n                A.HorizontalFlip(p=1),\n                A.VerticalFlip(p=1),\n                A.Transpose(p=1),\n                A.RandomRotate90(p=1)\n            ], p=0.7),\n            \n            # Adding environmental variations\n            A.RandomFog(fog_coef_lower=0.1,\n                        fog_coef_upper=0.2,\n                        p=0.02),  # Slight fog in natural environment\n            \n            # Crop and resize transformations\n            A.RandomSizedBBoxSafeCrop(img_size_training, \n                                      img_size_training, \n                                      p=0.05),\n            A.Resize(height=img_size_training, \n                     width=img_size_training, \n                     p=1),  # Resizing to the required size\n            \n            # Random Cutout for regularization\n            A.Cutout(num_holes=random.randint(1, 6),\n                     max_h_size=64, \n                     max_w_size=64,\n                     fill_value=0, \n                     p=0.15),\n            \n            ToTensorV2(p=1.0),\n        ],\n        p=1.0,\n        bbox_params={\n            'format': 'pascal_voc',  # Bounding boxes in Pascal VOC format\n            'label_fields': ['labels']  # Ensure labels for multiclass detection are retained\n        }\n    )\n\n# Albumentations for validation (simpler transformations)\ndef get_valid_transforms():\n    return A.Compose([\n        A.Resize(height=img_size_training, width=img_size_training, p=1),  # Resize for validation\n        ToTensorV2(p=1.0)\n    ], bbox_params={\n        'format': 'pascal_voc',  # Bounding boxes format remains Pascal VOC\n        'label_fields': ['labels']  # Ensure labels are retained in validation\n    })","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Validate Augmentations","metadata":{}},{"cell_type":"markdown","source":"It's always strongly recommended to check your input pictures into your model after augmentations, to ensure that not strange things happen.\n\nI've seen (and also accidently used)  \n```A.RGBShift(r_shift_limit = 20, \n            g_shift_limit = 20,\n            b_shift_limit = 10,\n            p = 0.3)```    \nin a training pipeline for normalized pictures, and guess what happend: They turned in completely yellow, blue or red. Why? Because RGBSHift expectes not-normalized pictures! So be sure you normalize RGB shift to get valid input data -->  \n```A.RGBShift(r_shift_limit = 20/255, \n            g_shift_limit = 20/255,\n            b_shift_limit = 10/255, \n            p = 0.3)```","metadata":{}},{"cell_type":"code","source":"## In several occasions in the next sections we will need to create a dataset and a dataloader.\n# In this section we create helper functions for this to stay DRY (dont repeast yourself).\n\ndef get_validation_datset(df):\n    return WheatDataset(\n    image_ids = df.index.values,\n    dataframe = bboxes_df,\n    transforms = get_valid_transforms()\n    )\n    \ndef get_train_datset(df):    \n    return WheatDataset(\n    image_ids = df.index.values,\n    dataframe = bboxes_df,\n    transforms = get_train_transforms()\n    )\n\ndef get_validation_data_loader(valid_dataset, batch_size = 16):\n    return DataLoader(\n    valid_dataset,\n    batch_size = batch_size,\n    shuffle = False,\n    num_workers = 4,\n    collate_fn = collate_fn\n    )    \n\ndef get_train_data_loader(train_dataset, batch_size = 16):\n    return DataLoader(\n    train_dataset,\n    batch_size = batch_size,\n    shuffle = False,\n    num_workers = 4,\n    collate_fn = collate_fn\n    ) \n\ndef collate_fn(batch):\n    return tuple(zip(*batch))","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# original\n## Lets check some augmentations!\n\n# get a fold\ndf_train = df_folds[df_folds['fold'] != 0]\n\n# create train dataset and data-loader\ntrain_dataset = get_train_datset(df_train)\ntrain_data_loader = get_train_data_loader(train_dataset, batch_size = 16)\n\ndevice=torch.device('cuda')\nimages, targets, image_ids = next(iter(train_data_loader))\n\nimages = list(image.to(device) for image in images)\ntargets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n# plot some augmentations!\nfig, ax = plt.subplots(figsize=(20, 20),  \n                       nrows = 4,\n                       ncols = 4)\nfor i in range (16):    \n    boxes = targets[i]['boxes'].cpu().numpy().astype(np.int32)\n    sample = images[i].permute(1,2,0).cpu().numpy()\n    for box in boxes:\n        cv2.rectangle(sample,\n                      (box[0], box[1]),\n                      (box[2], box[3]),\n                      (220, 0, 0), 3)\n    \n    ax[i // 4][i % 4].imshow(sample)   ","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ## Let's check some augmentations!\n\n# # Get a fold\n# print(\"Filtering training data from 'df_folds' where 'fold' is not 0\")\n# df_train = df_folds[df_folds['fold'] != 0]\n# print(\"Number of training samples:\", len(df_train))\n\n# # Create train dataset and data-loader\n# print(\"Creating training dataset and data loader...\")\n# train_dataset = get_train_datset(df_train)\n# train_data_loader = get_train_data_loader(train_dataset, batch_size=16)\n# print(\"Data loader created with batch size = 16\")\n\n# # Move data to device\n# device = torch.device('cuda')\n# print(\"Using device:\", device)\n\n# print(\"Fetching a batch from the data loader...\")\n# images, targets, image_ids = next(iter(train_data_loader))\n# print(f\"Batch fetched. Number of images: {len(images)}, Number of targets: {len(targets)}\")\n\n# print(\"Moving images and targets to the device...\")\n# images = list(image.to(device) for image in images)\n# targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n# print(\"Images and targets moved to device.\")\n\n# # Plot some augmentations\n# print(\"Plotting augmentations...\")\n# fig, ax = plt.subplots(figsize=(20, 20), nrows=4, ncols=4)\n\n# for i in range(16):\n#     print(f\"Processing image {i + 1}...\")\n#     boxes = targets[i]['boxes'].cpu().numpy().astype(np.int32)\n#     sample = images[i].permute(1, 2, 0).cpu().numpy()\n#     print(f\"Number of bounding boxes for image {i + 1}: {len(boxes)}\")\n    \n#     for box in boxes:\n#         print(f\"Drawing box: {box}\")\n#         cv2.rectangle(\n#             sample,\n#             (box[0], box[1]),\n#             (box[2], box[3]),\n#             (220, 0, 0), 3\n#         )\n    \n#     ax[i // 4][i % 4].imshow(sample)\n#     ax[i // 4][i % 4].axis('off')\n\n# print(\"Displaying augmentations.\")\n# plt.tight_layout()\n# plt.show()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Model\n\n","metadata":{}},{"cell_type":"markdown","source":"As mentioned in the introduction, we are using the default [ResNet50 pytroch implementation](https://kite.com/python/docs/torchvision.models.detection.fasterrcnn_resnet50_fpn) here.\nWe will start with defining a function to load and get the model, as we will be doing this several times in the later sections. Next, we will define an AverageMeter, tracking of the loss of our model.\nThen we can finally set up the training.","metadata":{}},{"cell_type":"code","source":"def get_model():    \n    # load pre-trained model incl. head\n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)\n\n    # get number of input features for the classifier custom head\n    in_features = model.roi_heads.box_predictor.cls_score.in_features\n\n    # replace the pre-trained head with a new one\n    model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)\n\n    return model","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Training Function\n\n","metadata":{}},{"cell_type":"code","source":"class AverageMeter(object):\n    \"\"\"Computes and stores the average and current value\"\"\"\n    # initialize and reset to zero\n    def __init__(self):\n        self.reset()\n\n    # reset everything to zero    \n    def reset(self):\n        self.val = 0\n        self.avg = 0\n        self.sum = 0\n        self.count = 0\n\n    # update loss after each batch\n    def update(self, val, n=1):\n        self.val = val\n        self.sum += val * n\n        self.count += n\n        self.avg = self.sum / self.count","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def train_fn(data_loader, model, optimizer, device, scheduler, epoch):\n    # Set the model to training mode\n    model.train()\n\n    # Use AverageMeter to track the loss across batches\n    summary_loss = AverageMeter()\n\n    # Initialize the progress bar\n    tk0 = tqdm(data_loader, total=len(data_loader))\n    \n    # Iterate through batches of data\n    for step, (images, targets, image_ids) in enumerate(tk0):   \n        \n        # Handle case where targets are empty (no bounding boxes detected)\n        if len(targets) < 1:\n            targets = [{'boxes': torch.zeros((0, 4)).to(device), 'labels': torch.zeros(0).to(device)}]\n            \n        # Move the images and targets to the device (GPU/CPU)\n        images = list(image.to(device) for image in images)\n        targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n        # Forward pass: calculate the loss based on the current state of the model\n        loss_dict = model(images, targets)        \n        losses = sum(loss for loss in loss_dict.values())\n\n        # Zero out the gradients from the previous step\n        optimizer.zero_grad()\n        \n        # Backward pass: compute the gradients based on the loss\n        losses.backward()\n        \n        # Step the optimizer (update the model's weights)\n        optimizer.step()\n        \n        # If a learning rate scheduler is provided, step it\n        if scheduler is not None:\n            scheduler.step()\n        \n        # Update the summary loss for tracking purposes\n        summary_loss.update(losses.item(), len(images))  # Update by the number of images in the batch\n        \n        # Update the progress bar with the current loss\n        tk0.set_postfix(loss=summary_loss.avg)\n    \n    return summary_loss  # Return the average loss after the epoch","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Evaluation Function","metadata":{}},{"cell_type":"markdown","source":"In order to select the best model, epoch & weights, we need to create a valid competition metric.\nIn this case, we take the very well coded version from [this notebook](https://www.kaggle.com/pestipeti/competition-metric-details-script). ","metadata":{}},{"cell_type":"code","source":"def calculate_iou(gt, pr, form='pascal_voc') -> float:\n    \"\"\"Calculates the Intersection over Union.\n\n    Args:\n        gt: (np.ndarray[Union[int, float]]) coordinates of the ground-truth box\n        pr: (np.ndarray[Union[int, float]]) coordinates of the prdected box\n        form: (str) gt/pred coordinates format\n            - pascal_voc: [xmin, ymin, xmax, ymax]\n            - coco: [xmin, ymin, w, h]\n    Returns:\n        (float) Intersection over union (0.0 <= iou <= 1.0)\n    \"\"\"\n    if form == 'coco':\n        gt = gt.copy()\n        pr = pr.copy()\n\n        gt[2] = gt[0] + gt[2]\n        gt[3] = gt[1] + gt[3]\n        pr[2] = pr[0] + pr[2]\n        pr[3] = pr[1] + pr[3]\n\n    # Calculate overlap area\n    dx = min(gt[2], pr[2]) - max(gt[0], pr[0]) + 1\n    \n    if dx < 0:\n        return 0.0\n    dy = min(gt[3], pr[3]) - max(gt[1], pr[1]) + 1\n\n    if dy < 0:\n        return 0.0\n\n    overlap_area = dx * dy\n\n    # Calculate union area\n    union_area = (\n            (gt[2] - gt[0] + 1) * (gt[3] - gt[1] + 1) +\n            (pr[2] - pr[0] + 1) * (pr[3] - pr[1] + 1) -\n            overlap_area\n    )\n\n    return overlap_area / union_area\n\ndef find_best_match(gts, pred, pred_idx, threshold = 0.5, form = 'pascal_voc', ious=None) -> int:\n    \"\"\"Returns the index of the 'best match' between the\n    ground-truth boxes and the prediction. The 'best match'\n    is the highest IoU. (0.0 IoUs are ignored).\n\n    Args:\n        gts: (List[List[Union[int, float]]]) Coordinates of the available ground-truth boxes\n        pred: (List[Union[int, float]]) Coordinates of the predicted box\n        pred_idx: (int) Index of the current predicted box\n        threshold: (float) Threshold\n        form: (str) Format of the coordinates\n        ious: (np.ndarray) len(gts) x len(preds) matrix for storing calculated ious.\n\n    Return:\n        (int) Index of the best match GT box (-1 if no match above threshold)\n    \"\"\"\n    best_match_iou = -np.inf\n    best_match_idx = -1\n    for gt_idx in range(len(gts)):\n        \n        if gts[gt_idx][0] < 0:\n            # Already matched GT-box\n            continue\n        \n        iou = -1 if ious is None else ious[gt_idx][pred_idx]\n\n        if iou < 0:\n            iou = calculate_iou(gts[gt_idx], pred, form = form)\n            \n            if ious is not None:\n                ious[gt_idx][pred_idx] = iou\n\n        if iou < threshold:\n            continue\n\n        if iou > best_match_iou:\n            best_match_iou = iou\n            best_match_idx = gt_idx\n\n    return best_match_idx\n\ndef calculate_precision(gts, preds, threshold = 0.5, form = 'coco', ious=None) -> float:\n    \"\"\"Calculates precision for GT - prediction pairs at one threshold.\n\n    Args:\n        gts: (List[List[Union[int, float]]]) Coordinates of the available ground-truth boxes\n        preds: (List[List[Union[int, float]]]) Coordinates of the predicted boxes,\n               sorted by confidence value (descending)\n        threshold: (float) Threshold\n        form: (str) Format of the coordinates\n        ious: (np.ndarray) len(gts) x len(preds) matrix for storing calculated ious.\n\n    Return:\n        (float) Precision\n    \"\"\"\n    n = len(preds)\n    tp = 0\n    fp = 0\n    \n    for pred_idx in range(n):\n\n        best_match_gt_idx = find_best_match(gts, preds[pred_idx], pred_idx,\n                                            threshold=threshold, form=form, ious=ious)\n\n        if best_match_gt_idx >= 0:\n            # True positive: The predicted box matches a gt box with an IoU above the threshold.\n            tp += 1\n            # Remove the matched GT box\n            gts[best_match_gt_idx] = -1\n        else:\n            # No match\n            # False positive: indicates a predicted box had no associated gt box.\n            fp += 1\n\n    # False negative: indicates a gt box had no associated predicted box.\n    fn = (gts.sum(axis=1) > 0).sum()\n\n    return tp / (tp + fp + fn)\n\n\n\ndef calculate_image_precision(gts, preds, thresholds = (0.5, ), form = 'coco') -> float:\n    \"\"\"Calculates image precision.\n\n    Args:\n        gts: (List[List[Union[int, float]]]) Coordinates of the available ground-truth boxes\n        preds: (List[List[Union[int, float]]]) Coordinates of the predicted boxes,\n               sorted by confidence value (descending)\n        thresholds: (float) Different thresholds\n        form: (str) Format of the coordinates\n\n    Return:\n        (float) Precision\n    \"\"\"\n    n_threshold = len(thresholds)\n    image_precision = 0.0\n    \n    ious = np.ones((len(gts), len(preds))) * -1\n    # ious = None\n\n    for threshold in thresholds:\n        precision_at_threshold = calculate_precision(gts.copy(), \n                                                     preds, \n                                                     threshold = threshold,\n                                                     form = form,\n                                                     ious = ious)\n        image_precision += precision_at_threshold / n_threshold\n\n    return image_precision\n","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# def calculate_iou(gt, pr, form='pascal_voc') -> float:\n#     if form == 'coco':\n#         gt = gt.copy()\n#         pr = pr.copy()\n\n#         # Convert COCO format (x, y, w, h) to Pascal VOC format (xmin, ymin, xmax, ymax)\n#         gt[2] = gt[0] + gt[2]\n#         gt[3] = gt[1] + gt[3]\n#         pr[2] = pr[0] + pr[2]\n#         pr[3] = pr[1] + pr[3]\n\n#     # Calculate overlap area\n#     dx = min(gt[2], pr[2]) - max(gt[0], pr[0]) + 1\n#     if dx < 0:\n#         return 0.0\n#     dy = min(gt[3], pr[3]) - max(gt[1], pr[1]) + 1\n#     if dy < 0:\n#         return 0.0\n\n#     overlap_area = dx * dy\n\n#     # Calculate union area\n#     union_area = (\n#         (gt[2] - gt[0] + 1) * (gt[3] - gt[1] + 1) +\n#         (pr[2] - pr[0] + 1) * (pr[3] - pr[1] + 1) - overlap_area\n#     )\n\n#     return overlap_area / union_area","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# def find_best_match(gts, pred, pred_idx, threshold=0.5, form='pascal_voc', ious=None) -> int:\n#     best_match_iou = -np.inf\n#     best_match_idx = -1\n\n#     for gt_idx in range(len(gts)):\n#         if gts[gt_idx][0] < 0:  # Skip already matched boxes\n#             continue\n\n#         iou = -1 if ious is None else ious[gt_idx][pred_idx]\n#         if iou < 0:\n#             iou = calculate_iou(gts[gt_idx], pred, form=form)\n#             if ious is not None:\n#                 ious[gt_idx][pred_idx] = iou\n\n#         if iou < threshold:\n#             continue\n\n#         if iou > best_match_iou:\n#             best_match_iou = iou\n#             best_match_idx = gt_idx\n\n#     return best_match_idx","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# def calculate_precision(gts, preds, threshold=0.5, form='coco', ious=None) -> float:\n#     n = len(preds)\n#     tp = 0\n#     fp = 0\n\n#     for pred_idx in range(n):\n#         best_match_gt_idx = find_best_match(gts, preds[pred_idx], pred_idx,\n#                                             threshold=threshold, form=form, ious=ious)\n#         if best_match_gt_idx >= 0:\n#             tp += 1  # True positive\n#             gts[best_match_gt_idx] = -1  # Mark GT box as matched\n#         else:\n#             fp += 1  # False positive\n\n#     fn = (gts.sum(axis=1) > 0).sum()  # False negatives\n\n#     return tp / (tp + fp + fn)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# def calculate_image_precision(gts, preds, thresholds=(0.5,), form='coco') -> float:\n#     n_threshold = len(thresholds)\n#     image_precision = 0.0\n\n#     ious = np.ones((len(gts), len(preds))) * -1  # Precompute IoUs\n\n#     for threshold in thresholds:\n#         precision_at_threshold = calculate_precision(gts.copy(), preds,\n#                                                      threshold=threshold,\n#                                                      form=form,\n#                                                      ious=ious)\n#         image_precision += precision_at_threshold / n_threshold\n\n#     return image_precision","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# def eval_fn(data_loader, model, device):\n#     model.eval()\n#     summary_loss_eval = AverageMeter()\n#     iou_thresholds = [x for x in np.arange(0.5, 0.76, 0.05)]\n#     validation_image_precisions = []\n    \n#     with torch.no_grad():\n        \n#         tk0 = tqdm(data_loader, total=len(data_loader))\n#         for step, (images, targets, image_ids) in enumerate(tk0):\n            \n#             images = list(image.to(device) for image in images)\n#             targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n            \n#             \"\"\"\n#             In model.train() mode, model(images)  is returning losses.\n#             We are using model.eval() mode --> it will return boxes and scores. \n#             \"\"\"\n#             outputs = model(images)\n\n#             for i, image in enumerate(images):\n#                 boxes = outputs[i]['boxes'].data.cpu().numpy()\n#                 scores = outputs[i]['scores'].data.cpu().numpy()\n#                 gt_boxes = targets[i]['boxes'].cpu().numpy()\n#                 preds_sorted_idx = np.argsort(scores)[::-1]\n#                 preds_sorted = boxes[preds_sorted_idx]\n#                 image_precision = calculate_image_precision(preds_sorted,\n#                                                             gt_boxes,\n#                                                             thresholds = iou_thresholds,\n#                                                             form = 'pascal_voc')\n#                 validation_image_precisions.append(image_precision)\n\n#     valid_prec = np.mean(validation_image_precisions)\n        \n#     return valid_prec","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#original\ndef eval_fn(data_loader, model, device):\n    model.eval()  # Set model to evaluation mode\n    summary_loss_eval = AverageMeter()  # To track loss during evaluation\n    iou_thresholds = [x for x in np.arange(0.5, 0.76, 0.05)]  # IoU thresholds for evaluation\n    validation_image_precisions = []  # To store precision values for each image\n    \n    # Disable gradient calculation to save memory and computation\n    with torch.no_grad():\n        tk0 = tqdm(data_loader, total=len(data_loader))  # Progress bar\n        for step, (images, targets, image_ids) in enumerate(tk0):\n            # Move images and targets to the device (GPU/CPU)\n            images = list(image.to(device) for image in images)\n            targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n            # Get model outputs (predicted boxes, scores, etc.)\n            outputs = model(images)\n            \n            # Iterate over each image in the batch\n            for i, image in enumerate(images):\n                # Extract predicted boxes and scores for each image\n                boxes = outputs[i]['boxes'].data.cpu().numpy()  # Predicted boxes\n                scores = outputs[i]['scores'].data.cpu().numpy()  # Confidence scores\n                gt_boxes = targets[i]['boxes'].cpu().numpy()  # Ground truth boxes\n\n                # Sort predictions by scores in descending order\n                preds_sorted_idx = np.argsort(scores)[::-1]  # Highest scores first\n                preds_sorted = boxes[preds_sorted_idx]  # Sort boxes by scores\n\n                # Calculate image precision at multiple IoU thresholds\n                image_precision = calculate_image_precision(\n                    preds_sorted, gt_boxes, thresholds=iou_thresholds, form='pascal_voc'\n                )\n                validation_image_precisions.append(image_precision)  # Store precision for the image\n\n    # Calculate the mean precision across all images in the validation set\n    valid_prec = np.mean(validation_image_precisions)\n    \n    return valid_prec  # Return the average validation precision","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from torchvision.ops import box_iou\n\ndef calculate_map(outputs, targets, iou_thresholds):\n    \"\"\"\n    Calculates mAP for a batch of images.\n    \"\"\"\n    aps = []\n    for threshold in iou_thresholds:\n        tp, fp, fn = 0, 0, 0\n        for output, target in zip(outputs, targets):\n            pred_boxes = output['boxes'].cpu().numpy()\n            pred_scores = output['scores'].cpu().numpy()\n            gt_boxes = target['boxes'].cpu().numpy()\n\n            if len(pred_boxes) == 0:\n                fn += len(gt_boxes)\n                continue\n            \n            if len(gt_boxes) == 0:\n                fp += len(pred_boxes)\n                continue\n\n            ious = box_iou(torch.tensor(pred_boxes), torch.tensor(gt_boxes)).numpy()\n            matches = ious >= threshold\n\n            tp += matches.sum()\n            fp += len(pred_boxes) - matches.sum()\n            fn += len(gt_boxes) - matches.sum()\n\n        # Calculate precision and recall\n        precision = tp / (tp + fp) if tp + fp > 0 else 0\n        recall = tp / (tp + fn) if tp + fn > 0 else 0\n\n        # Average precision over IoU thresholds\n        ap = precision * recall\n        aps.append(ap)\n    \n    return np.mean(aps) if aps else 0.0","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def eval_fn(data_loader, model, device):\n    model.eval()\n    iou_thresholds = np.arange(0.5, 0.95, 0.05)  # IoU thresholds for mAP\n    all_maps = []  # To store mAP scores\n\n    with torch.no_grad():\n        for images, targets, _ in tqdm(data_loader, total=len(data_loader)):\n            images = list(image.to(device) for image in images)\n            targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n            outputs = model(images)\n            batch_map = calculate_map(outputs, targets, iou_thresholds)\n            all_maps.append(batch_map)\n\n    final_map = np.mean(all_maps)  # Mean mAP over all validation images\n    return final_map","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Engine","metadata":{}},{"cell_type":"markdown","source":"In this section we will do the actual training, comining the previous defined functions to a full pipeline.","metadata":{}},{"cell_type":"code","source":"# original\ndef run(fold):\n    summary_loss = AverageMeter()\n    \n    # split data in training and validation set based on the fold\n    df_train = df_folds[df_folds['fold'] != fold]\n    df_valid = df_folds[df_folds['fold'] == fold]\n    \n    # get data loaders\n    train_dataset = get_train_datset(df_train)\n    train_data_loader = get_train_data_loader(train_dataset, batch_size = BATCH_SIZE)\n    \n    validation_dataset = get_validation_datset(df_valid)\n    validation_data_loader = get_validation_data_loader(validation_dataset, batch_size = 16)\n          \n    # get GPU device\n    device = torch.device('cuda')\n    \n    # get model\n    model = get_model()\n    model = model.to(device)\n    \n    # get all trainable parameters for the optimizer\n    params = [p for p in model.parameters() if p.requires_grad]\n    \n    # get the configured optimizer\n    if Adam:\n        optimizer = torch.optim.Adam(params, **Adam_config)\n    else:\n        optimizer = torch.optim.SGD(params, **SGD_config)\n        \n    best_precision = 0.01\n    for epoch in range(EPOCHS):\n        \n        # reset loss for each new epoch\n        summary_loss.reset()\n                                \n        train_loss = train_fn(train_data_loader, \n                              model, optimizer, \n                              device, \n                              scheduler = None, \n                              epoch = epoch)\n        \n        valid_precision = eval_fn(validation_data_loader, \n                                  model,\n                                  device)\n        \n        print('|EPOCH {}| TRAIN_LOSS {}| VAL_PRECISION {}|'.format(\n            epoch+1,\n            train_loss.avg,\n            valid_precision))\n        \n        if valid_precision > best_precision:\n            best_precision = valid_precision\n            print('Best model found for Epoch {}'.format(epoch+1))\n            torch.save(model.state_dict(), f'FRCNN_best_{fold}.pth')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def run(fold):\n    print(f\"Running Fold {fold}...\")\n    \n    # Split data in training and validation set based on the fold\n    df_train = df_folds[df_folds['fold'] != fold]\n    df_valid = df_folds[df_folds['fold'] == fold]\n    \n    # Get data loaders\n    train_dataset = WheatDataset(\n        image_ids=df_train.index.values,\n        dataframe=bboxes_df,\n        transforms=get_train_transforms()\n    )\n    train_data_loader = DataLoader(\n        train_dataset,\n        batch_size=BATCH_SIZE,\n        shuffle=True,\n        num_workers=4,\n        collate_fn=lambda x: tuple(zip(*x))\n    )\n    \n    validation_dataset = WheatDataset(\n        image_ids=df_valid.index.values,\n        dataframe=bboxes_df,\n        transforms=get_valid_transforms()\n    )\n    validation_data_loader = DataLoader(\n        validation_dataset,\n        batch_size=BATCH_SIZE,\n        shuffle=False,\n        num_workers=4,\n        collate_fn=lambda x: tuple(zip(*x))\n    )\n    \n    # Set device\n    device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')\n    \n    # Get model and move to device\n    model = get_model()\n    model = model.to(device)\n    \n    # Set optimizer\n    params = [p for p in model.parameters() if p.requires_grad]\n    optimizer = torch.optim.Adam(params, **Adam_config) if Adam else torch.optim.SGD(params, **SGD_config)\n    \n    # Training\n    best_precision = 0.01\n    for epoch in range(EPOCHS):\n        train_loss = train_fn(train_data_loader, model, optimizer, device, scheduler=None, epoch=epoch)\n        valid_precision = eval_fn(validation_data_loader, model, device)\n        \n        print(f\"Epoch {epoch+1}: Train Loss = {train_loss.avg:.4f}, Validation Precision = {valid_precision:.4f}\")\n        \n        if valid_precision > best_precision:\n            best_precision = valid_precision\n            print(f\"Saving best model for Fold {fold} (Epoch {epoch+1})...\")\n            torch.save(model.state_dict(), f\"FRCNN_best_fold_{fold}.pth\")\n    \n    # Return the validation data loader and model for external evaluation\n    return validation_data_loader, model","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# def run(fold):\n#     summary_loss = AverageMeter()  # Track the average loss during training\n\n#     # Split data into training and validation sets based on the fold\n#     df_train = df_folds[df_folds['fold'] != fold]\n#     df_valid = df_folds[df_folds['fold'] == fold]\n\n#     # Create training and validation datasets and dataloaders\n#     train_dataset = get_train_dataset(df_train)  # Use updated function for multiclass\n#     train_data_loader = get_train_data_loader(train_dataset, batch_size=BATCH_SIZE)\n\n#     validation_dataset = get_validation_dataset(df_valid)  # Use updated function for multiclass\n#     validation_data_loader = get_validation_data_loader(validation_dataset, batch_size=16)\n\n#     # Get the device (GPU/CPU)\n#     device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n\n#     # Initialize the model and move it to the device\n#     model = get_model()  # Model now handles multiclass detection\n#     model = model.to(device)\n\n#     # Get the parameters that require gradients for the optimizer\n#     params = [p for p in model.parameters() if p.requires_grad]\n\n#     # Configure the optimizer (Adam or SGD)\n#     if Adam:\n#         optimizer = torch.optim.Adam(params, **Adam_config)\n#     else:\n#         optimizer = torch.optim.SGD(params, **SGD_config)\n\n#     # Keep track of the best precision seen during training\n#     best_precision = 0.01\n\n#     # Training loop for multiple epochs\n#     for epoch in range(EPOCHS):\n#         # Reset loss tracking for the new epoch\n#         summary_loss.reset()\n\n#         # Train the model for one epoch and calculate the training loss\n#         train_loss = train_fn(train_data_loader, \n#                               model, \n#                               optimizer, \n#                               device, \n#                               scheduler=None,  # No scheduler for now\n#                               epoch=epoch)\n\n#         # Evaluate the model on the validation set and calculate validation precision\n#         valid_precision = eval_fn(validation_data_loader, \n#                                   model,\n#                                   device)\n\n#         # Output the epoch results: training loss and validation precision\n#         print('|EPOCH {}| TRAIN_LOSS {:.4f}| VAL_PRECISION {:.4f}|'.format(\n#             epoch + 1,\n#             train_loss.avg,\n#             valid_precision))\n\n#         # If the validation precision improves, save the model\n#         if valid_precision > best_precision:\n#             best_precision = valid_precision\n#             print('Best model found for Epoch {}'.format(epoch + 1))\n#             # Save the model weights to disk\n#             torch.save(model.state_dict(), f'FRCNN_best_{fold}.pth')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"run(fold=0)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"fold_maps = []\n\nfor fold in range(n_folds):\n    print(f\"Training Fold {fold}...\")\n    validation_data_loader, model = run(fold)  # Capture the validation loader and model\n    valid_map = eval_fn(validation_data_loader, model, torch.device('cuda'))  # Calculate mAP\n    fold_maps.append(valid_map)\n\n    # Ask the user if they want to continue to the next fold\n    proceed = input(f\"Fold {fold} completed. Do you want to continue to the next fold? (y/n): \")\n    if proceed.lower() != 'y':\n        print(\"Stopping execution.\")\n        break  # Exit the loop if the user doesn't want to continue\n\nprint(f\"Average mAP across folds: {np.mean(fold_maps):.4f}\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"### The model works as expected: \nThe loss is continuously dropping, the VAL_PRECISION is continuously increasing.\nUsing more epochs will lead to much better results and only the best model is saved in your OUTPUT folder.","metadata":{"jp-MarkdownHeadingCollapsed":true}},{"cell_type":"markdown","source":"# Sample visualization of predictions\n\nIn this step we load the best saved model and make our predictions.","metadata":{}},{"cell_type":"code","source":"def view_sample(df_valid,model,device):\n    '''\n    Code merged from Peter's & KnowNothing's great Kernels\n    https://www.kaggle.com/pestipeti/pytorch-starter-fasterrcnn-train\n    https://www.kaggle.com/tanulsingh077/end-to-end-object-detection-with-transformers-detr\n    '''\n    \n    validation_dataset = get_validation_datset(df_valid)\n    validation_data_loader = get_validation_data_loader(validation_dataset, batch_size = 16)\n    \n    # not needed\n    # images, targets, image_ids = next(iter(validation_data_loader))\n    # images = list(img.to(device) for img in images)\n    # targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n    \n    #_,h,w = images[0].shape # for de normalizing images\n    \n    images, targets, image_ids = next(iter(validation_data_loader))\n    images = list(img.to(device) for img in images)\n    targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n    \n    boxes_gt = targets[0]['boxes'].cpu().numpy().astype(np.int32)\n    sample = images[0].permute(1,2,0).cpu().numpy()\n    \n    model.to(device)\n    model.eval()\n    cpu_device = torch.device(\"cpu\")\n    #model.cuda()\n\n    outputs = model(images)\n    outputs = [{k: v.to(cpu_device) for k, v in t.items()} for t in outputs]\n    \n    fig, ax = plt.subplots(1, 1, figsize=(16, 8))\n\n    # paint ground_truth boxes (red)\n    for box in boxes_gt:\n        cv2.rectangle(sample,\n                      (box[0], box[1]),\n                      (box[2], box[3]),\n                      (220, 0, 0), 3)\n        \n    boxes = outputs[0]['boxes'].data.cpu().numpy()\n    scores = outputs[0]['scores'].data.cpu().numpy()\n          \n    # paint predicted boxes (blue)\n    pred_box_count = 0 \n    for box,p in zip(boxes,scores):        \n        if p >0.5:\n            pred_box_count += 1\n            color = (0,0,220) \n            cv2.rectangle(sample,\n                  (box[0], box[1]),\n                  (box[2], box[3]),\n                  color, 2)\n    \n    \n    print(f\"Predicted {pred_box_count} BBoxes (blue); Number of GT BBoxes (red) : {len(boxes_gt)}\")\n    ax.set_axis_off()\n    ax.imshow(sample)       \n\n  ","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = get_model()\n# load the best saved weights\nmodel.load_state_dict(torch.load(\"/kaggle/working/FRCNN_best_fold_0.pth\"))\n# show a prediction\nview_sample(df_folds[df_folds['fold'] == 0],\n            model = model,\n            device = torch.device('cuda'))\n\n# As expected, using less than 20 Epochs is not enough. Good results can be achived with 40+ Epochs, mostly using Colab for longer notebook availability.","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nimport cv2\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom PIL import Image\nimport requests\nfrom io import BytesIO\n\ndef detect_oranges_from_url(image_source, model_path, num_classes=9, score_threshold=0.5, device=None):\n    \"\"\"\n    Detect oranges from an image (local or from a URL) using a saved model and draw bounding boxes for classes 1-9.\n\n    Args:\n        image_source (str): URL or path to the input image.\n        model_path (str): Path to the saved Faster R-CNN model.\n        num_classes (int): Number of classes in the dataset.\n        score_threshold (float): Confidence score threshold for predictions.\n        device (torch.device): The device to use for inference (CPU or GPU).\n\n    Returns:\n        None: Displays the image with bounding boxes and class labels.\n    \"\"\"\n\n    # Load the model\n    if device is None:\n        device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')\n\n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=False, num_classes=num_classes+1)\n    model.load_state_dict(torch.load(model_path))\n    model.to(device)\n    model.eval()\n\n    # Determine if the image source is a URL or a local file\n    if image_source.startswith('http://') or image_source.startswith('https://'):\n        # Load image from URL\n        response = requests.get(image_source)\n        image_pil = Image.open(BytesIO(response.content)).convert(\"RGB\")\n        image_np = np.array(image_pil)\n    else:\n        # Load image from local path\n        image_np = cv2.imread(image_source)\n        image_np = cv2.cvtColor(image_np, cv2.COLOR_BGR2RGB)\n\n    # Preprocess the image\n    image_tensor = torch.tensor(image_np / 255.0, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(device)\n\n    # Make predictions\n    with torch.no_grad():\n        outputs = model(image_tensor)\n\n    # Get the bounding boxes and labels from predictions\n    boxes = outputs[0]['boxes'].cpu().numpy()\n    scores = outputs[0]['scores'].cpu().numpy()\n    labels = outputs[0]['labels'].cpu().numpy()\n\n    # Draw the bounding boxes only for class labels 1 to 9\n    for box, score, label in zip(boxes, scores, labels):\n        if score >= score_threshold and 1 <= label <= 9:\n            x1, y1, x2, y2 = map(int, box)\n            color = (0, 255, 0)  # Green color for bounding boxes\n            cv2.rectangle(image_np, (x1, y1), (x2, y2), color, 2)\n\n            # Draw the class label with confidence score\n            label_text = f'{label}'\n            cv2.putText(image_np, label_text, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)\n\n    # Display the image with bounding boxes\n    plt.figure(figsize=(10, 10))\n    plt.imshow(image_np)\n    plt.axis('off')\n    plt.show()\n\n# Example usage for image URL\ndetect_oranges_from_url(\"https://images.saymedia-content.com/.image/c_limit%2Ccs_srgb%2Cq_auto:eco%2Cw_700/MTc3NTUxMjExNTg2MjAxMDUw/interesting-facts-about-oranges.webp\", \"/kaggle/working/FRCNN_best_fold_0.pth\")\n\n# Example usage for local image\n# detect_oranges_from_url(\"path_to_local_image.jpg\", \"path_to_saved_model.pth\")\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nimport torchvision  # Make sure to import torchvision\nimport cv2\nimport numpy as np\nimport matplotlib.pyplot as plt\n\ndef detect_oranges(image_path, model_path, num_classes=9, score_threshold=0.5, device=None):\n    \"\"\"\n    Detect oranges from a new image using a saved model and draw bounding boxes.\n\n    Args:\n        image_path (str): Path to the input image.\n        model_path (str): Path to the saved Faster R-CNN model.\n        num_classes (int): Number of classes in the dataset.\n        score_threshold (float): Confidence score threshold for predictions.\n        device (torch.device): The device to use for inference (CPU or GPU).\n    \n    Returns:\n        None: Displays the image with bounding boxes and class labels.\n    \"\"\"\n\n    # Load the model\n    if device is None:\n        device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')\n\n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=False, num_classes=num_classes + 1)\n    model.load_state_dict(torch.load(model_path))\n    model.to(device)\n    model.eval()\n\n    # Load and preprocess the image\n    image = cv2.imread(image_path)\n    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n    image_tensor = torch.tensor(image_rgb / 255.0, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(device)\n\n    # Make predictions\n    with torch.no_grad():\n        outputs = model(image_tensor)\n\n    # Get the bounding boxes and labels from predictions\n    boxes = outputs[0]['boxes'].cpu().numpy()\n    scores = outputs[0]['scores'].cpu().numpy()\n    labels = outputs[0]['labels'].cpu().numpy()\n\n    # Draw the bounding boxes\n    for box, score, label in zip(boxes, scores, labels):\n        if score >= score_threshold:\n            x1, y1, x2, y2 = map(int, box)\n            color = (0, 255, 0)  # Green color for bounding boxes\n            cv2.rectangle(image, (x1, y1), (x2, y2), color, 2)\n\n            # Draw the class label with confidence score\n            label_text = f'{label}'  # You may want to format this for clarity\n            cv2.putText(image, label_text, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)\n\n            # Print predicted labels and scores\n            print(f'Predicted label: {label}, Score: {score:.2f}, Box: {box}')\n\n    # Display the image with bounding boxes\n    plt.figure(figsize=(10, 10))\n    plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))\n    plt.axis('off')\n    plt.show()\n\n# Example usage\ndetect_oranges(\"/kaggle/input/oranges-dataset-1955/Orange Yield Estimation 1955/test/Vid-12-frame-123.jpg\", \"/kaggle/working/FRCNN_best_fold_0.pth\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nimport torchvision\nimport cv2\nimport numpy as np\nimport matplotlib.pyplot as plt\n\ndef detect_oranges_correctly(image_path, model_path, num_classes=9, score_threshold=0.5, iou_threshold=0.5, device=None):\n    \"\"\"\n    Detect oranges from a new image using a saved model, handle overlapping boxes, and count the total number of oranges.\n\n    Args:\n        image_path (str): Path to the input image.\n        model_path (str): Path to the saved Faster R-CNN model.\n        num_classes (int): Number of classes in the dataset.\n        score_threshold (float): Confidence score threshold for predictions.\n        iou_threshold (float): IoU threshold for non-maximum suppression (NMS).\n        device (torch.device): The device to use for inference (CPU or GPU).\n    \n    Returns:\n        int: The total count of oranges in the image.\n    \"\"\"\n\n    # Load the model\n    if device is None:\n        device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')\n\n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=False, num_classes=num_classes + 1)\n    model.load_state_dict(torch.load(model_path))\n    model.to(device)\n    model.eval()\n\n    # Load and preprocess the image\n    image = cv2.imread(image_path)\n    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n    image_tensor = torch.tensor(image_rgb / 255.0, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(device)\n\n    # Make predictions\n    with torch.no_grad():\n        outputs = model(image_tensor)\n\n    # Get the bounding boxes, scores, and labels from predictions\n    boxes = outputs[0]['boxes']\n    scores = outputs[0]['scores']\n    labels = outputs[0]['labels']\n\n    # Apply score threshold\n    valid_indices = scores >= score_threshold\n    boxes = boxes[valid_indices].cpu().numpy()\n    scores = scores[valid_indices].cpu().numpy()\n    labels = labels[valid_indices].cpu().numpy()\n\n    # Apply non-maximum suppression (NMS)\n    keep_indices = torchvision.ops.nms(torch.tensor(boxes), torch.tensor(scores), iou_threshold)\n    boxes = boxes[keep_indices.numpy()]\n    scores = scores[keep_indices.numpy()]\n    labels = labels[keep_indices.numpy()]\n\n    # Calculate the total count of oranges by summing the class labels\n    total_oranges = int(labels.sum())\n\n    # Draw the bounding boxes\n    for box, score, label in zip(boxes, scores, labels):\n        x1, y1, x2, y2 = map(int, box)\n        color = (0, 255, 0)  # Green for bounding boxes\n        cv2.rectangle(image, (x1, y1), (x2, y2), color, 2)\n\n        # Draw the class label and score\n        label_text = f'{label}'\n        cv2.putText(image, label_text, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)\n\n        # Print predicted labels and scores\n        print(f'Predicted label: {label}, Score: {score:.2f}, Box: {box}')\n\n    # Display the total count of oranges on the image\n    cv2.putText(image, f'Total Oranges: {total_oranges}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)\n\n    # Display the image with bounding boxes\n    plt.figure(figsize=(10, 10))\n    plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))\n    plt.axis('off')\n    plt.show()\n\n    # Return the total count of oranges\n    return total_oranges\n\n# Example usage\nimage_path = \"/kaggle/input/orange-yield-detection/Orange Yield Detection/test/Vid-12-frame-123.jpg\"\nmodel_path = \"/kaggle/working/FRCNN_best_fold_0.pth\"\ntotal_oranges = detect_oranges_correctly(image_path, model_path)\nprint(f'Total Oranges Detected: {total_oranges}')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nimport torchvision\nimport cv2\nimport numpy as np\nimport matplotlib.pyplot as plt\n\ndef detect_outer_oranges(image_path, model_path, num_classes=9, score_threshold=0.5, iou_threshold=0.5, device=None):\n    \"\"\"\n    Detect oranges from a new image using a saved model, handle nested boxes, and count the total number of outer boxes.\n\n    Args:\n        image_path (str): Path to the input image.\n        model_path (str): Path to the saved Faster R-CNN model.\n        num_classes (int): Number of classes in the dataset.\n        score_threshold (float): Confidence score threshold for predictions.\n        iou_threshold (float): IoU threshold for non-maximum suppression (NMS).\n        device (torch.device): The device to use for inference (CPU or GPU).\n    \n    Returns:\n        int: The total count of oranges based on outer bounding boxes.\n    \"\"\"\n\n    # Load the model\n    if device is None:\n        device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')\n\n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=False, num_classes=num_classes + 1)\n    model.load_state_dict(torch.load(model_path))\n    model.to(device)\n    model.eval()\n\n    # Load and preprocess the image\n    image = cv2.imread(image_path)\n    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n    image_tensor = torch.tensor(image_rgb / 255.0, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(device)\n\n    # Make predictions\n    with torch.no_grad():\n        outputs = model(image_tensor)\n\n    # Get the bounding boxes, scores, and labels from predictions\n    boxes = outputs[0]['boxes']\n    scores = outputs[0]['scores']\n    labels = outputs[0]['labels']\n\n    # Apply score threshold\n    valid_indices = scores >= score_threshold\n    boxes = boxes[valid_indices].cpu().numpy()\n    scores = scores[valid_indices].cpu().numpy()\n    labels = labels[valid_indices].cpu().numpy()\n\n    # Apply non-maximum suppression (NMS)\n    keep_indices = torchvision.ops.nms(torch.tensor(boxes), torch.tensor(scores), iou_threshold)\n    boxes = boxes[keep_indices.numpy()]\n    scores = scores[keep_indices.numpy()]\n    labels = labels[keep_indices.numpy()]\n\n    # Identify and retain only outer boxes\n    outer_boxes = []\n    for i, box1 in enumerate(boxes):\n        x1_min, y1_min, x1_max, y1_max = box1\n        is_outer = True\n        for j, box2 in enumerate(boxes):\n            if i != j:\n                x2_min, y2_min, x2_max, y2_max = box2\n                # Check if box1 is completely inside box2\n                if x1_min >= x2_min and y1_min >= y2_min and x1_max <= x2_max and y1_max <= y2_max:\n                    is_outer = False\n                    break\n        if is_outer:\n            outer_boxes.append((box1, labels[i], scores[i]))\n\n    # Calculate the total count of oranges using only outer boxes\n    total_oranges = int(sum(label for _, label, _ in outer_boxes))\n\n    # Draw the bounding boxes\n    for box, label, score in outer_boxes:\n        x1, y1, x2, y2 = map(int, box)\n        color = (0, 255, 0)  # Green for bounding boxes\n        cv2.rectangle(image, (x1, y1), (x2, y2), color, 2)\n\n        # Draw the class label and score\n        label_text = f'{label}'\n        cv2.putText(image, label_text, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)\n\n        # Print predicted labels and scores\n        print(f'Predicted label: {label}, Score: {score:.2f}, Box: {box}')\n\n    # Display the total count of oranges on the image\n    cv2.putText(image, f'Total Oranges: {total_oranges}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)\n\n    # Display the image with bounding boxes\n    plt.figure(figsize=(10, 10))\n    plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))\n    plt.axis('off')\n    plt.show()\n\n    # Return the total count of oranges\n    return total_oranges\n\n# Example usage\nimage_path = \"/kaggle/input/oranges-dataset-2700/Dataset 2700/Test/Vid-12-frame-235.jpg\"\nmodel_path = \"/kaggle/working/FRCNN_best_fold_0.pth\"\ntotal_oranges = detect_outer_oranges(image_path, model_path)\nprint(f'Total Oranges Detected: {total_oranges}')\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Conclusion\n\nAs Yolov5 is not really allowed due to its GPLv3 license (see [discussions](https://www.kaggle.com/c/global-wheat-detection/discussion/163433)), most probably FasterRCCN, EfficientDet or a combination of their results will win this competition. \n\nThank you for reading!","metadata":{}},{"cell_type":"code","source":"import os\nimport numpy as np \nimport pandas as pd \nimport random\nimport time\nfrom tqdm import tqdm_notebook as tqdm  # Progress bar\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.metrics import confusion_matrix\n\n# PyTorch\nimport torch\nimport torch.nn as nn\nfrom torch.utils.data import Dataset, DataLoader\nfrom torch.utils.data.sampler import SequentialSampler, RandomSampler\n\n# Torchvision\nimport torchvision\nfrom torchvision.models.detection.faster_rcnn import FastRCNNPredictor\nfrom torchvision.ops import box_iou\n\n# Albumentations\nimport albumentations as A\nfrom albumentations.pytorch.transforms import ToTensorV2\n\n# Sklearn\nfrom sklearn.model_selection import StratifiedKFold\n\n# OpenCV\nimport cv2\n\n# Glob\nfrom glob import glob\n\n# Suppress warnings\nimport warnings\nwarnings.filterwarnings('ignore')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Check GPU availability\ngpu_info = !nvidia-smi\ngpu_info = '\\n'.join(gpu_info)\nif gpu_info.find('failed') >= 0:\n    print('Select the Runtime > \"Change runtime type\" menu to enable a GPU accelerator, ')\n    print('and then re-execute this cell.')\nelse:\n    print(gpu_info)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Configuration\nn_folds = 5\nseed = 2020\nnum_classes = 10\nBATCH_SIZE = 4\nLR = 0.05\nEPOCHS = 5\nimg_size_training = 800\n\n# Optimizer configuration\nAdam = False\nif Adam: \n    Adam_config = {\"lr\": 0.001, \"betas\": (0.9, 0.999), \"eps\": 1e-08}\nelse:\n    SGD_config = {\"lr\": 0.001, \"momentum\": 0.9, \"weight_decay\": 0.001}","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Seed everything for reproducibility\ndef seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = True\nseed_everything(seed)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load dataset\nbboxes_df = pd.read_csv('/kaggle/input/oranges-dataset-2700/Dataset 2700/train2700.csv')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Parse bounding boxes\nbboxs = np.stack(bboxes_df['bbox'].apply(lambda x: np.fromstring(x[1:-1], sep=',')))\nfor i, column in enumerate(['x', 'y', 'w', 'h']):\n    bboxes_df[column] = bboxs[:, i]\nbboxes_df.drop(columns=['bbox'], inplace=True)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Create stratified folds\nskf = StratifiedKFold(n_splits=n_folds, shuffle=True, random_state=seed)\ndf_folds = bboxes_df[['image_id']].copy()\ndf_folds.loc[:, 'bbox_count'] = 1\ndf_folds = df_folds.groupby('image_id').count()\ndf_folds.loc[:, 'source'] = bboxes_df[['image_id', 'source']].groupby('image_id').min()['source']\ndf_folds.loc[:, 'stratify_group'] = np.char.add(\n    df_folds['source'].values.astype(str),\n    df_folds['bbox_count'].apply(lambda x: f'_{x // 15}').values.astype(str))\ndf_folds.loc[:, 'fold'] = 0\n\nfor fold_number, (train_index, val_index) in enumerate(skf.split(X=df_folds.index, y=df_folds['stratify_group'])):\n    df_folds.loc[df_folds.iloc[val_index].index, 'fold'] = fold_number\n\n# Dataset directory\nDIR_TRAIN = '/kaggle/input/oranges-dataset-2700/Dataset 2700/Train'","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Custom Dataset Class\nclass WheatDataset(Dataset):\n    def __init__(self, image_ids, dataframe, transforms=None):\n        self.image_ids = image_ids\n        self.df = dataframe\n        self.transforms = transforms\n        \n    def __len__(self):\n        return self.image_ids.shape[0]\n    \n    def __getitem__(self, index):\n        image_id = self.image_ids[index]\n        records = self.df[self.df['image_id'] == image_id]\n        \n        # Load and normalize image\n        image = cv2.imread(f'{DIR_TRAIN}/{image_id}.jpg', cv2.IMREAD_COLOR)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB).astype(np.float32)\n        image /= 255.0\n        \n        # Adjust bounding boxes from COCO format to Pascal VOC\n        boxes = records[['x', 'y', 'w', 'h']].values\n        boxes[:, 2] = boxes[:, 0] + boxes[:, 2]\n        boxes[:, 3] = boxes[:, 1] + boxes[:, 3]\n        \n        # Convert labels to tensor\n        labels = torch.tensor(records['class_id'].values, dtype=torch.int64)\n        \n        area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])\n        area = torch.as_tensor(area, dtype=torch.float32)\n        iscrowd = torch.zeros((records.shape[0],), dtype=torch.int64)\n        \n        target = {\n            'boxes': torch.as_tensor(boxes, dtype=torch.float32),\n            'labels': labels,\n            'image_id': torch.tensor([index]),\n            'area': area,\n            'iscrowd': iscrowd\n        }\n        \n        # Apply transformations if any\n        if self.transforms:\n            sample = {\n                'image': image,\n                'bboxes': target['boxes'],\n                'labels': labels\n            }\n            sample = self.transforms(**sample)\n            image = sample['image']\n            target['boxes'] = torch.as_tensor(sample['bboxes'], dtype=torch.float32)\n        \n        return image, target, image_id","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Albumentations for training\ndef get_train_transforms():\n    return A.Compose(\n        [\n            A.OneOf([\n                A.HueSaturationValue(hue_shift_limit=0.2, sat_shift_limit=0.2, val_shift_limit=0.2, p=0.3),\n                A.RandomBrightnessContrast(brightness_limit=0.2, contrast_limit=0.2, p=0.3),\n                A.RGBShift(r_shift_limit=20/255, g_shift_limit=20/255, b_shift_limit=10/255, p=0.3)\n            ], p=0.2),\n            A.OneOf([\n                A.RandomGamma(gamma_limit=(80, 120), p=0.3),\n                A.Blur(p=0.6),\n                A.GaussNoise(var_limit=(0.01, 0.05), mean=0, p=0.05),\n                A.ToGray(p=0.05)\n            ], p=0.1),\n            A.OneOf([\n                A.HorizontalFlip(p=1),\n                A.VerticalFlip(p=1),\n                A.Transpose(p=1),\n                A.RandomRotate90(p=1)\n            ], p=0.7),\n            A.RandomFog(fog_coef_lower=0.1, fog_coef_upper=0.2, p=0.02),\n            A.RandomSizedBBoxSafeCrop(img_size_training, img_size_training, p=0.05),\n            A.Resize(height=img_size_training, width=img_size_training, p=1),\n            A.Cutout(num_holes=random.randint(1, 6), max_h_size=64, max_w_size=64, fill_value=0, p=0.15),\n            ToTensorV2(p=1.0),\n        ],\n        p=1.0,\n        bbox_params={\n            'format': 'pascal_voc',\n            'label_fields': ['labels']\n        }\n    )\n\n# Albumentations for validation\ndef get_valid_transforms():\n    return A.Compose([\n        A.Resize(height=img_size_training, width=img_size_training, p=1),\n        ToTensorV2(p=1.0)\n    ], bbox_params={\n        'format': 'pascal_voc',\n        'label_fields': ['labels']\n    })\n\n# Helper functions for dataset and dataloader\ndef get_validation_dataset(df):\n    return WheatDataset(\n        image_ids=df.index.values,\n        dataframe=bboxes_df,\n        transforms=get_valid_transforms()\n    )\n    \ndef get_train_dataset(df):    \n    return WheatDataset(\n        image_ids=df.index.values,\n        dataframe=bboxes_df,\n        transforms=get_train_transforms()\n    )\n\ndef get_validation_data_loader(valid_dataset, batch_size=16):\n    return DataLoader(\n        valid_dataset,\n        batch_size=batch_size,\n        shuffle=False,\n        num_workers=4,\n        collate_fn=collate_fn\n    )    \n\ndef get_train_data_loader(train_dataset, batch_size=16):\n    return DataLoader(\n        train_dataset,\n        batch_size=batch_size,\n        shuffle=False,\n        num_workers=4,\n        collate_fn=collate_fn\n    ) \n\ndef collate_fn(batch):\n    return tuple(zip(*batch))","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Model definition\ndef get_model():    \n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)\n    in_features = model.roi_heads.box_predictor.cls_score.in_features\n    model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)\n    return model","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Average Meter for tracking loss\nclass AverageMeter:\n    def __init__(self):\n        self.reset()\n    \n    def reset(self):\n        self.val = 0\n        self.avg = 0\n        self.sum = 0\n        self.count = 0\n    \n    def update(self, val, n=1):\n        self.val = val\n        self.sum += val * n\n        self.count += n\n        self.avg = self.sum / self.count","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Training function\ndef train_fn(data_loader, model, optimizer, device, scheduler, epoch):\n    model.train()\n    summary_loss = AverageMeter()\n    tk0 = tqdm(data_loader, total=len(data_loader))\n    \n    for step, (images, targets, image_ids) in enumerate(tk0):   \n        if len(targets) < 1:\n            targets = [{'boxes': torch.zeros((0, 4)).to(device), 'labels': torch.zeros(0).to(device)}]\n            \n        images = list(image.to(device) for image in images)\n        targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n        loss_dict = model(images, targets)        \n        losses = sum(loss for loss in loss_dict.values())\n\n        optimizer.zero_grad()\n        losses.backward()\n        optimizer.step()\n        \n        if scheduler is not None:\n            scheduler.step()\n        \n        summary_loss.update(losses.item(), len(images))\n        tk0.set_postfix(loss=summary_loss.avg)\n    \n    return summary_loss\n\n# Function to calculate mAP\ndef calculate_map(outputs, targets, iou_thresholds):\n    \"\"\"\n    Calculates mAP for a batch of images.\n    \"\"\"\n    aps = []\n    for threshold in iou_thresholds:\n        tp, fp, fn = 0, 0, 0\n        for output, target in zip(outputs, targets):\n            pred_boxes = output['boxes'].cpu().numpy()\n            pred_scores = output['scores'].cpu().numpy()\n            gt_boxes = target['boxes'].cpu().numpy()\n\n            if len(pred_boxes) == 0:\n                fn += len(gt_boxes)\n                continue\n            \n            if len(gt_boxes) == 0:\n                fp += len(pred_boxes)\n                continue\n\n            ious = box_iou(torch.tensor(pred_boxes), torch.tensor(gt_boxes)).numpy()\n            matches = ious >= threshold\n\n            tp += matches.sum()\n            fp += len(pred_boxes) - matches.sum()\n            fn += len(gt_boxes) - matches.sum()\n\n        # Calculate precision and recall\n        precision = tp / (tp + fp) if tp + fp > 0 else 0\n        recall = tp / (tp + fn) if tp + fn > 0 else 0\n\n        # Average precision over IoU thresholds\n        ap = precision * recall\n        aps.append(ap)\n    \n    return np.mean(aps) if aps else 0.0\n\n# Evaluation function with AP per class and confusion matrix\ndef eval_fn(data_loader, model, device, num_classes, class_names):\n    model.eval()\n    iou_thresholds = np.arange(0.5, 0.95, 0.05)\n    all_maps = []\n    all_outputs = []\n    all_targets = []\n\n    with torch.no_grad():\n        for images, targets, _ in tqdm(data_loader, total=len(data_loader)):\n            images = list(image.to(device) for image in images)\n            targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n            outputs = model(images)\n            batch_map = calculate_map(outputs, targets, iou_thresholds)\n            all_maps.append(batch_map)\n            all_outputs.extend(outputs)\n            all_targets.extend(targets)\n\n    final_map = np.mean(all_maps)\n\n    # Calculate AP per class\n    mean_aps = calculate_ap_per_class(all_outputs, all_targets, iou_thresholds, num_classes)\n    print(\"Average Precision per Class:\", mean_aps)\n\n    # Generate and plot confusion matrix\n    confusion_matrix = generate_confusion_matrix(all_outputs, all_targets, num_classes)\n    plot_confusion_matrix(confusion_matrix, class_names)\n\n    # Plot AP per class\n    plot_ap_per_class(mean_aps, class_names)\n\n    return final_map\n\n# Function to calculate AP per class\ndef calculate_ap_per_class(outputs, targets, iou_thresholds, num_classes):\n    aps = {cls: [] for cls in range(num_classes)}\n    for threshold in iou_thresholds:\n        for cls in range(num_classes):\n            tp, fp, fn = 0, 0, 0\n            for output, target in zip(outputs, targets):\n                pred_boxes = output['boxes'].cpu().numpy()\n                pred_scores = output['scores'].cpu().numpy()\n                pred_labels = output['labels'].cpu().numpy()\n                gt_boxes = target['boxes'].cpu().numpy()\n                gt_labels = target['labels'].cpu().numpy()\n\n                if len(pred_boxes) == 0:\n                    fn += len(gt_boxes[gt_labels == cls])\n                    continue\n                \n                if len(gt_boxes) == 0:\n                    fp += len(pred_boxes[pred_labels == cls])\n                    continue\n\n                ious = box_iou(torch.tensor(pred_boxes[pred_labels == cls]), torch.tensor(gt_boxes[gt_labels == cls])).numpy()\n                matches = ious >= threshold\n\n                tp += matches.sum()\n                fp += len(pred_boxes[pred_labels == cls]) - matches.sum()\n                fn += len(gt_boxes[gt_labels == cls]) - matches.sum()\n\n            precision = tp / (tp + fp) if tp + fp > 0 else 0\n            recall = tp / (tp + fn) if tp + fn > 0 else 0\n            ap = precision * recall\n            aps[cls].append(ap)\n    \n    mean_aps = {cls: np.mean(aps[cls]) if aps[cls] else 0.0 for cls in range(num_classes)}\n    return mean_aps\n\n# Function to generate confusion matrix\ndef generate_confusion_matrix(outputs, targets, num_classes):\n    confusion_matrix = np.zeros((num_classes, num_classes))\n    for output, target in zip(outputs, targets):\n        pred_labels = output['labels'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        for pred_label, gt_label in zip(pred_labels, gt_labels):\n            confusion_matrix[gt_label][pred_label] += 1\n\n    return confusion_matrix\n\n# Function to plot confusion matrix\ndef plot_confusion_matrix(confusion_matrix, class_names):\n    plt.figure(figsize=(10, 10))\n    sns.heatmap(confusion_matrix, annot=True, fmt='g', cmap='Blues', xticklabels=class_names, yticklabels=class_names)\n    plt.xlabel('Predicted')\n    plt.ylabel('Actual')\n    plt.title('Confusion Matrix')\n    plt.show()\n\n# Function to plot AP per class\ndef plot_ap_per_class(mean_aps, class_names):\n    plt.figure(figsize=(10, 5))\n    plt.bar(range(len(mean_aps)), list(mean_aps.values()), align='center')\n    plt.xticks(range(len(mean_aps)), class_names, rotation=45)\n    plt.xlabel('Class')\n    plt.ylabel('Average Precision')\n    plt.title('Average Precision per Class')\n    plt.show()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Main training loop\ndef run(fold):\n    summary_loss = AverageMeter()\n    \n    # Split data into training and validation sets\n    df_train = df_folds[df_folds['fold'] != fold]\n    df_valid = df_folds[df_folds['fold'] == fold]\n    \n    # Get data loaders\n    train_dataset = get_train_dataset(df_train)\n    train_data_loader = get_train_data_loader(train_dataset, batch_size=BATCH_SIZE)\n    \n    validation_dataset = get_validation_dataset(df_valid)\n    validation_data_loader = get_validation_data_loader(validation_dataset, batch_size=16)\n          \n    # Get GPU device\n    device = torch.device('cuda')\n    \n    # Get model\n    model = get_model()\n    model = model.to(device)\n    \n    # Get optimizer\n    params = [p for p in model.parameters() if p.requires_grad]\n    if Adam:\n        optimizer = torch.optim.Adam(params, **Adam_config)\n    else:\n        optimizer = torch.optim.SGD(params, **SGD_config)\n        \n    best_precision = 0.01\n    for epoch in range(EPOCHS):\n        summary_loss.reset()\n        train_loss = train_fn(train_data_loader, model, optimizer, device, scheduler=None, epoch=epoch)\n        \n        valid_precision = eval_fn(validation_data_loader, model, device, num_classes, class_names)\n        \n        print(f'|EPOCH {epoch+1}| TRAIN_LOSS {train_loss.avg}| VAL_PRECISION {valid_precision}|')\n        \n        if valid_precision > best_precision:\n            best_precision = valid_precision\n            print(f'Best model found for Epoch {epoch+1}')\n            torch.save(model.state_dict(), f'FRCNN_best_{fold}.pth')\n    \n    # Return validation_data_loader and model\n    return validation_data_loader, model\n\n\n# Class names\nclass_names = ['class_0', 'class_1', 'class_2', 'class_3', 'class_4', 'class_5', 'class_6', 'class_7', 'class_8', 'class_9']","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Execute training and evaluation\nfold_maps = []\nfor fold in range(n_folds):\n    print(f\"Training Fold {fold}...\")\n    validation_data_loader, model = run(fold)  # Unpack returned values\n    valid_map = eval_fn(validation_data_loader, model, torch.device('cuda'), num_classes, class_names)\n    fold_maps.append(valid_map)\n\n    proceed = input(f\"Fold {fold} completed. Do you want to continue to the next fold? (y/n): \")\n    if proceed.lower() != 'y':\n        print(\"Stopping execution.\")\n        break\n\nprint(f\"Average mAP across folds: {np.mean(fold_maps):.4f}\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nimport torchvision\nimport cv2\nimport numpy as np\nimport matplotlib.pyplot as plt\n\ndef detect_outer_oranges(image_path, model_path, num_classes=9, score_threshold=0.5, iou_threshold=0.5, device=None):\n    \"\"\"\n    Detect oranges from a new image using a saved model, handle nested boxes, and count the total number of outer boxes.\n\n    Args:\n        image_path (str): Path to the input image.\n        model_path (str): Path to the saved Faster R-CNN model.\n        num_classes (int): Number of classes in the dataset.\n        score_threshold (float): Confidence score threshold for predictions.\n        iou_threshold (float): IoU threshold for non-maximum suppression (NMS).\n        device (torch.device): The device to use for inference (CPU or GPU).\n    \n    Returns:\n        int: The total count of oranges based on outer bounding boxes.\n    \"\"\"\n\n    # Load the model\n    if device is None:\n        device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')\n\n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=False, num_classes=num_classes + 1)\n    model.load_state_dict(torch.load(model_path))\n    model.to(device)\n    model.eval()\n\n    # Load and preprocess the image\n    image = cv2.imread(image_path)\n    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n    image_tensor = torch.tensor(image_rgb / 255.0, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(device)\n\n    # Make predictions\n    with torch.no_grad():\n        outputs = model(image_tensor)\n\n    # Get the bounding boxes, scores, and labels from predictions\n    boxes = outputs[0]['boxes']\n    scores = outputs[0]['scores']\n    labels = outputs[0]['labels']\n\n    # Apply score threshold\n    valid_indices = scores >= score_threshold\n    boxes = boxes[valid_indices].cpu().numpy()\n    scores = scores[valid_indices].cpu().numpy()\n    labels = labels[valid_indices].cpu().numpy()\n\n    # Apply non-maximum suppression (NMS)\n    keep_indices = torchvision.ops.nms(torch.tensor(boxes), torch.tensor(scores), iou_threshold)\n    boxes = boxes[keep_indices.numpy()]\n    scores = scores[keep_indices.numpy()]\n    labels = labels[keep_indices.numpy()]\n\n    # Identify and retain only outer boxes\n    outer_boxes = []\n    for i, box1 in enumerate(boxes):\n        x1_min, y1_min, x1_max, y1_max = box1\n        is_outer = True\n        for j, box2 in enumerate(boxes):\n            if i != j:\n                x2_min, y2_min, x2_max, y2_max = box2\n                # Check if box1 is completely inside box2\n                if x1_min >= x2_min and y1_min >= y2_min and x1_max <= x2_max and y1_max <= y2_max:\n                    is_outer = False\n                    break\n        if is_outer:\n            outer_boxes.append((box1, labels[i], scores[i]))\n\n    # Calculate the total count of oranges using only outer boxes\n    total_oranges = int(sum(label for _, label, _ in outer_boxes))\n\n    # Draw the bounding boxes\n    for box, label, score in outer_boxes:\n        x1, y1, x2, y2 = map(int, box)\n        color = (0, 255, 0)  # Green for bounding boxes\n        cv2.rectangle(image, (x1, y1), (x2, y2), color, 2)\n\n        # Draw the class label and score\n        label_text = f'{label}'\n        cv2.putText(image, label_text, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)\n\n        # Print predicted labels and scores\n        print(f'Predicted label: {label}, Score: {score:.2f}, Box: {box}')\n\n    # Display the total count of oranges on the image\n    cv2.putText(image, f'Total Oranges: {total_oranges}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)\n\n    # Display the image with bounding boxes\n    plt.figure(figsize=(10, 10))\n    plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))\n    plt.axis('off')\n    plt.show()\n\n    # Return the total count of oranges\n    return total_oranges\n\n# Example usage\nimage_path = \"/kaggle/input/oranges-dataset-1955/Orange Yield Estimation 1955/Images/Vid-0-frame-100.jpg\"\nmodel_path = \"/kaggle/working/FRCNN_best_0.pth\"\ntotal_oranges = detect_outer_oranges(image_path, model_path)\nprint(f'Total Oranges Detected: {total_oranges}')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Import libraries\nimport os\nimport numpy as np\nimport pandas as pd\nimport random\nimport time\nfrom tqdm import tqdm  # Progress bar\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.metrics import confusion_matrix, accuracy_score\nimport matplotlib.patches as patches\n\n# PyTorch\nimport torch\nimport torch.nn as nn\nfrom torch.utils.data import Dataset, DataLoader\nfrom torch.utils.data.sampler import SequentialSampler, RandomSampler\n\n# Torchvision\nimport torchvision\nfrom torchvision.models.detection.faster_rcnn import FastRCNNPredictor\nfrom torchvision.ops import box_iou, nms\n\n# Albumentations\nimport albumentations as A\nfrom albumentations.pytorch.transforms import ToTensorV2\n\n# Sklearn\nfrom sklearn.model_selection import StratifiedKFold\n\n# OpenCV\nimport cv2\n\n# Suppress warnings\nimport warnings\nwarnings.filterwarnings('ignore')\n\n# Check GPU availability\ngpu_info = !nvidia-smi\ngpu_info = '\\n'.join(gpu_info)\nif gpu_info.find('failed') >= 0:\n    print('Select the Runtime > \"Change runtime type\" menu to enable a GPU accelerator, ')\n    print('and then re-execute this cell.')\nelse:\n    print(gpu_info)\n\n# Configuration\nn_folds = 5\nseed = 2020\nnum_classes = 10\nBATCH_SIZE = 4  # Consistent batch size for training and validation\nLR = 0.05\nEPOCHS = 3\nimg_size_training = 800\n\n# Optimizer configuration\nAdam = False\nif Adam:\n    Adam_config = {\"lr\": 0.001, \"betas\": (0.9, 0.999), \"eps\": 1e-08}\nelse:\n    SGD_config = {\"lr\": 0.001, \"momentum\": 0.9, \"weight_decay\": 0.001}\n\n# Seed everything for reproducibility\ndef seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = True\nseed_everything(seed)\n\n# Load dataset\nbboxes_df = pd.read_csv('/kaggle/input/oranges-dataset-2700/Dataset 2700/train2700.csv')\n\n# Parse bounding boxes\nbboxs = np.stack(bboxes_df['bbox'].apply(lambda x: np.fromstring(x[1:-1], sep=',')))\nfor i, column in enumerate(['x', 'y', 'w', 'h']):\n    bboxes_df[column] = bboxs[:, i]\nbboxes_df.drop(columns=['bbox'], inplace=True)\n\n# Create stratified folds\nskf = StratifiedKFold(n_splits=n_folds, shuffle=True, random_state=seed)\ndf_folds = bboxes_df[['image_id']].copy()\ndf_folds.loc[:, 'bbox_count'] = 1\ndf_folds = df_folds.groupby('image_id').count()\ndf_folds.loc[:, 'source'] = bboxes_df[['image_id', 'source']].groupby('image_id').min()['source']\ndf_folds.loc[:, 'stratify_group'] = np.char.add(\n    df_folds['source'].values.astype(str),\n    df_folds['bbox_count'].apply(lambda x: f'_{x // 15}').values.astype(str))\ndf_folds.loc[:, 'fold'] = 0\n\nfor fold_number, (train_index, val_index) in enumerate(skf.split(X=df_folds.index, y=df_folds['stratify_group'])):\n    df_folds.loc[df_folds.iloc[val_index].index, 'fold'] = fold_number\n\n# Dataset directory\nDIR_TRAIN = '/kaggle/input/oranges-dataset-2700/Dataset 2700/Train'\n\n# Custom Dataset Class\nclass WheatDataset(Dataset):\n    def __init__(self, image_ids, dataframe, transforms=None):\n        self.image_ids = image_ids\n        self.df = dataframe\n        self.transforms = transforms\n        \n    def __len__(self):\n        return len(self.image_ids)\n    \n    def __getitem__(self, index):\n        image_id = self.image_ids[index]\n        records = self.df[self.df['image_id'] == image_id]\n        \n        # Load and normalize image\n        image = cv2.imread(f'{DIR_TRAIN}/{image_id}.jpg', cv2.IMREAD_COLOR)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB).astype(np.float32)\n        image /= 255.0\n        \n        # Log image size\n        image_size = image.shape[:2]  # (height, width)\n        \n        # Adjust bounding boxes from COCO format to Pascal VOC\n        boxes = records[['x', 'y', 'w', 'h']].values\n        boxes[:, 2] = boxes[:, 0] + boxes[:, 2]\n        boxes[:, 3] = boxes[:, 1] + boxes[:, 3]\n        \n        # Convert labels to tensor\n        labels = torch.tensor(records['class_id'].values, dtype=torch.int64)\n        \n        area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])\n        area = torch.as_tensor(area, dtype=torch.float32)\n        iscrowd = torch.zeros((records.shape[0],), dtype=torch.int64)\n        \n        target = {\n            'boxes': torch.as_tensor(boxes, dtype=torch.float32),\n            'labels': labels,\n            'image_id': torch.tensor([index]),\n            'area': area,\n            'iscrowd': iscrowd\n        }\n        \n        # Apply transformations if any\n        if self.transforms:\n            sample = {\n                'image': image,\n                'bboxes': target['boxes'],\n                'labels': labels\n            }\n            sample = self.transforms(**sample)\n            image = sample['image']\n            target['boxes'] = torch.as_tensor(sample['bboxes'], dtype=torch.float32)\n        \n        return image, target, image_id, image_size\n\n# Albumentations for training\ndef get_train_transforms():\n    return A.Compose(\n        [\n            A.OneOf([\n                A.HueSaturationValue(hue_shift_limit=0.2, sat_shift_limit=0.2, val_shift_limit=0.2, p=0.3),\n                A.RandomBrightnessContrast(brightness_limit=0.2, contrast_limit=0.2, p=0.3),\n                A.RGBShift(r_shift_limit=20/255, g_shift_limit=20/255, b_shift_limit=10/255, p=0.3)\n            ], p=0.2),\n            A.OneOf([\n                A.RandomGamma(gamma_limit=(80, 120), p=0.3),\n                A.Blur(p=0.6),\n                A.GaussNoise(var_limit=(0.01, 0.05), mean=0, p=0.05),\n                A.ToGray(p=0.05)\n            ], p=0.1),\n            A.OneOf([\n                A.HorizontalFlip(p=1),\n                A.VerticalFlip(p=1),\n                A.Transpose(p=1),\n                A.RandomRotate90(p=1)\n            ], p=0.7),\n            A.RandomFog(fog_coef_lower=0.1, fog_coef_upper=0.2, p=0.02),\n            A.RandomSizedBBoxSafeCrop(img_size_training, img_size_training, p=0.05),\n            A.Resize(height=img_size_training, width=img_size_training, p=1),\n            A.Cutout(num_holes=random.randint(1, 6), max_h_size=64, max_w_size=64, fill_value=0, p=0.15),\n            ToTensorV2(p=1.0),\n        ],\n        p=1.0,\n        bbox_params={\n            'format': 'pascal_voc',\n            'label_fields': ['labels']\n        }\n    )\n\n# Albumentations for validation\ndef get_valid_transforms():\n    return A.Compose([\n        A.Resize(height=img_size_training, width=img_size_training, p=1),\n        ToTensorV2(p=1.0)\n    ], bbox_params={\n        'format': 'pascal_voc',\n        'label_fields': ['labels']\n    })\n\n# Helper functions for dataset and dataloader\ndef get_validation_dataset(df):\n    return WheatDataset(\n        image_ids=df.index.values,\n        dataframe=bboxes_df,\n        transforms=get_valid_transforms()\n    )\n    \ndef get_train_dataset(df):    \n    return WheatDataset(\n        image_ids=df.index.values,\n        dataframe=bboxes_df,\n        transforms=get_train_transforms()\n    )\n\ndef get_validation_data_loader(valid_dataset, batch_size=BATCH_SIZE):  # Use consistent batch size\n    return DataLoader(\n        valid_dataset,\n        batch_size=batch_size,\n        shuffle=False,\n        num_workers=4,\n        collate_fn=collate_fn\n    )    \n\ndef get_train_data_loader(train_dataset, batch_size=BATCH_SIZE):  # Use consistent batch size\n    return DataLoader(\n        train_dataset,\n        batch_size=batch_size,\n        shuffle=False,\n        num_workers=4,\n        collate_fn=collate_fn\n    ) \n\ndef collate_fn(batch):\n    return tuple(zip(*batch))\n\n# Model definition\ndef get_model():    \n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)\n    in_features = model.roi_heads.box_predictor.cls_score.in_features\n    model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)\n    return model\n\n# Average Meter for tracking loss\nclass AverageMeter:\n    def __init__(self):\n        self.reset()\n    \n    def reset(self):\n        self.val = 0\n        self.avg = 0\n        self.sum = 0\n        self.count = 0\n    \n    def update(self, val, n=1):\n        self.val = val\n        self.sum += val * n\n        self.count += n\n        self.avg = self.sum / self.count\n\n# Training function\ndef train_fn(data_loader, model, optimizer, device, scheduler, epoch):\n    model.train()\n    summary_loss = AverageMeter()\n    tk0 = tqdm(data_loader, total=len(data_loader), desc=f\"Training Epoch {epoch + 1}\")\n    \n    for step, (images, targets, image_ids, image_sizes) in enumerate(tk0):   \n        if len(targets) < 1:\n            targets = [{'boxes': torch.zeros((0, 4)).to(device), 'labels': torch.zeros(0).to(device)}]\n            \n        images = list(image.to(device) for image in images)\n        targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n        loss_dict = model(images, targets)        \n        losses = sum(loss for loss in loss_dict.values())\n\n        optimizer.zero_grad()\n        losses.backward()\n        optimizer.step()\n        \n        if scheduler is not None:\n            scheduler.step()\n        \n        summary_loss.update(losses.item(), len(images))\n        tk0.set_postfix(loss=summary_loss.avg)\n    \n    return summary_loss\n\n# Function to calculate mAP\ndef calculate_map(outputs, targets, iou_thresholds):\n    \"\"\"\n    Calculates mAP for a batch of images.\n    \"\"\"\n    aps = []\n    for threshold in iou_thresholds:\n        tp, fp, fn = 0, 0, 0\n        for output, target in zip(outputs, targets):\n            pred_boxes = output['boxes'].cpu().numpy()\n            pred_scores = output['scores'].cpu().numpy()\n            gt_boxes = target['boxes'].cpu().numpy()\n\n            if len(pred_boxes) == 0:\n                fn += len(gt_boxes)\n                continue\n            \n            if len(gt_boxes) == 0:\n                fp += len(pred_boxes)\n                continue\n\n            ious = box_iou(torch.tensor(pred_boxes), torch.tensor(gt_boxes)).numpy()\n            matches = ious >= threshold\n\n            tp += matches.sum()\n            fp += len(pred_boxes) - matches.sum()\n            fn += len(gt_boxes) - matches.sum()\n\n        # Calculate precision and recall\n        precision = tp / (tp + fp) if tp + fp > 0 else 0\n        recall = tp / (tp + fn) if tp + fn > 0 else 0\n\n        # Average precision over IoU thresholds\n        ap = precision * recall\n        aps.append(ap)\n    \n    return np.mean(aps) if aps else 0.0\n\n# Function to calculate F1 score, precision, and recall\ndef calculate_f1_precision_recall(outputs, targets, num_classes):\n    # Initialize counters for TP, FP, FN\n    tp = {cls: 0 for cls in range(num_classes)}\n    fp = {cls: 0 for cls in range(num_classes)}\n    fn = {cls: 0 for cls in range(num_classes)}\n\n    for output, target in zip(outputs, targets):\n        pred_boxes = output['boxes'].cpu().numpy()\n        pred_labels = output['labels'].cpu().numpy()\n        gt_boxes = target['boxes'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        # For each class, calculate TP, FP, FN\n        for cls in range(num_classes):\n            pred_cls = pred_labels == cls\n            gt_cls = gt_labels == cls\n\n            if len(pred_boxes[pred_cls]) == 0 and len(gt_boxes[gt_cls]) == 0:\n                continue  # No predictions or ground truth for this class\n\n            if len(pred_boxes[pred_cls]) == 0:\n                fn[cls] += len(gt_boxes[gt_cls])  # All ground truth are false negatives\n                continue\n\n            if len(gt_boxes[gt_cls]) == 0:\n                fp[cls] += len(pred_boxes[pred_cls])  # All predictions are false positives\n                continue\n\n            # Calculate IoU between predicted and ground truth boxes\n            ious = box_iou(torch.tensor(pred_boxes[pred_cls]), torch.tensor(gt_boxes[gt_cls])).numpy()\n            matches = ious >= 0.5  # IoU threshold of 0.5 for matching\n\n            # Count TP, FP, FN\n            tp[cls] += matches.sum()\n            fp[cls] += len(pred_boxes[pred_cls]) - matches.sum()\n            fn[cls] += len(gt_boxes[gt_cls]) - matches.sum()\n\n    # Calculate precision, recall, and F1 score for each class\n    precision = {cls: tp[cls] / (tp[cls] + fp[cls]) if (tp[cls] + fp[cls]) > 0 else 0 for cls in range(num_classes)}\n    recall = {cls: tp[cls] / (tp[cls] + fn[cls]) if (tp[cls] + fn[cls]) > 0 else 0 for cls in range(num_classes)}\n    f1_score = {cls: 2 * (precision[cls] * recall[cls]) / (precision[cls] + recall[cls]) if (precision[cls] + recall[cls]) > 0 else 0 for cls in range(num_classes)}\n\n    return precision, recall, f1_score\n\ndef visualize_predictions(data_loader, outputs, targets, class_names, num_images=5):\n    indices = np.random.choice(len(data_loader.dataset), num_images, replace=False)\n    \n    for idx in indices:\n        image, target, image_id, _ = data_loader.dataset[idx]\n        output = outputs[idx]\n        \n        # Convert image to numpy for visualization\n        if isinstance(image, torch.Tensor):  # Check if image is a PyTorch Tensor\n            image = image.cpu().numpy()  # Convert to NumPy array\n            image = np.transpose(image, (1, 2, 0))  # Permute dimensions to (height, width, channels)\n            image = (image * 255).astype(np.uint8)  # Scale to [0, 255] and convert to uint8\n        \n        # Create figure and axes with a larger size\n        plt.figure(figsize=(12, 12))  # Increase figure size for better visibility\n        ax = plt.gca()\n        ax.imshow(image)\n        \n        # Plot actual bounding boxes (red)\n        for box, label in zip(target['boxes'], target['labels']):\n            xmin, ymin, xmax, ymax = box\n            rect = patches.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, linewidth=2, edgecolor='red', facecolor='none')\n            ax.add_patch(rect)\n        \n        # Plot predicted bounding boxes (blue)\n        for box, label, score in zip(output['boxes'], output['labels'], output['scores']):\n            xmin, ymin, xmax, ymax = box\n            rect = patches.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, linewidth=2, edgecolor='blue', facecolor='none')\n            ax.add_patch(rect)\n        \n        # Print actual and predicted labels outside the image\n        actual_labels = [class_names[label] for label in target['labels'].cpu().numpy()]\n        predicted_labels = [class_names[label] for label in output['labels'].cpu().numpy()]\n        \n        print(f\"Image ID: {image_id}\")\n        print(f\"Actual Labels: {actual_labels}\")\n        print(f\"Predicted Labels: {predicted_labels}\")\n        print(\"-\" * 50)  # Separator for clarity\n        \n        plt.axis('off')  # Hide axes for better visualization\n        plt.show()\n\n# Evaluation function with AP per class and confusion matrix\ndef eval_fn(data_loader, model, device, num_classes, class_names):\n    model.eval()\n    iou_thresholds = np.arange(0.5, 0.95, 0.05)\n    all_maps = []\n    all_outputs = []\n    all_targets = []\n\n    with torch.no_grad():\n        tk0 = tqdm(data_loader, total=len(data_loader), desc=\"Validation\")\n        for images, targets, _, _ in tk0:\n            images = list(image.to(device) for image in images)\n            targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n            outputs = model(images)\n            batch_map = calculate_map(outputs, targets, iou_thresholds)\n            all_maps.append(batch_map)\n            all_outputs.extend(outputs)\n            all_targets.extend(targets)\n\n    final_map = np.mean(all_maps)\n\n    # Calculate AP per class\n    mean_aps = calculate_ap_per_class(all_outputs, all_targets, iou_thresholds, num_classes)\n    print(\"Average Precision per Class:\", mean_aps)\n\n    # Calculate F1 score, precision, and recall\n    precision, recall, f1_score = calculate_f1_precision_recall(all_outputs, all_targets, num_classes)\n    print(\"Precision per Class:\", precision)\n    print(\"Recall per Class:\", recall)\n    print(\"F1 Score per Class:\", f1_score)\n\n    # Generate and plot confusion matrix\n    confusion_matrix = generate_confusion_matrix(all_outputs, all_targets, num_classes)\n    plot_confusion_matrix(confusion_matrix, class_names)\n\n    # Plot AP per class\n    plot_ap_per_class(mean_aps, class_names)\n\n    # Visualize random images with ground truth and predicted bounding boxes\n    visualize_predictions(data_loader, all_outputs, all_targets, class_names)\n\n    # Calculate estimation accuracy\n    accuracy = calculate_accuracy(all_outputs, all_targets)\n    print(f\"Estimation Accuracy: {accuracy:.2f}%\")\n\n    return final_map\n\n# Function to calculate AP per class\ndef calculate_ap_per_class(outputs, targets, iou_thresholds, num_classes):\n    aps = {cls: [] for cls in range(num_classes)}\n    for threshold in iou_thresholds:\n        for cls in range(num_classes):\n            tp, fp, fn = 0, 0, 0\n            for output, target in zip(outputs, targets):\n                pred_boxes = output['boxes'].cpu().numpy()\n                pred_scores = output['scores'].cpu().numpy()\n                pred_labels = output['labels'].cpu().numpy()\n                gt_boxes = target['boxes'].cpu().numpy()\n                gt_labels = target['labels'].cpu().numpy()\n\n                if len(pred_boxes) == 0:\n                    fn += len(gt_boxes[gt_labels == cls])\n                    continue\n                \n                if len(gt_boxes) == 0:\n                    fp += len(pred_boxes[pred_labels == cls])\n                    continue\n\n                ious = box_iou(torch.tensor(pred_boxes[pred_labels == cls]), torch.tensor(gt_boxes[gt_labels == cls])).numpy()\n                matches = ious >= threshold\n\n                tp += matches.sum()\n                fp += len(pred_boxes[pred_labels == cls]) - matches.sum()\n                fn += len(gt_boxes[gt_labels == cls]) - matches.sum()\n\n            precision = tp / (tp + fp) if tp + fp > 0 else 0\n            recall = tp / (tp + fn) if tp + fn > 0 else 0\n            ap = precision * recall\n            aps[cls].append(ap)\n    \n    mean_aps = {cls: np.mean(aps[cls]) if aps[cls] else 0.0 for cls in range(num_classes)}\n    return mean_aps\n\n# Function to generate confusion matrix\ndef generate_confusion_matrix(outputs, targets, num_classes):\n    confusion_matrix = np.zeros((num_classes, num_classes))\n    for output, target in zip(outputs, targets):\n        pred_labels = output['labels'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        # Only consider images where both predictions and ground truth are non-empty\n        if len(pred_labels) > 0 and len(gt_labels) > 0:\n            # Ensure the number of predictions matches the number of ground truth labels\n            min_length = min(len(pred_labels), len(gt_labels))\n            for pred_label, gt_label in zip(pred_labels[:min_length], gt_labels[:min_length]):\n                confusion_matrix[gt_label][pred_label] += 1\n\n    return confusion_matrix\n\n# Function to plot confusion matrix\ndef plot_confusion_matrix(confusion_matrix, class_names):\n    plt.figure(figsize=(10, 10))\n    sns.heatmap(confusion_matrix, annot=True, fmt='g', cmap='Blues', xticklabels=class_names, yticklabels=class_names)\n    plt.xlabel('Predicted')\n    plt.ylabel('Actual')\n    plt.title('Confusion Matrix')\n    plt.show()\n\n# Function to plot AP per class\ndef plot_ap_per_class(mean_aps, class_names):\n    plt.figure(figsize=(10, 5))\n    plt.bar(range(len(mean_aps)), list(mean_aps.values()), align='center')\n    plt.xticks(range(len(mean_aps)), class_names, rotation=45)\n    plt.xlabel('Class')\n    plt.ylabel('Average Precision')\n    plt.title('Average Precision per Class')\n    plt.show()\n\n# Function to calculate estimation accuracy\ndef calculate_accuracy(outputs, targets):\n    all_preds = []\n    all_targets = []\n    \n    for output, target in zip(outputs, targets):\n        pred_labels = output['labels'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        # Only consider images where both predictions and ground truth are non-empty\n        if len(pred_labels) > 0 and len(gt_labels) > 0:\n            # Ensure the number of predictions matches the number of ground truth labels\n            min_length = min(len(pred_labels), len(gt_labels))\n            all_preds.extend(pred_labels[:min_length])\n            all_targets.extend(gt_labels[:min_length])\n    \n    if len(all_preds) == 0 or len(all_targets) == 0:\n        return 0.0  # Return 0 accuracy if no valid predictions or ground truth\n    \n    accuracy = accuracy_score(all_targets, all_preds) * 100\n    return accuracy\n\n# Function to print class instance sizes\ndef print_class_instance_sizes(data_loader, class_names):\n    class_counts = {cls: 0 for cls in range(len(class_names))}\n    \n    for _, targets, _, _ in data_loader:\n        for target in targets:\n            labels = target['labels'].cpu().numpy()\n            for label in labels:\n                class_counts[label] += 1\n    \n    print(\"Class Instance Sizes:\")\n    for cls, count in class_counts.items():\n        print(f\"{class_names[cls]}: {count} instances\")\n\n# Main training loop\ndef run(fold):\n    summary_loss = AverageMeter()\n    \n    # Split data into training and validation sets\n    df_train = df_folds[df_folds['fold'] != fold]\n    df_valid = df_folds[df_folds['fold'] == fold]\n    \n    # Get data loaders\n    train_dataset = get_train_dataset(df_train)\n    train_data_loader = get_train_data_loader(train_dataset, batch_size=BATCH_SIZE)\n    \n    validation_dataset = get_validation_dataset(df_valid)\n    validation_data_loader = get_validation_data_loader(validation_dataset, batch_size=BATCH_SIZE)\n          \n    # Print class instance sizes for training and validation\n    print(\"Training Class Instance Sizes:\")\n    print_class_instance_sizes(train_data_loader, class_names)\n    \n    print(\"Validation Class Instance Sizes:\")\n    print_class_instance_sizes(validation_data_loader, class_names)\n    \n    # Get GPU device\n    device = torch.device('cuda')\n    \n    # Get model\n    model = get_model()\n    model = model.to(device)\n    \n    # Get optimizer\n    params = [p for p in model.parameters() if p.requires_grad]\n    if Adam:\n        optimizer = torch.optim.Adam(params, **Adam_config)\n    else:\n        optimizer = torch.optim.SGD(params, **SGD_config)\n        \n    best_precision = 0.01\n    best_epoch = 0\n    train_losses = []\n    val_maps = []\n    \n    for epoch in range(EPOCHS):\n        summary_loss.reset()\n        train_loss = train_fn(train_data_loader, model, optimizer, device, scheduler=None, epoch=epoch)\n        train_losses.append(train_loss.avg)\n        \n        valid_precision = eval_fn(validation_data_loader, model, device, num_classes, class_names)\n        val_maps.append(valid_precision)\n        \n        print(f'|EPOCH {epoch+1}| TRAIN_LOSS {train_loss.avg}| VAL_PRECISION {valid_precision}|')\n        \n        # Save the model with the highest mAP\n        if valid_precision > best_precision:\n            best_precision = valid_precision\n            best_epoch = epoch + 1\n            torch.save(model.state_dict(), f'FRCNN_best_{fold}_epoch_{best_epoch}.pth')\n            print(f'Best model found at epoch {best_epoch} with mAP {best_precision:.4f}')\n    \n    # Save the model at the last epoch\n    torch.save(model.state_dict(), f'FRCNN_last_epoch_{EPOCHS}_{fold}.pth')\n    print(f'Model saved at last epoch {EPOCHS}')\n    \n    # Plot training and validation performance\n    plt.figure(figsize=(12, 5))\n    plt.subplot(1, 2, 1)\n    plt.plot(train_losses, label='Training Loss')\n    plt.xlabel('Epoch')\n    plt.ylabel('Loss')\n    plt.title('Training Loss Curve')\n    plt.legend()\n\n    plt.subplot(1, 2, 2)\n    plt.plot(val_maps, label='Validation mAP')\n    plt.xlabel('Epoch')\n    plt.ylabel('mAP')\n    plt.title('Validation mAP Curve')\n    plt.legend()\n\n    plt.tight_layout()\n    plt.show()\n    \n    # Return validation_data_loader and model\n    return validation_data_loader, model\n\n\n# Class names\nclass_names = ['class_0', 'class_1', 'class_2', 'class_3', 'class_4', 'class_5', 'class_6', 'class_7', 'class_8', 'class_9']\n\n# Execute training and evaluation\nfold_maps = []\nfor fold in range(n_folds):\n    print(f\"Training Fold {fold}...\")\n    validation_data_loader, model = run(fold)  # Unpack returned values\n    valid_map = eval_fn(validation_data_loader, model, torch.device('cuda'), num_classes, class_names)\n    fold_maps.append(valid_map)\n\n    proceed = input(f\"Fold {fold} completed. Do you want to continue to the next fold? (y/n): \")\n    if proceed.lower() != 'y':\n        print(\"Stopping execution.\")\n        break\n\nprint(f\"Average mAP across folds: {np.mean(fold_maps):.4f}\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport numpy as np\nimport pandas as pd\nimport random\nimport time\nfrom tqdm import tqdm  # Progress bar\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.metrics import confusion_matrix, accuracy_score\n\n# PyTorch\nimport torch\nimport torch.nn as nn\nfrom torch.utils.data import Dataset, DataLoader\nfrom torch.utils.data.sampler import SequentialSampler, RandomSampler\n\n# Torchvision\nimport torchvision\nfrom torchvision.models.detection.faster_rcnn import FastRCNNPredictor\nfrom torchvision.ops import box_iou, nms\n\n# Albumentations\nimport albumentations as A\nfrom albumentations.pytorch.transforms import ToTensorV2\n\n# Sklearn\nfrom sklearn.model_selection import StratifiedKFold\n\n# OpenCV\nimport cv2\n\n# Suppress warnings\nimport warnings\nwarnings.filterwarnings('ignore')\n\n# Check GPU availability\ngpu_info = !nvidia-smi\ngpu_info = '\\n'.join(gpu_info)\nif gpu_info.find('failed') >= 0:\n    print('Select the Runtime > \"Change runtime type\" menu to enable a GPU accelerator, ')\n    print('and then re-execute this cell.')\nelse:\n    print(gpu_info)\n\n# Configuration\nn_folds = 5\nseed = 2020\nnum_classes = 10\nBATCH_SIZE = 4  # Consistent batch size for training and validation\nLR = 0.05\nEPOCHS = 3\nimg_size_training = 800\n\n# Optimizer configuration\nAdam = False\nif Adam:\n    Adam_config = {\"lr\": 0.001, \"betas\": (0.9, 0.999), \"eps\": 1e-08}\nelse:\n    SGD_config = {\"lr\": 0.001, \"momentum\": 0.9, \"weight_decay\": 0.001}\n\n# Seed everything for reproducibility\ndef seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = True\nseed_everything(seed)\n\n# Load dataset\nbboxes_df = pd.read_csv('/kaggle/input/oranges-dataset-2700/Dataset 2700/train2700.csv')\n\n# Parse bounding boxes\nbboxs = np.stack(bboxes_df['bbox'].apply(lambda x: np.fromstring(x[1:-1], sep=',')))\nfor i, column in enumerate(['x', 'y', 'w', 'h']):\n    bboxes_df[column] = bboxs[:, i]\nbboxes_df.drop(columns=['bbox'], inplace=True)\n\n# Create stratified folds\nskf = StratifiedKFold(n_splits=n_folds, shuffle=True, random_state=seed)\ndf_folds = bboxes_df[['image_id']].copy()\ndf_folds.loc[:, 'bbox_count'] = 1\ndf_folds = df_folds.groupby('image_id').count()\ndf_folds.loc[:, 'source'] = bboxes_df[['image_id', 'source']].groupby('image_id').min()['source']\ndf_folds.loc[:, 'stratify_group'] = np.char.add(\n    df_folds['source'].values.astype(str),\n    df_folds['bbox_count'].apply(lambda x: f'_{x // 15}').values.astype(str))\ndf_folds.loc[:, 'fold'] = 0\n\nfor fold_number, (train_index, val_index) in enumerate(skf.split(X=df_folds.index, y=df_folds['stratify_group'])):\n    df_folds.loc[df_folds.iloc[val_index].index, 'fold'] = fold_number\n\n# Dataset directory\nDIR_TRAIN = '/kaggle/input/oranges-dataset-2700/Dataset 2700/Train'\n\n# Custom Dataset Class\nclass WheatDataset(Dataset):\n    def __init__(self, image_ids, dataframe, transforms=None):\n        self.image_ids = image_ids\n        self.df = dataframe\n        self.transforms = transforms\n        \n    def __len__(self):\n        return len(self.image_ids)\n    \n    def __getitem__(self, index):\n        image_id = self.image_ids[index]\n        records = self.df[self.df['image_id'] == image_id]\n        \n        # Load and normalize image\n        image = cv2.imread(f'{DIR_TRAIN}/{image_id}.jpg', cv2.IMREAD_COLOR)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB).astype(np.float32)\n        image /= 255.0\n        \n        # Log image size\n        image_size = image.shape[:2]  # (height, width)\n        \n        # Adjust bounding boxes from COCO format to Pascal VOC\n        boxes = records[['x', 'y', 'w', 'h']].values\n        boxes[:, 2] = boxes[:, 0] + boxes[:, 2]\n        boxes[:, 3] = boxes[:, 1] + boxes[:, 3]\n        \n        # Convert labels to tensor\n        labels = torch.tensor(records['class_id'].values, dtype=torch.int64)\n        \n        area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])\n        area = torch.as_tensor(area, dtype=torch.float32)\n        iscrowd = torch.zeros((records.shape[0],), dtype=torch.int64)\n        \n        target = {\n            'boxes': torch.as_tensor(boxes, dtype=torch.float32),\n            'labels': labels,\n            'image_id': torch.tensor([index]),\n            'area': area,\n            'iscrowd': iscrowd\n        }\n        \n        # Apply transformations if any\n        if self.transforms:\n            sample = {\n                'image': image,\n                'bboxes': target['boxes'],\n                'labels': labels\n            }\n            sample = self.transforms(**sample)\n            image = sample['image']\n            target['boxes'] = torch.as_tensor(sample['bboxes'], dtype=torch.float32)\n        \n        return image, target, image_id, image_size\n\n# Albumentations for training\ndef get_train_transforms():\n    return A.Compose(\n        [\n            A.OneOf([\n                A.HueSaturationValue(hue_shift_limit=0.2, sat_shift_limit=0.2, val_shift_limit=0.2, p=0.3),\n                A.RandomBrightnessContrast(brightness_limit=0.2, contrast_limit=0.2, p=0.3),\n                A.RGBShift(r_shift_limit=20/255, g_shift_limit=20/255, b_shift_limit=10/255, p=0.3)\n            ], p=0.2),\n            A.OneOf([\n                A.RandomGamma(gamma_limit=(80, 120), p=0.3),\n                A.Blur(p=0.6),\n                A.GaussNoise(var_limit=(0.01, 0.05), mean=0, p=0.05),\n                A.ToGray(p=0.05)\n            ], p=0.1),\n            A.OneOf([\n                A.HorizontalFlip(p=1),\n                A.VerticalFlip(p=1),\n                A.Transpose(p=1),\n                A.RandomRotate90(p=1)\n            ], p=0.7),\n            A.RandomFog(fog_coef_lower=0.1, fog_coef_upper=0.2, p=0.02),\n            A.RandomSizedBBoxSafeCrop(img_size_training, img_size_training, p=0.05),\n            A.Resize(height=img_size_training, width=img_size_training, p=1),\n            A.Cutout(num_holes=random.randint(1, 6), max_h_size=64, max_w_size=64, fill_value=0, p=0.15),\n            ToTensorV2(p=1.0),\n        ],\n        p=1.0,\n        bbox_params={\n            'format': 'pascal_voc',\n            'label_fields': ['labels']\n        }\n    )\n\n# Albumentations for validation\ndef get_valid_transforms():\n    return A.Compose([\n        A.Resize(height=img_size_training, width=img_size_training, p=1),\n        ToTensorV2(p=1.0)\n    ], bbox_params={\n        'format': 'pascal_voc',\n        'label_fields': ['labels']\n    })\n\n# Helper functions for dataset and dataloader\ndef get_validation_dataset(df):\n    return WheatDataset(\n        image_ids=df.index.values,\n        dataframe=bboxes_df,\n        transforms=get_valid_transforms()\n    )\n    \ndef get_train_dataset(df):    \n    return WheatDataset(\n        image_ids=df.index.values,\n        dataframe=bboxes_df,\n        transforms=get_train_transforms()\n    )\n\ndef get_validation_data_loader(valid_dataset, batch_size=BATCH_SIZE):  # Use consistent batch size\n    return DataLoader(\n        valid_dataset,\n        batch_size=batch_size,\n        shuffle=False,\n        num_workers=4,\n        collate_fn=collate_fn\n    )    \n\ndef get_train_data_loader(train_dataset, batch_size=BATCH_SIZE):  # Use consistent batch size\n    return DataLoader(\n        train_dataset,\n        batch_size=batch_size,\n        shuffle=False,\n        num_workers=4,\n        collate_fn=collate_fn\n    ) \n\ndef collate_fn(batch):\n    return tuple(zip(*batch))\n\n# Model definition\ndef get_model():    \n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)\n    in_features = model.roi_heads.box_predictor.cls_score.in_features\n    model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)\n    return model\n\n# Average Meter for tracking loss\nclass AverageMeter:\n    def __init__(self):\n        self.reset()\n    \n    def reset(self):\n        self.val = 0\n        self.avg = 0\n        self.sum = 0\n        self.count = 0\n    \n    def update(self, val, n=1):\n        self.val = val\n        self.sum += val * n\n        self.count += n\n        self.avg = self.sum / self.count\n\n# Training function\ndef train_fn(data_loader, model, optimizer, device, scheduler, epoch):\n    model.train()\n    summary_loss = AverageMeter()\n    tk0 = tqdm(data_loader, total=len(data_loader), desc=f\"Training Epoch {epoch + 1}\")\n    \n    for step, (images, targets, image_ids, image_sizes) in enumerate(tk0):   \n        if len(targets) < 1:\n            targets = [{'boxes': torch.zeros((0, 4)).to(device), 'labels': torch.zeros(0).to(device)}]\n            \n        images = list(image.to(device) for image in images)\n        targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n        loss_dict = model(images, targets)        \n        losses = sum(loss for loss in loss_dict.values())\n\n        optimizer.zero_grad()\n        losses.backward()\n        optimizer.step()\n        \n        if scheduler is not None:\n            scheduler.step()\n        \n        summary_loss.update(losses.item(), len(images))\n        tk0.set_postfix(loss=summary_loss.avg)\n    \n    return summary_loss\n\n# Function to calculate mAP\ndef calculate_map(outputs, targets, iou_thresholds):\n    \"\"\"\n    Calculates mAP for a batch of images.\n    \"\"\"\n    aps = []\n    for threshold in iou_thresholds:\n        tp, fp, fn = 0, 0, 0\n        for output, target in zip(outputs, targets):\n            pred_boxes = output['boxes'].cpu().numpy()\n            pred_scores = output['scores'].cpu().numpy()\n            gt_boxes = target['boxes'].cpu().numpy()\n\n            if len(pred_boxes) == 0:\n                fn += len(gt_boxes)\n                continue\n            \n            if len(gt_boxes) == 0:\n                fp += len(pred_boxes)\n                continue\n\n            ious = box_iou(torch.tensor(pred_boxes), torch.tensor(gt_boxes)).numpy()\n            matches = ious >= threshold\n\n            tp += matches.sum()\n            fp += len(pred_boxes) - matches.sum()\n            fn += len(gt_boxes) - matches.sum()\n\n        # Calculate precision and recall\n        precision = tp / (tp + fp) if tp + fp > 0 else 0\n        recall = tp / (tp + fn) if tp + fn > 0 else 0\n\n        # Average precision over IoU thresholds\n        ap = precision * recall\n        aps.append(ap)\n    \n    return np.mean(aps) if aps else 0.0\n\n# Function to calculate F1 score, precision, and recall\ndef calculate_f1_precision_recall(outputs, targets, num_classes):\n    # Initialize counters for TP, FP, FN\n    tp = {cls: 0 for cls in range(num_classes)}\n    fp = {cls: 0 for cls in range(num_classes)}\n    fn = {cls: 0 for cls in range(num_classes)}\n\n    for output, target in zip(outputs, targets):\n        pred_boxes = output['boxes'].cpu().numpy()\n        pred_labels = output['labels'].cpu().numpy()\n        gt_boxes = target['boxes'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        # For each class, calculate TP, FP, FN\n        for cls in range(num_classes):\n            pred_cls = pred_labels == cls\n            gt_cls = gt_labels == cls\n\n            if len(pred_boxes[pred_cls]) == 0 and len(gt_boxes[gt_cls]) == 0:\n                continue  # No predictions or ground truth for this class\n\n            if len(pred_boxes[pred_cls]) == 0:\n                fn[cls] += len(gt_boxes[gt_cls])  # All ground truth are false negatives\n                continue\n\n            if len(gt_boxes[gt_cls]) == 0:\n                fp[cls] += len(pred_boxes[pred_cls])  # All predictions are false positives\n                continue\n\n            # Calculate IoU between predicted and ground truth boxes\n            ious = box_iou(torch.tensor(pred_boxes[pred_cls]), torch.tensor(gt_boxes[gt_cls])).numpy()\n            matches = ious >= 0.5  # IoU threshold of 0.5 for matching\n\n            # Count TP, FP, FN\n            tp[cls] += matches.sum()\n            fp[cls] += len(pred_boxes[pred_cls]) - matches.sum()\n            fn[cls] += len(gt_boxes[gt_cls]) - matches.sum()\n\n    # Calculate precision, recall, and F1 score for each class\n    precision = {cls: tp[cls] / (tp[cls] + fp[cls]) if (tp[cls] + fp[cls]) > 0 else 0 for cls in range(num_classes)}\n    recall = {cls: tp[cls] / (tp[cls] + fn[cls]) if (tp[cls] + fn[cls]) > 0 else 0 for cls in range(num_classes)}\n    f1_score = {cls: 2 * (precision[cls] * recall[cls]) / (precision[cls] + recall[cls]) if (precision[cls] + recall[cls]) > 0 else 0 for cls in range(num_classes)}\n\n    return precision, recall, f1_score\n\n# Evaluation function with AP per class and confusion matrix\ndef eval_fn(data_loader, model, device, num_classes, class_names, confidence_threshold=0.5):\n    model.eval()\n    iou_thresholds = np.arange(0.5, 0.95, 0.05)\n    all_maps = []\n    all_outputs = []\n    all_targets = []\n\n    with torch.no_grad():\n        tk0 = tqdm(data_loader, total=len(data_loader), desc=\"Validation\")\n        for images, targets, _, _ in tk0:\n            images = list(image.to(device) for image in images)\n            targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n            outputs = model(images)\n            batch_map = calculate_map(outputs, targets, iou_thresholds)\n            all_maps.append(batch_map)\n            all_outputs.extend(outputs)\n            all_targets.extend(targets)\n\n    final_map = np.mean(all_maps)\n\n    # Calculate AP per class\n    mean_aps = calculate_ap_per_class(all_outputs, all_targets, iou_thresholds, num_classes)\n    print(\"Average Precision per Class:\", mean_aps)\n\n    # Calculate F1 score, precision, and recall\n    precision, recall, f1_score = calculate_f1_precision_recall(all_outputs, all_targets, num_classes)\n    print(\"Precision per Class:\", precision)\n    print(\"Recall per Class:\", recall)\n    print(\"F1 Score per Class:\", f1_score)\n\n    # Generate and plot confusion matrix\n    confusion_matrix = generate_confusion_matrix(all_outputs, all_targets, num_classes)\n    plot_confusion_matrix(confusion_matrix, class_names)\n\n    # Plot AP per class\n    plot_ap_per_class(mean_aps, class_names)\n\n    # Calculate estimation accuracy with confidence threshold\n    accuracy = calculate_accuracy(all_outputs, all_targets, confidence_threshold=confidence_threshold)\n    print(f\"Estimation Accuracy: {accuracy:.2f}%\")\n\n    return final_map\n\n# Function to calculate AP per class\ndef calculate_ap_per_class(outputs, targets, iou_thresholds, num_classes):\n    aps = {cls: [] for cls in range(num_classes)}\n    for threshold in iou_thresholds:\n        for cls in range(num_classes):\n            tp, fp, fn = 0, 0, 0\n            for output, target in zip(outputs, targets):\n                pred_boxes = output['boxes'].cpu().numpy()\n                pred_scores = output['scores'].cpu().numpy()\n                pred_labels = output['labels'].cpu().numpy()\n                gt_boxes = target['boxes'].cpu().numpy()\n                gt_labels = target['labels'].cpu().numpy()\n\n                if len(pred_boxes) == 0:\n                    fn += len(gt_boxes[gt_labels == cls])\n                    continue\n                \n                if len(gt_boxes) == 0:\n                    fp += len(pred_boxes[pred_labels == cls])\n                    continue\n\n                ious = box_iou(torch.tensor(pred_boxes[pred_labels == cls]), torch.tensor(gt_boxes[gt_labels == cls])).numpy()\n                matches = ious >= threshold\n\n                tp += matches.sum()\n                fp += len(pred_boxes[pred_labels == cls]) - matches.sum()\n                fn += len(gt_boxes[gt_labels == cls]) - matches.sum()\n\n            precision = tp / (tp + fp) if tp + fp > 0 else 0\n            recall = tp / (tp + fn) if tp + fn > 0 else 0\n            ap = precision * recall\n            aps[cls].append(ap)\n    \n    mean_aps = {cls: np.mean(aps[cls]) if aps[cls] else 0.0 for cls in range(num_classes)}\n    return mean_aps\n\n# Function to generate confusion matrix\ndef generate_confusion_matrix(outputs, targets, num_classes):\n    confusion_matrix = np.zeros((num_classes, num_classes))\n    for output, target in zip(outputs, targets):\n        pred_labels = output['labels'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        # Only consider images where both predictions and ground truth are non-empty\n        if len(pred_labels) > 0 and len(gt_labels) > 0:\n            # Ensure the number of predictions matches the number of ground truth labels\n            min_length = min(len(pred_labels), len(gt_labels))\n            for pred_label, gt_label in zip(pred_labels[:min_length], gt_labels[:min_length]):\n                confusion_matrix[gt_label][pred_label] += 1\n\n    return confusion_matrix\n\n# Function to plot confusion matrix\ndef plot_confusion_matrix(confusion_matrix, class_names):\n    plt.figure(figsize=(10, 10))\n    sns.heatmap(confusion_matrix, annot=True, fmt='g', cmap='Blues', xticklabels=class_names, yticklabels=class_names)\n    plt.xlabel('Predicted')\n    plt.ylabel('Actual')\n    plt.title('Confusion Matrix')\n    plt.show()\n\n# Function to plot AP per class\ndef plot_ap_per_class(mean_aps, class_names):\n    plt.figure(figsize=(10, 5))\n    plt.bar(range(len(mean_aps)), list(mean_aps.values()), align='center')\n    plt.xticks(range(len(mean_aps)), class_names, rotation=45)\n    plt.xlabel('Class')\n    plt.ylabel('Average Precision')\n    plt.title('Average Precision per Class')\n    plt.show()\n\n# Function to calculate estimation accuracy with confidence threshold\ndef calculate_accuracy(outputs, targets, confidence_threshold=0.5):\n    all_preds = []\n    all_targets = []\n    \n    for output, target in zip(outputs, targets):\n        pred_boxes = output['boxes'].cpu().numpy()\n        pred_scores = output['scores'].cpu().numpy()\n        pred_labels = output['labels'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        # Filter predictions based on confidence score\n        high_confidence_mask = pred_scores >= confidence_threshold\n        pred_boxes = pred_boxes[high_confidence_mask]\n        pred_labels = pred_labels[high_confidence_mask]\n\n        # Only consider images where both predictions and ground truth are non-empty\n        if len(pred_labels) > 0 and len(gt_labels) > 0:\n            # Ensure the number of predictions matches the number of ground truth labels\n            min_length = min(len(pred_labels), len(gt_labels))\n            all_preds.extend(pred_labels[:min_length])\n            all_targets.extend(gt_labels[:min_length])\n    \n    if len(all_preds) == 0 or len(all_targets) == 0:\n        return 0.0  # Return 0 accuracy if no valid predictions or ground truth\n    \n    accuracy = accuracy_score(all_targets, all_preds) * 100\n    return accuracy\n\n# Function to print class instance sizes\ndef print_class_instance_sizes(data_loader, class_names):\n    class_counts = {cls: 0 for cls in range(len(class_names))}\n    \n    for _, targets, _, _ in data_loader:\n        for target in targets:\n            labels = target['labels'].cpu().numpy()\n            for label in labels:\n                class_counts[label] += 1\n    \n    print(\"Class Instance Sizes:\")\n    for cls, count in class_counts.items():\n        print(f\"{class_names[cls]}: {count} instances\")\n\n# Main training loop\ndef run(fold):\n    summary_loss = AverageMeter()\n    \n    # Split data into training and validation sets\n    df_train = df_folds[df_folds['fold'] != fold]\n    df_valid = df_folds[df_folds['fold'] == fold]\n    \n    # Get data loaders\n    train_dataset = get_train_dataset(df_train)\n    train_data_loader = get_train_data_loader(train_dataset, batch_size=BATCH_SIZE)\n    \n    validation_dataset = get_validation_dataset(df_valid)\n    validation_data_loader = get_validation_data_loader(validation_dataset, batch_size=BATCH_SIZE)\n          \n    # Print class instance sizes for training and validation\n    print(\"Training Class Instance Sizes:\")\n    print_class_instance_sizes(train_data_loader, class_names)\n    \n    print(\"Validation Class Instance Sizes:\")\n    print_class_instance_sizes(validation_data_loader, class_names)\n    \n    # Get GPU device\n    device = torch.device('cuda')\n    \n    # Get model\n    model = get_model()\n    model = model.to(device)\n    \n    # Get optimizer\n    params = [p for p in model.parameters() if p.requires_grad]\n    if Adam:\n        optimizer = torch.optim.Adam(params, **Adam_config)\n    else:\n        optimizer = torch.optim.SGD(params, **SGD_config)\n        \n    best_precision = 0.01\n    best_epoch = 0\n    train_losses = []\n    val_maps = []\n    \n    for epoch in range(EPOCHS):\n        summary_loss.reset()\n        train_loss = train_fn(train_data_loader, model, optimizer, device, scheduler=None, epoch=epoch)\n        train_losses.append(train_loss.avg)\n        \n        valid_precision = eval_fn(validation_data_loader, model, device, num_classes, class_names)\n        val_maps.append(valid_precision)\n        \n        print(f'|EPOCH {epoch+1}| TRAIN_LOSS {train_loss.avg}| VAL_PRECISION {valid_precision}|')\n        \n        # Save the model with the highest mAP\n        if valid_precision > best_precision:\n            best_precision = valid_precision\n            best_epoch = epoch + 1\n            torch.save(model.state_dict(), f'FRCNN_best_{fold}_epoch_{best_epoch}.pth')\n            print(f'Best model found at epoch {best_epoch} with mAP {best_precision:.4f}')\n    \n    # Save the model at the last epoch\n    torch.save(model.state_dict(), f'FRCNN_last_epoch_{EPOCHS}_{fold}.pth')\n    print(f'Model saved at last epoch {EPOCHS}')\n    \n    # Plot training and validation performance\n    plt.figure(figsize=(12, 5))\n    plt.subplot(1, 2, 1)\n    plt.plot(train_losses, label='Training Loss')\n    plt.xlabel('Epoch')\n    plt.ylabel('Loss')\n    plt.title('Training Loss Curve')\n    plt.legend()\n\n    plt.subplot(1, 2, 2)\n    plt.plot(val_maps, label='Validation mAP')\n    plt.xlabel('Epoch')\n    plt.ylabel('mAP')\n    plt.title('Validation mAP Curve')\n    plt.legend()\n\n    plt.tight_layout()\n    plt.show()\n    \n    # Return validation_data_loader and model\n    return validation_data_loader, model\n\n\n# Class names\nclass_names = ['class_0', 'class_1', 'class_2', 'class_3', 'class_4', 'class_5', 'class_6', 'class_7', 'class_8', 'class_9']\n\n# Execute training and evaluation\nfold_maps = []\nfor fold in range(n_folds):\n    print(f\"Training Fold {fold}...\")\n    validation_data_loader, model = run(fold)  # Unpack returned values\n    valid_map = eval_fn(validation_data_loader, model, torch.device('cuda'), num_classes, class_names)\n    fold_maps.append(valid_map)\n\n    proceed = input(f\"Fold {fold} completed. Do you want to continue to the next fold? (y/n): \")\n    if proceed.lower() != 'y':\n        print(\"Stopping execution.\")\n        break\n\nprint(f\"Average mAP across folds: {np.mean(fold_maps):.4f}\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport numpy as np\nimport pandas as pd\nimport random\nimport time\nfrom tqdm import tqdm  # Progress bar\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.metrics import accuracy_score\n\n# PyTorch\nimport torch\nimport torch.nn as nn\nfrom torch.utils.data import Dataset, DataLoader\nfrom torch.utils.data.sampler import SequentialSampler, RandomSampler\n\n# Torchvision\nimport torchvision\nfrom torchvision.models.detection.faster_rcnn import FastRCNNPredictor\nfrom torchvision.ops import box_iou, nms\n\n# Albumentations\nimport albumentations as A\nfrom albumentations.pytorch.transforms import ToTensorV2\n\n# Sklearn\nfrom sklearn.model_selection import StratifiedKFold\n\n# OpenCV\nimport cv2\n\n# Suppress warnings\nimport warnings\nwarnings.filterwarnings('ignore')\n\n# Check GPU availability\ngpu_info = !nvidia-smi\ngpu_info = '\\n'.join(gpu_info)\nif gpu_info.find('failed') >= 0:\n    print('Select the Runtime > \"Change runtime type\" menu to enable a GPU accelerator, ')\n    print('and then re-execute this cell.')\nelse:\n    print(gpu_info)\n\n# Configuration\nn_folds = 5\nseed = 2020\nnum_classes = 5\nBATCH_SIZE = 4  # Consistent batch size for training and validation\nLR = 0.05\nEPOCHS = 20\nimg_size_training = 800\n\n# Optimizer configuration\nAdam = False\nif Adam:\n    Adam_config = {\"lr\": 0.001, \"betas\": (0.9, 0.999), \"eps\": 1e-08}\nelse:\n    SGD_config = {\"lr\": 0.001, \"momentum\": 0.9, \"weight_decay\": 0.001}\n\n# Seed everything for reproducibility\ndef seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = True\nseed_everything(seed)\n\n# Load dataset\nbboxes_df = pd.read_csv('/kaggle/input/multiclass-oranges-detection-dataset-4356/Oranges Dataset (4356)/train4356.csv')\n\n# Parse bounding boxes\nbboxs = np.stack(bboxes_df['bbox'].apply(lambda x: np.fromstring(x[1:-1], sep=',')))\nfor i, column in enumerate(['x', 'y', 'w', 'h']):\n    bboxes_df[column] = bboxs[:, i]\nbboxes_df.drop(columns=['bbox'], inplace=True)\n\n# Filter out invalid bounding boxes with non-positive width or height\ninvalid_boxes = (bboxes_df['w'] <= 0) | (bboxes_df['h'] <= 0)\nprint(f\"Removing {invalid_boxes.sum()} invalid bounding boxes with width or height <= 0.\")\nbboxes_df = bboxes_df[~invalid_boxes].reset_index(drop=True)\n\n# Create stratified folds\nskf = StratifiedKFold(n_splits=n_folds, shuffle=True, random_state=seed)\ndf_folds = bboxes_df[['image_id']].copy()\ndf_folds.loc[:, 'bbox_count'] = 1\ndf_folds = df_folds.groupby('image_id').count()\ndf_folds.loc[:, 'source'] = bboxes_df[['image_id', 'source']].groupby('image_id').min()['source']\ndf_folds.loc[:, 'stratify_group'] = np.char.add(\n    df_folds['source'].values.astype(str),\n    df_folds['bbox_count'].apply(lambda x: f'_{x // 15}').values.astype(str))\ndf_folds.loc[:, 'fold'] = 0\n\nfor fold_number, (train_index, val_index) in enumerate(skf.split(X=df_folds.index, y=df_folds['stratify_group'])):\n    df_folds.loc[df_folds.iloc[val_index].index, 'fold'] = fold_number\n\n# Dataset directory\nDIR_TRAIN = '/kaggle/input/multiclass-oranges-detection-dataset-4356/Oranges Dataset (4356)/Images'\n\n# Custom Dataset Class\nclass WheatDataset(Dataset):\n    def __init__(self, image_ids, dataframe, transforms=None):\n        self.image_ids = image_ids\n        self.df = dataframe\n        self.transforms = transforms\n        \n    def __len__(self):\n        return len(self.image_ids)\n    \n    def __getitem__(self, index):\n        image_id = self.image_ids[index]\n        records = self.df[self.df['image_id'] == image_id]\n        \n        # Load and normalize image\n        image = cv2.imread(f'{DIR_TRAIN}/{image_id}.jpg', cv2.IMREAD_COLOR)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB).astype(np.float32)\n        image /= 255.0\n        \n        # Log image size\n        image_size = image.shape[:2]  # (height, width)\n        \n        # Adjust bounding boxes from COCO format to Pascal VOC\n        boxes = records[['x', 'y', 'w', 'h']].values\n        boxes[:, 2] = boxes[:, 0] + boxes[:, 2]\n        boxes[:, 3] = boxes[:, 1] + boxes[:, 3]\n        \n        # Convert labels to tensor\n        labels = torch.tensor(records['class_id'].values, dtype=torch.int64)\n        \n        area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])\n        area = torch.as_tensor(area, dtype=torch.float32)\n        iscrowd = torch.zeros((records.shape[0],), dtype=torch.int64)\n        \n        target = {\n            'boxes': torch.as_tensor(boxes, dtype=torch.float32),\n            'labels': labels,\n            'image_id': torch.tensor([index]),\n            'area': area,\n            'iscrowd': iscrowd\n        }\n        \n        # Apply transformations if any\n        if self.transforms:\n            sample = {\n                'image': image,\n                'bboxes': target['boxes'],\n                'labels': labels\n            }\n            sample = self.transforms(**sample)\n            image = sample['image']\n            target['boxes'] = torch.as_tensor(sample['bboxes'], dtype=torch.float32)\n        \n        return image, target, image_id, image_size\n\n# Albumentations for training\ndef get_train_transforms():\n    return A.Compose(\n        [\n            A.OneOf([\n                A.HueSaturationValue(hue_shift_limit=0.2, sat_shift_limit=0.2, val_shift_limit=0.2, p=0.3),\n                A.RandomBrightnessContrast(brightness_limit=0.2, contrast_limit=0.2, p=0.3),\n                A.RGBShift(r_shift_limit=20/255, g_shift_limit=20/255, b_shift_limit=10/255, p=0.3)\n            ], p=0.2),\n            A.OneOf([\n                A.RandomGamma(gamma_limit=(80, 120), p=0.3),\n                A.Blur(p=0.6),\n                A.GaussNoise(var_limit=(0.01, 0.05), mean=0, p=0.05),\n                A.ToGray(p=0.05)\n            ], p=0.1),\n            A.OneOf([\n                A.HorizontalFlip(p=1),\n                A.VerticalFlip(p=1),\n                A.Transpose(p=1),\n                A.RandomRotate90(p=1)\n            ], p=0.7),\n            A.RandomFog(fog_coef_lower=0.1, fog_coef_upper=0.2, p=0.02),\n            A.RandomSizedBBoxSafeCrop(img_size_training, img_size_training, p=0.05),\n            A.Resize(height=img_size_training, width=img_size_training, p=1),\n            A.Cutout(num_holes=random.randint(1, 6), max_h_size=64, max_w_size=64, fill_value=0, p=0.15),\n            ToTensorV2(p=1.0),\n        ],\n        p=1.0,\n        bbox_params={\n            'format': 'pascal_voc',\n            'label_fields': ['labels']\n        }\n    )\n\n# Albumentations for validation\ndef get_valid_transforms():\n    return A.Compose([\n        A.Resize(height=img_size_training, width=img_size_training, p=1),\n        ToTensorV2(p=1.0)\n    ], bbox_params={\n        'format': 'pascal_voc',\n        'label_fields': ['labels']\n    })\n\n# Helper functions for dataset and dataloader\ndef get_validation_dataset(df):\n    return WheatDataset(\n        image_ids=df.index.values,\n        dataframe=bboxes_df,\n        transforms=get_valid_transforms()\n    )\n    \ndef get_train_dataset(df):    \n    return WheatDataset(\n        image_ids=df.index.values,\n        dataframe=bboxes_df,\n        transforms=get_train_transforms()\n    )\n\ndef get_validation_data_loader(valid_dataset, batch_size=BATCH_SIZE):  # Use consistent batch size\n    return DataLoader(\n        valid_dataset,\n        batch_size=batch_size,\n        shuffle=False,\n        num_workers=4,\n        collate_fn=collate_fn\n    )    \n\ndef get_train_data_loader(train_dataset, batch_size=BATCH_SIZE):  # Use consistent batch size\n    return DataLoader(\n        train_dataset,\n        batch_size=batch_size,\n        shuffle=False,\n        num_workers=4,\n        collate_fn=collate_fn\n    ) \n\ndef collate_fn(batch):\n    return tuple(zip(*batch))\n\n# Model definition\ndef get_model():    \n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)\n    in_features = model.roi_heads.box_predictor.cls_score.in_features\n    model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)\n    return model\n\n# Average Meter for tracking loss\nclass AverageMeter:\n    def __init__(self):\n        self.reset()\n    \n    def reset(self):\n        self.val = 0\n        self.avg = 0\n        self.sum = 0\n        self.count = 0\n    \n    def update(self, val, n=1):\n        self.val = val\n        self.sum += val * n\n        self.count += n\n        self.avg = self.sum / self.count\n\n# Training function\ndef train_fn(data_loader, model, optimizer, device, scheduler, epoch):\n    model.train()\n    summary_loss = AverageMeter()\n    tk0 = tqdm(data_loader, total=len(data_loader), desc=f\"Training Epoch {epoch + 1}\")\n    \n    for step, (images, targets, image_ids, image_sizes) in enumerate(tk0):   \n        if len(targets) < 1:\n            targets = [{'boxes': torch.zeros((0, 4)).to(device), 'labels': torch.zeros(0).to(device)}]\n            \n        images = list(image.to(device) for image in images)\n        targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n        loss_dict = model(images, targets)        \n        losses = sum(loss for loss in loss_dict.values())\n\n        optimizer.zero_grad()\n        losses.backward()\n        optimizer.step()\n        \n        if scheduler is not None:\n            scheduler.step()\n        \n        summary_loss.update(losses.item(), len(images))\n        tk0.set_postfix(loss=summary_loss.avg)\n    \n    return summary_loss\n\n# Function to calculate estimation accuracy\ndef calculate_accuracy(outputs, targets, iou_threshold=0.5, confidence_threshold=0.5):\n    true_positives = 0\n    false_positives = 0\n    false_negatives = 0\n\n    for output, target in zip(outputs, targets):\n        # Extract predictions and ground truth\n        pred_boxes = output['boxes'].cpu().numpy()\n        pred_scores = output['scores'].cpu().numpy()\n        pred_labels = output['labels'].cpu().numpy()\n        gt_boxes = target['boxes'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        # Filter predictions based on confidence score\n        high_confidence_mask = pred_scores >= confidence_threshold\n        pred_boxes = pred_boxes[high_confidence_mask]\n        pred_labels = pred_labels[high_confidence_mask]\n\n        # Initialize matched flags for ground truth objects\n        gt_matched = [False] * len(gt_boxes)\n\n        # Match predictions to ground truth objects\n        for pred_box, pred_label in zip(pred_boxes, pred_labels):\n            best_iou = 0\n            best_gt_idx = -1\n\n            # Find the ground truth object with the highest IoU\n            for gt_idx, (gt_box, gt_label) in enumerate(zip(gt_boxes, gt_labels)):\n                if gt_matched[gt_idx]:\n                    continue  # Skip already matched ground truth objects\n\n                iou = box_iou(torch.tensor([pred_box]), torch.tensor([gt_box])).item()\n                if iou > best_iou:\n                    best_iou = iou\n                    best_gt_idx = gt_idx\n\n            # Check if the best IoU meets the threshold\n            if best_iou >= iou_threshold:\n                if pred_label == gt_labels[best_gt_idx]:\n                    true_positives += 1  # Correct prediction\n                else:\n                    false_positives += 1  # Incorrect label\n                gt_matched[best_gt_idx] = True  # Mark as matched\n            else:\n                false_positives += 1  # No matching ground truth\n\n        # Count false negatives (unmatched ground truth objects)\n        false_negatives += sum(not matched for matched in gt_matched)\n\n    # Calculate accuracy\n    if true_positives + false_positives + false_negatives == 0:\n        return 0.0  # Avoid division by zero\n\n    accuracy = (true_positives / (true_positives + false_positives + false_negatives)) * 100\n    return accuracy\n\n# Function to calculate AP per class\ndef calculate_ap_per_class(outputs, targets, iou_thresholds, num_classes):\n    aps = {cls: [] for cls in range(num_classes)}\n    for threshold in iou_thresholds:\n        for cls in range(num_classes):\n            tp, fp, fn = 0, 0, 0\n            for output, target in zip(outputs, targets):\n                pred_boxes = output['boxes'].cpu().numpy()\n                pred_scores = output['scores'].cpu().numpy()\n                pred_labels = output['labels'].cpu().numpy()\n                gt_boxes = target['boxes'].cpu().numpy()\n                gt_labels = target['labels'].cpu().numpy()\n\n                if len(pred_boxes) == 0:\n                    fn += len(gt_boxes[gt_labels == cls])\n                    continue\n                \n                if len(gt_boxes) == 0:\n                    fp += len(pred_boxes[pred_labels == cls])\n                    continue\n\n                ious = box_iou(torch.tensor(pred_boxes[pred_labels == cls]), torch.tensor(gt_boxes[gt_labels == cls])).numpy()\n                matches = ious >= threshold\n\n                tp += matches.sum()\n                fp += len(pred_boxes[pred_labels == cls]) - matches.sum()\n                fn += len(gt_boxes[gt_labels == cls]) - matches.sum()\n\n            precision = tp / (tp + fp) if tp + fp > 0 else 0\n            recall = tp / (tp + fn) if tp + fn > 0 else 0\n            ap = precision * recall\n            aps[cls].append(ap)\n    \n    mean_aps = {cls: np.mean(aps[cls]) if aps[cls] else 0.0 for cls in range(num_classes)}\n    return mean_aps\n\n# Function to calculate mAP\ndef calculate_map(outputs, targets, iou_thresholds):\n    aps = []\n    for threshold in iou_thresholds:\n        ap = calculate_ap_per_threshold(outputs, targets, threshold)\n        aps.append(ap)\n    return np.mean(aps) if aps else 0.0\n\ndef calculate_ap_per_threshold(outputs, targets, iou_threshold):\n    tp, fp, fn = 0, 0, 0\n    for output, target in zip(outputs, targets):\n        pred_boxes = output['boxes'].cpu().numpy()\n        pred_scores = output['scores'].cpu().numpy()\n        pred_labels = output['labels'].cpu().numpy()\n        gt_boxes = target['boxes'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        if len(pred_boxes) == 0:\n            fn += len(gt_boxes)\n            continue\n        \n        if len(gt_boxes) == 0:\n            fp += len(pred_boxes)\n            continue\n\n        ious = box_iou(torch.tensor(pred_boxes), torch.tensor(gt_boxes)).numpy()\n        matches = ious >= iou_threshold\n\n        tp += matches.sum()\n        fp += len(pred_boxes) - matches.sum()\n        fn += len(gt_boxes) - matches.sum()\n\n    precision = tp / (tp + fp) if tp + fp > 0 else 0\n    recall = tp / (tp + fn) if tp + fn > 0 else 0\n    ap = precision * recall\n    return ap\n\n# Function to calculate F1 score, precision, and recall\ndef calculate_f1_precision_recall(outputs, targets, num_classes):\n    \"\"\"\n    Calculate precision, recall, and F1 score for each class.\n    \n    Args:\n        outputs (list): List of model outputs (predictions).\n        targets (list): List of ground truth targets.\n        num_classes (int): Number of classes.\n    \n    Returns:\n        precision (list): Precision for each class.\n        recall (list): Recall for each class.\n        f1_score (list): F1 score for each class.\n    \"\"\"\n    # Initialize true positives, false positives, and false negatives for each class\n    tp = [0] * num_classes\n    fp = [0] * num_classes\n    fn = [0] * num_classes\n\n    for output, target in zip(outputs, targets):\n        pred_boxes = output['boxes'].cpu().numpy()\n        pred_scores = output['scores'].cpu().numpy()\n        pred_labels = output['labels'].cpu().numpy()\n        gt_boxes = target['boxes'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        # Iterate over each class\n        for cls in range(num_classes):\n            # Filter predictions and ground truth for the current class\n            pred_mask = pred_labels == cls\n            gt_mask = gt_labels == cls\n\n            pred_boxes_cls = pred_boxes[pred_mask]\n            gt_boxes_cls = gt_boxes[gt_mask]\n\n            # Calculate IoU between predictions and ground truth\n            if len(pred_boxes_cls) > 0 and len(gt_boxes_cls) > 0:\n                ious = box_iou(torch.tensor(pred_boxes_cls), torch.tensor(gt_boxes_cls)).numpy()\n                matches = ious >= 0.5  # IoU threshold for matching\n\n                # Count true positives and false positives\n                tp[cls] += matches.sum()\n                fp[cls] += len(pred_boxes_cls) - matches.sum()\n                fn[cls] += len(gt_boxes_cls) - matches.sum()\n            elif len(pred_boxes_cls) > 0:\n                # All predictions are false positives if there are no ground truth boxes\n                fp[cls] += len(pred_boxes_cls)\n            elif len(gt_boxes_cls) > 0:\n                # All ground truth boxes are false negatives if there are no predictions\n                fn[cls] += len(gt_boxes_cls)\n\n    # Calculate precision, recall, and F1 score for each class\n    precision = []\n    recall = []\n    f1_score = []\n\n    for cls in range(num_classes):\n        precision_cls = tp[cls] / (tp[cls] + fp[cls]) if tp[cls] + fp[cls] > 0 else 0\n        recall_cls = tp[cls] / (tp[cls] + fn[cls]) if tp[cls] + fn[cls] > 0 else 0\n        f1_cls = 2 * (precision_cls * recall_cls) / (precision_cls + recall_cls) if precision_cls + recall_cls > 0 else 0\n\n        precision.append(precision_cls)\n        recall.append(recall_cls)\n        f1_score.append(f1_cls)\n\n    return precision, recall, f1_score\n    \n# Evaluation function with AP per class and confusion matrix\ndef eval_fn(data_loader, model, device, num_classes, class_names):\n    model.eval()\n    iou_thresholds = np.arange(0.5, 0.95, 0.05)\n    all_maps = []\n    all_outputs = []\n    all_targets = []\n\n    with torch.no_grad():\n        tk0 = tqdm(data_loader, total=len(data_loader), desc=\"Validation\")\n        for images, targets, _, _ in tk0:\n            images = list(image.to(device) for image in images)\n            targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n            outputs = model(images)\n            batch_map = calculate_map(outputs, targets, iou_thresholds)\n            all_maps.append(batch_map)\n            all_outputs.extend(outputs)\n            all_targets.extend(targets)\n\n    final_map = np.mean(all_maps)\n\n    # Calculate AP per class\n    mean_aps = calculate_ap_per_class(all_outputs, all_targets, iou_thresholds, num_classes)\n    print(\"Average Precision per Class:\", mean_aps)\n\n    # Calculate F1 score, precision, and recall\n    precision, recall, f1_score = calculate_f1_precision_recall(all_outputs, all_targets, num_classes)\n    print(\"Precision per Class:\", precision)\n    print(\"Recall per Class:\", recall)\n    print(\"F1 Score per Class:\", f1_score)\n\n    # Generate and plot confusion matrix\n    confusion_matrix = generate_confusion_matrix(all_outputs, all_targets, num_classes)\n    plot_confusion_matrix(confusion_matrix, class_names)\n\n    # Plot AP per class\n    plot_ap_per_class(mean_aps, class_names)\n\n    # Calculate estimation accuracy with confidence threshold\n    accuracy = calculate_accuracy(all_outputs, all_targets, iou_threshold=0.5, confidence_threshold=0.5)\n    print(f\"Estimation Accuracy: {accuracy:.2f}%\")\n\n    return final_map\n\n# Function to generate confusion matrix\ndef generate_confusion_matrix(outputs, targets, num_classes):\n    confusion_matrix = np.zeros((num_classes, num_classes))\n    for output, target in zip(outputs, targets):\n        pred_labels = output['labels'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        # Only consider images where both predictions and ground truth are non-empty\n        if len(pred_labels) > 0 and len(gt_labels) > 0:\n            # Ensure the number of predictions matches the number of ground truth labels\n            min_length = min(len(pred_labels), len(gt_labels))\n            for pred_label, gt_label in zip(pred_labels[:min_length], gt_labels[:min_length]):\n                confusion_matrix[gt_label][pred_label] += 1\n\n    return confusion_matrix\n\n# Function to plot confusion matrix\ndef plot_confusion_matrix(confusion_matrix, class_names):\n    plt.figure(figsize=(10, 10))\n    sns.heatmap(confusion_matrix, annot=True, fmt='g', cmap='Blues', xticklabels=class_names, yticklabels=class_names)\n    plt.xlabel('Predicted')\n    plt.ylabel('Actual')\n    plt.title('Confusion Matrix')\n    plt.show()\n\n# Function to plot AP per class\ndef plot_ap_per_class(mean_aps, class_names):\n    plt.figure(figsize=(10, 5))\n    plt.bar(range(len(mean_aps)), list(mean_aps.values()), align='center')\n    plt.xticks(range(len(mean_aps)), class_names, rotation=45)\n    plt.xlabel('Class')\n    plt.ylabel('Average Precision')\n    plt.title('Average Precision per Class')\n    plt.show()\n\n# Function to print class instance sizes\ndef print_class_instance_sizes(data_loader, class_names):\n    class_counts = {cls: 0 for cls in range(len(class_names))}\n    \n    for _, targets, _, _ in data_loader:\n        for target in targets:\n            labels = target['labels'].cpu().numpy()\n            for label in labels:\n                class_counts[label] += 1\n    \n    print(\"Class Instance Sizes:\")\n    for cls, count in class_counts.items():\n        print(f\"{class_names[cls]}: {count} instances\")\n\n# Main training loop\ndef run(fold):\n    summary_loss = AverageMeter()\n    \n    # Split data into training and validation sets\n    df_train = df_folds[df_folds['fold'] != fold]\n    df_valid = df_folds[df_folds['fold'] == fold]\n    \n    # Get data loaders\n    train_dataset = get_train_dataset(df_train)\n    train_data_loader = get_train_data_loader(train_dataset, batch_size=BATCH_SIZE)\n    \n    validation_dataset = get_validation_dataset(df_valid)\n    validation_data_loader = get_validation_data_loader(validation_dataset, batch_size=BATCH_SIZE)\n          \n    # Print class instance sizes for training and validation\n    print(\"Training Class Instance Sizes:\")\n    print_class_instance_sizes(train_data_loader, class_names)\n    \n    print(\"Validation Class Instance Sizes:\")\n    print_class_instance_sizes(validation_data_loader, class_names)\n    \n    # Get GPU device\n    device = torch.device('cuda')\n    \n    # Get model\n    model = get_model()\n    model = model.to(device)\n    \n    # Get optimizer\n    params = [p for p in model.parameters() if p.requires_grad]\n    if Adam:\n        optimizer = torch.optim.Adam(params, **Adam_config)\n    else:\n        optimizer = torch.optim.SGD(params, **SGD_config)\n        \n    best_precision = 0.01\n    best_epoch = 0\n    train_losses = []\n    val_maps = []\n    \n    for epoch in range(EPOCHS):\n        summary_loss.reset()\n        train_loss = train_fn(train_data_loader, model, optimizer, device, scheduler=None, epoch=epoch)\n        train_losses.append(train_loss.avg)\n        \n        valid_precision = eval_fn(validation_data_loader, model, device, num_classes, class_names)\n        val_maps.append(valid_precision)\n        \n        print(f'|EPOCH {epoch+1}| TRAIN_LOSS {train_loss.avg}| VAL_PRECISION {valid_precision}|')\n        \n        # Save the model with the highest mAP\n        if valid_precision > best_precision:\n            best_precision = valid_precision\n            best_epoch = epoch + 1\n            torch.save(model.state_dict(), f'FRCNN_best_{fold}_epoch_{best_epoch}.pth')\n            print(f'Best model found at epoch {best_epoch} with mAP {best_precision:.4f}')\n    \n    # Save the model at the last epoch\n    torch.save(model.state_dict(), f'FRCNN_last_epoch_{EPOCHS}_{fold}.pth')\n    print(f'Model saved at last epoch {EPOCHS}')\n    \n    # Plot training and validation performance\n    plt.figure(figsize=(12, 5))\n    plt.subplot(1, 2, 1)\n    plt.plot(train_losses, label='Training Loss')\n    plt.xlabel('Epoch')\n    plt.ylabel('Loss')\n    plt.title('Training Loss Curve')\n    plt.legend()\n\n    plt.subplot(1, 2, 2)\n    plt.plot(val_maps, label='Validation mAP')\n    plt.xlabel('Epoch')\n    plt.ylabel('mAP')\n    plt.title('Validation mAP Curve')\n    plt.legend()\n\n    plt.tight_layout()\n    plt.show()\n    \n    # Return validation_data_loader and model\n    return validation_data_loader, model\n\n\n# Class names\nclass_names = ['class0', 'class_1', 'class_2', 'class_3', 'class_4']\n\n# Execute training and evaluation\nfold_maps = []\nfor fold in range(n_folds):\n    print(f\"Training Fold {fold}...\")\n    validation_data_loader, model = run(fold)  # Unpack returned values\n    valid_map = eval_fn(validation_data_loader, model, torch.device('cuda'), num_classes, class_names)\n    fold_maps.append(valid_map)\n\n    proceed = input(f\"Fold {fold} completed. Do you want to continue to the next fold? (y/n): \")\n    if proceed.lower() != 'y':\n        print(\"Stopping execution.\")\n        break\n\nprint(f\"Average mAP across folds: {np.mean(fold_maps):.4f}\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nimport torchvision\nimport cv2\nimport numpy as np\nimport matplotlib.pyplot as plt\n\ndef detect_outer_oranges(image_path, model_path, num_classes=4, score_threshold=0.5, iou_threshold=0.5, device=None):\n    \"\"\"\n    Detect oranges from a new image using a saved model, handle nested boxes, and count the total number of outer boxes.\n\n    Args:\n        image_path (str): Path to the input image.\n        model_path (str): Path to the saved Faster R-CNN model.\n        num_classes (int): Number of classes in the dataset.\n        score_threshold (float): Confidence score threshold for predictions.\n        iou_threshold (float): IoU threshold for non-maximum suppression (NMS).\n        device (torch.device): The device to use for inference (CPU or GPU).\n    \n    Returns:\n        int: The total count of oranges based on outer bounding boxes.\n    \"\"\"\n\n    # Load the model\n    if device is None:\n        device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')\n\n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=False, num_classes=num_classes + 1)\n    model.load_state_dict(torch.load(model_path))\n    model.to(device)\n    model.eval()\n\n    # Load and preprocess the image\n    image = cv2.imread(image_path)\n    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n    image_tensor = torch.tensor(image_rgb / 255.0, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(device)\n\n    # Make predictions\n    with torch.no_grad():\n        outputs = model(image_tensor)\n\n    # Get the bounding boxes, scores, and labels from predictions\n    boxes = outputs[0]['boxes']\n    scores = outputs[0]['scores']\n    labels = outputs[0]['labels']\n\n    # Apply score threshold\n    valid_indices = scores >= score_threshold\n    boxes = boxes[valid_indices].cpu().numpy()\n    scores = scores[valid_indices].cpu().numpy()\n    labels = labels[valid_indices].cpu().numpy()\n\n    # Apply non-maximum suppression (NMS)\n    keep_indices = torchvision.ops.nms(torch.tensor(boxes), torch.tensor(scores), iou_threshold)\n    boxes = boxes[keep_indices.numpy()]\n    scores = scores[keep_indices.numpy()]\n    labels = labels[keep_indices.numpy()]\n\n    # Identify and retain only outer boxes\n    outer_boxes = []\n    for i, box1 in enumerate(boxes):\n        x1_min, y1_min, x1_max, y1_max = box1\n        is_outer = True\n        for j, box2 in enumerate(boxes):\n            if i != j:\n                x2_min, y2_min, x2_max, y2_max = box2\n                # Check if box1 is completely inside box2\n                if x1_min >= x2_min and y1_min >= y2_min and x1_max <= x2_max and y1_max <= y2_max:\n                    is_outer = False\n                    break\n        if is_outer:\n            outer_boxes.append((box1, labels[i], scores[i]))\n\n    # Calculate the total count of oranges using only outer boxes\n    total_oranges = int(sum(label for _, label, _ in outer_boxes))\n\n    # Draw the bounding boxes\n    for box, label, score in outer_boxes:\n        x1, y1, x2, y2 = map(int, box)\n        color = (0, 255, 0)  # Green for bounding boxes\n        cv2.rectangle(image, (x1, y1), (x2, y2), color, 2)\n\n        # Draw the class label and score\n        label_text = f'{label}'\n        cv2.putText(image, label_text, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)\n\n        # Print predicted labels and scores\n        print(f'Predicted label: {label}, Score: {score:.2f}, Box: {box}')\n\n    # Display the total count of oranges on the image\n    cv2.putText(image, f'Total Oranges: {total_oranges}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)\n\n    # Display the image with bounding boxes\n    plt.figure(figsize=(10, 10))\n    plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))\n    plt.axis('off')\n    plt.show()\n\n    # Return the total count of oranges\n    return total_oranges\n\n# Example usage\nimage_path = \"/kaggle/input/oranges-dataset-1955/Orange Yield Estimation 1955/Images/Vid-0-frame-100.jpg\"\nmodel_path = \"/kaggle/working/FRCNN_last_epoch_20_0.pth\"\ntotal_oranges = detect_outer_oranges(image_path, model_path, num_classes=4)\nprint(f'Total Oranges Detected: {total_oranges}')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport numpy as np\nimport pandas as pd\nimport random\nimport time\nfrom tqdm import tqdm  # Progress bar\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.metrics import accuracy_score\n\n# PyTorch\nimport torch\nimport torch.nn as nn\nfrom torch.utils.data import Dataset, DataLoader\nfrom torch.utils.data.sampler import SequentialSampler, RandomSampler\n\n# Torchvision\nimport torchvision\nfrom torchvision.models.detection.faster_rcnn import FastRCNNPredictor\nfrom torchvision.ops import box_iou, nms\n\n# Albumentations\nimport albumentations as A\nfrom albumentations.pytorch.transforms import ToTensorV2\n\n# Sklearn\nfrom sklearn.model_selection import StratifiedKFold\n\n# OpenCV\nimport cv2\n\n# Suppress warnings\nimport warnings\nwarnings.filterwarnings('ignore')\n\n# Check GPU availability\ngpu_info = !nvidia-smi\ngpu_info = '\\n'.join(gpu_info)\nif gpu_info.find('failed') >= 0:\n    print('Select the Runtime > \"Change runtime type\" menu to enable a GPU accelerator, ')\n    print('and then re-execute this cell.')\nelse:\n    print(gpu_info)\n\n# Configuration\nn_folds = 5\nseed = 2020\nnum_classes = 5\nBATCH_SIZE = 8  # Consistent batch size for training and validation\nLR = 0.05\nEPOCHS = 50\nimg_size_training = 800\n\n# Optimizer configuration\nAdam = False\nif Adam:\n    Adam_config = {\"lr\": 0.001, \"betas\": (0.9, 0.999), \"eps\": 1e-08}\nelse:\n    SGD_config = {\"lr\": 0.001, \"momentum\": 0.9, \"weight_decay\": 0.001}\n\n# Seed everything for reproducibility\ndef seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = True\nseed_everything(seed)\n\n# Load dataset\nbboxes_df = pd.read_csv('/kaggle/input/multiclass-orange-yield-estimation-4756/Oranges Dataset 4756/train4756.csv')\n\n# Parse bounding boxes\nbboxs = np.stack(bboxes_df['bbox'].apply(lambda x: np.fromstring(x[1:-1], sep=',')))\nfor i, column in enumerate(['x', 'y', 'w', 'h']):\n    bboxes_df[column] = bboxs[:, i]\nbboxes_df.drop(columns=['bbox'], inplace=True)\n\n# Filter out invalid bounding boxes with non-positive width or height\ninvalid_boxes = (bboxes_df['w'] <= 0) | (bboxes_df['h'] <= 0)\nprint(f\"Removing {invalid_boxes.sum()} invalid bounding boxes with width or height <= 0.\")\nbboxes_df = bboxes_df[~invalid_boxes].reset_index(drop=True)\n\n# Create stratified folds\nskf = StratifiedKFold(n_splits=n_folds, shuffle=True, random_state=seed)\ndf_folds = bboxes_df[['image_id']].copy()\ndf_folds.loc[:, 'bbox_count'] = 1\ndf_folds = df_folds.groupby('image_id').count()\ndf_folds.loc[:, 'source'] = bboxes_df[['image_id', 'source']].groupby('image_id').min()['source']\ndf_folds.loc[:, 'stratify_group'] = np.char.add(\n    df_folds['source'].values.astype(str),\n    df_folds['bbox_count'].apply(lambda x: f'_{x // 15}').values.astype(str))\ndf_folds.loc[:, 'fold'] = 0\n\nfor fold_number, (train_index, val_index) in enumerate(skf.split(X=df_folds.index, y=df_folds['stratify_group'])):\n    df_folds.loc[df_folds.iloc[val_index].index, 'fold'] = fold_number\n\n# Dataset directory\nDIR_TRAIN = '/kaggle/input/multiclass-orange-yield-estimation-4756/Oranges Dataset 4756/Images'\n\n# Custom Dataset Class\nclass WheatDataset(Dataset):\n    def __init__(self, image_ids, dataframe, transforms=None):\n        self.image_ids = image_ids\n        self.df = dataframe\n        self.transforms = transforms\n        \n    def __len__(self):\n        return len(self.image_ids)\n    \n    def __getitem__(self, index):\n        image_id = self.image_ids[index]\n        records = self.df[self.df['image_id'] == image_id]\n        \n        # Load and normalize image\n        image = cv2.imread(f'{DIR_TRAIN}/{image_id}.jpg', cv2.IMREAD_COLOR)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB).astype(np.float32)\n        image /= 255.0\n        \n        # Log image size\n        image_size = image.shape[:2]  # (height, width)\n        \n        # Adjust bounding boxes from COCO format to Pascal VOC\n        boxes = records[['x', 'y', 'w', 'h']].values\n        boxes[:, 2] = boxes[:, 0] + boxes[:, 2]\n        boxes[:, 3] = boxes[:, 1] + boxes[:, 3]\n        \n        # Convert labels to tensor\n        labels = torch.tensor(records['class_id'].values, dtype=torch.int64)\n        \n        area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])\n        area = torch.as_tensor(area, dtype=torch.float32)\n        iscrowd = torch.zeros((records.shape[0],), dtype=torch.int64)\n        \n        target = {\n            'boxes': torch.as_tensor(boxes, dtype=torch.float32),\n            'labels': labels,\n            'image_id': torch.tensor([index]),\n            'area': area,\n            'iscrowd': iscrowd\n        }\n        \n        # Apply transformations if any\n        if self.transforms:\n            sample = {\n                'image': image,\n                'bboxes': target['boxes'],\n                'labels': labels\n            }\n            sample = self.transforms(**sample)\n            image = sample['image']\n            target['boxes'] = torch.as_tensor(sample['bboxes'], dtype=torch.float32)\n        \n        return image, target, image_id, image_size\n\n# Albumentations for training\ndef get_train_transforms():\n    return A.Compose(\n        [\n            A.OneOf([\n                A.HueSaturationValue(hue_shift_limit=0.2, sat_shift_limit=0.2, val_shift_limit=0.2, p=0.3),\n                A.RandomBrightnessContrast(brightness_limit=0.2, contrast_limit=0.2, p=0.3),\n                A.RGBShift(r_shift_limit=20/255, g_shift_limit=20/255, b_shift_limit=10/255, p=0.3)\n            ], p=0.2),\n            A.OneOf([\n                A.RandomGamma(gamma_limit=(80, 120), p=0.3),\n                A.Blur(p=0.6),\n                A.GaussNoise(var_limit=(0.01, 0.05), mean=0, p=0.05),\n                A.ToGray(p=0.05)\n            ], p=0.1),\n            A.OneOf([\n                A.HorizontalFlip(p=1),\n                A.VerticalFlip(p=1),\n                A.Transpose(p=1),\n                A.RandomRotate90(p=1)\n            ], p=0.7),\n            A.RandomFog(fog_coef_lower=0.1, fog_coef_upper=0.2, p=0.02),\n            A.RandomSizedBBoxSafeCrop(img_size_training, img_size_training, p=0.05),\n            A.Resize(height=img_size_training, width=img_size_training, p=1),\n            A.Cutout(num_holes=random.randint(1, 6), max_h_size=64, max_w_size=64, fill_value=0, p=0.15),\n            ToTensorV2(p=1.0),\n        ],\n        p=1.0,\n        bbox_params={\n            'format': 'pascal_voc',\n            'label_fields': ['labels']\n        }\n    )\n\n# Albumentations for validation\ndef get_valid_transforms():\n    return A.Compose([\n        A.Resize(height=img_size_training, width=img_size_training, p=1),\n        ToTensorV2(p=1.0)\n    ], bbox_params={\n        'format': 'pascal_voc',\n        'label_fields': ['labels']\n    })\n\n# Helper functions for dataset and dataloader\ndef get_validation_dataset(df):\n    return WheatDataset(\n        image_ids=df.index.values,\n        dataframe=bboxes_df,\n        transforms=get_valid_transforms()\n    )\n    \ndef get_train_dataset(df):    \n    return WheatDataset(\n        image_ids=df.index.values,\n        dataframe=bboxes_df,\n        transforms=get_train_transforms()\n    )\n\ndef get_validation_data_loader(valid_dataset, batch_size=BATCH_SIZE):  # Use consistent batch size\n    return DataLoader(\n        valid_dataset,\n        batch_size=batch_size,\n        shuffle=False,\n        num_workers=4,\n        collate_fn=collate_fn\n    )    \n\ndef get_train_data_loader(train_dataset, batch_size=BATCH_SIZE):  # Use consistent batch size\n    return DataLoader(\n        train_dataset,\n        batch_size=batch_size,\n        shuffle=False,\n        num_workers=4,\n        collate_fn=collate_fn\n    ) \n\ndef collate_fn(batch):\n    return tuple(zip(*batch))\n\n# Model definition\ndef get_model():    \n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)\n    in_features = model.roi_heads.box_predictor.cls_score.in_features\n    model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)\n    return model\n\n# Average Meter for tracking loss\nclass AverageMeter:\n    def __init__(self):\n        self.reset()\n    \n    def reset(self):\n        self.val = 0\n        self.avg = 0\n        self.sum = 0\n        self.count = 0\n    \n    def update(self, val, n=1):\n        self.val = val\n        self.sum += val * n\n        self.count += n\n        self.avg = self.sum / self.count\n\n# Training function\ndef train_fn(data_loader, model, optimizer, device, scheduler, epoch):\n    model.train()\n    summary_loss = AverageMeter()\n    tk0 = tqdm(data_loader, total=len(data_loader), desc=f\"Training Epoch {epoch + 1}\")\n    \n    for step, (images, targets, image_ids, image_sizes) in enumerate(tk0):   \n        if len(targets) < 1:\n            targets = [{'boxes': torch.zeros((0, 4)).to(device), 'labels': torch.zeros(0).to(device)}]\n            \n        images = list(image.to(device) for image in images)\n        targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n        loss_dict = model(images, targets)        \n        losses = sum(loss for loss in loss_dict.values())\n\n        optimizer.zero_grad()\n        losses.backward()\n        optimizer.step()\n        \n        if scheduler is not None:\n            scheduler.step()\n        \n        summary_loss.update(losses.item(), len(images))\n        tk0.set_postfix(loss=summary_loss.avg)\n    \n    return summary_loss\n\n# Function to calculate estimation accuracy\ndef calculate_accuracy(outputs, targets, iou_threshold=0.5, confidence_threshold=0.5):\n    true_positives = 0\n    false_positives = 0\n    false_negatives = 0\n\n    for output, target in zip(outputs, targets):\n        # Extract predictions and ground truth\n        pred_boxes = output['boxes'].cpu().numpy()\n        pred_scores = output['scores'].cpu().numpy()\n        pred_labels = output['labels'].cpu().numpy()\n        gt_boxes = target['boxes'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        # Filter predictions based on confidence score\n        high_confidence_mask = pred_scores >= confidence_threshold\n        pred_boxes = pred_boxes[high_confidence_mask]\n        pred_labels = pred_labels[high_confidence_mask]\n\n        # Initialize matched flags for ground truth objects\n        gt_matched = [False] * len(gt_boxes)\n\n        # Match predictions to ground truth objects\n        for pred_box, pred_label in zip(pred_boxes, pred_labels):\n            best_iou = 0\n            best_gt_idx = -1\n\n            # Find the ground truth object with the highest IoU\n            for gt_idx, (gt_box, gt_label) in enumerate(zip(gt_boxes, gt_labels)):\n                if gt_matched[gt_idx]:\n                    continue  # Skip already matched ground truth objects\n\n                iou = box_iou(torch.tensor([pred_box]), torch.tensor([gt_box])).item()\n                if iou > best_iou:\n                    best_iou = iou\n                    best_gt_idx = gt_idx\n\n            # Check if the best IoU meets the threshold\n            if best_iou >= iou_threshold:\n                if pred_label == gt_labels[best_gt_idx]:\n                    true_positives += 1  # Correct prediction\n                else:\n                    false_positives += 1  # Incorrect label\n                gt_matched[best_gt_idx] = True  # Mark as matched\n            else:\n                false_positives += 1  # No matching ground truth\n\n        # Count false negatives (unmatched ground truth objects)\n        false_negatives += sum(not matched for matched in gt_matched)\n\n    # Calculate accuracy\n    if true_positives + false_positives + false_negatives == 0:\n        return 0.0  # Avoid division by zero\n\n    accuracy = (true_positives / (true_positives + false_positives + false_negatives)) * 100\n    return accuracy\n\n# Function to calculate AP per class\ndef calculate_ap_per_class(outputs, targets, iou_thresholds, num_classes):\n    aps = {cls: [] for cls in range(num_classes)}\n    for threshold in iou_thresholds:\n        for cls in range(num_classes):\n            tp, fp, fn = 0, 0, 0\n            for output, target in zip(outputs, targets):\n                pred_boxes = output['boxes'].cpu().numpy()\n                pred_scores = output['scores'].cpu().numpy()\n                pred_labels = output['labels'].cpu().numpy()\n                gt_boxes = target['boxes'].cpu().numpy()\n                gt_labels = target['labels'].cpu().numpy()\n\n                if len(pred_boxes) == 0:\n                    fn += len(gt_boxes[gt_labels == cls])\n                    continue\n                \n                if len(gt_boxes) == 0:\n                    fp += len(pred_boxes[pred_labels == cls])\n                    continue\n\n                ious = box_iou(torch.tensor(pred_boxes[pred_labels == cls]), torch.tensor(gt_boxes[gt_labels == cls])).numpy()\n                matches = ious >= threshold\n\n                tp += matches.sum()\n                fp += len(pred_boxes[pred_labels == cls]) - matches.sum()\n                fn += len(gt_boxes[gt_labels == cls]) - matches.sum()\n\n            precision = tp / (tp + fp) if tp + fp > 0 else 0\n            recall = tp / (tp + fn) if tp + fn > 0 else 0\n            ap = precision * recall\n            aps[cls].append(ap)\n    \n    mean_aps = {cls: np.mean(aps[cls]) if aps[cls] else 0.0 for cls in range(num_classes)}\n    return mean_aps\n\n# Function to calculate mAP\ndef calculate_map(outputs, targets, iou_thresholds):\n    aps = []\n    for threshold in iou_thresholds:\n        ap = calculate_ap_per_threshold(outputs, targets, threshold)\n        aps.append(ap)\n    return np.mean(aps) if aps else 0.0\n\ndef calculate_ap_per_threshold(outputs, targets, iou_threshold):\n    tp, fp, fn = 0, 0, 0\n    for output, target in zip(outputs, targets):\n        pred_boxes = output['boxes'].cpu().numpy()\n        pred_scores = output['scores'].cpu().numpy()\n        pred_labels = output['labels'].cpu().numpy()\n        gt_boxes = target['boxes'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        if len(pred_boxes) == 0:\n            fn += len(gt_boxes)\n            continue\n        \n        if len(gt_boxes) == 0:\n            fp += len(pred_boxes)\n            continue\n\n        ious = box_iou(torch.tensor(pred_boxes), torch.tensor(gt_boxes)).numpy()\n        matches = ious >= iou_threshold\n\n        tp += matches.sum()\n        fp += len(pred_boxes) - matches.sum()\n        fn += len(gt_boxes) - matches.sum()\n\n    precision = tp / (tp + fp) if tp + fp > 0 else 0\n    recall = tp / (tp + fn) if tp + fn > 0 else 0\n    ap = precision * recall\n    return ap\n\n# Function to calculate F1 score, precision, and recall\ndef calculate_f1_precision_recall(outputs, targets, num_classes):\n    \"\"\"\n    Calculate precision, recall, and F1 score for each class.\n    \n    Args:\n        outputs (list): List of model outputs (predictions).\n        targets (list): List of ground truth targets.\n        num_classes (int): Number of classes.\n    \n    Returns:\n        precision (list): Precision for each class.\n        recall (list): Recall for each class.\n        f1_score (list): F1 score for each class.\n    \"\"\"\n    # Initialize true positives, false positives, and false negatives for each class\n    tp = [0] * num_classes\n    fp = [0] * num_classes\n    fn = [0] * num_classes\n\n    for output, target in zip(outputs, targets):\n        pred_boxes = output['boxes'].cpu().numpy()\n        pred_scores = output['scores'].cpu().numpy()\n        pred_labels = output['labels'].cpu().numpy()\n        gt_boxes = target['boxes'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        # Iterate over each class\n        for cls in range(num_classes):\n            # Filter predictions and ground truth for the current class\n            pred_mask = pred_labels == cls\n            gt_mask = gt_labels == cls\n\n            pred_boxes_cls = pred_boxes[pred_mask]\n            gt_boxes_cls = gt_boxes[gt_mask]\n\n            # Calculate IoU between predictions and ground truth\n            if len(pred_boxes_cls) > 0 and len(gt_boxes_cls) > 0:\n                ious = box_iou(torch.tensor(pred_boxes_cls), torch.tensor(gt_boxes_cls)).numpy()\n                matches = ious >= 0.5  # IoU threshold for matching\n\n                # Count true positives and false positives\n                tp[cls] += matches.sum()\n                fp[cls] += len(pred_boxes_cls) - matches.sum()\n                fn[cls] += len(gt_boxes_cls) - matches.sum()\n            elif len(pred_boxes_cls) > 0:\n                # All predictions are false positives if there are no ground truth boxes\n                fp[cls] += len(pred_boxes_cls)\n            elif len(gt_boxes_cls) > 0:\n                # All ground truth boxes are false negatives if there are no predictions\n                fn[cls] += len(gt_boxes_cls)\n\n    # Calculate precision, recall, and F1 score for each class\n    precision = []\n    recall = []\n    f1_score = []\n\n    for cls in range(num_classes):\n        precision_cls = tp[cls] / (tp[cls] + fp[cls]) if tp[cls] + fp[cls] > 0 else 0\n        recall_cls = tp[cls] / (tp[cls] + fn[cls]) if tp[cls] + fn[cls] > 0 else 0\n        f1_cls = 2 * (precision_cls * recall_cls) / (precision_cls + recall_cls) if precision_cls + recall_cls > 0 else 0\n\n        precision.append(precision_cls)\n        recall.append(recall_cls)\n        f1_score.append(f1_cls)\n\n    return precision, recall, f1_score\n    \n# Evaluation function with AP per class and confusion matrix\ndef eval_fn(data_loader, model, device, num_classes, class_names):\n    model.eval()\n    iou_thresholds = np.arange(0.5, 0.95, 0.05)\n    all_maps = []\n    all_outputs = []\n    all_targets = []\n\n    with torch.no_grad():\n        tk0 = tqdm(data_loader, total=len(data_loader), desc=\"Validation\")\n        for images, targets, _, _ in tk0:\n            images = list(image.to(device) for image in images)\n            targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n            outputs = model(images)\n            batch_map = calculate_map(outputs, targets, iou_thresholds)\n            all_maps.append(batch_map)\n            all_outputs.extend(outputs)\n            all_targets.extend(targets)\n\n    final_map = np.mean(all_maps)\n\n    # Calculate AP per class\n    mean_aps = calculate_ap_per_class(all_outputs, all_targets, iou_thresholds, num_classes)\n    print(\"Average Precision per Class:\", mean_aps)\n\n    # Calculate F1 score, precision, and recall\n    precision, recall, f1_score = calculate_f1_precision_recall(all_outputs, all_targets, num_classes)\n    print(\"Precision per Class:\", precision)\n    print(\"Recall per Class:\", recall)\n    print(\"F1 Score per Class:\", f1_score)\n\n    # Generate and plot confusion matrix\n    confusion_matrix = generate_confusion_matrix(all_outputs, all_targets, num_classes)\n    plot_confusion_matrix(confusion_matrix, class_names)\n\n    # Plot AP per class\n    plot_ap_per_class(mean_aps, class_names)\n\n    # Calculate estimation accuracy with confidence threshold\n    accuracy = calculate_accuracy(all_outputs, all_targets, iou_threshold=0.5, confidence_threshold=0.5)\n    print(f\"Estimation Accuracy: {accuracy:.2f}%\")\n\n    return final_map\n\n# Function to generate confusion matrix\ndef generate_confusion_matrix(outputs, targets, num_classes):\n    confusion_matrix = np.zeros((num_classes, num_classes))\n    for output, target in zip(outputs, targets):\n        pred_labels = output['labels'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n\n        # Only consider images where both predictions and ground truth are non-empty\n        if len(pred_labels) > 0 and len(gt_labels) > 0:\n            # Ensure the number of predictions matches the number of ground truth labels\n            min_length = min(len(pred_labels), len(gt_labels))\n            for pred_label, gt_label in zip(pred_labels[:min_length], gt_labels[:min_length]):\n                confusion_matrix[gt_label][pred_label] += 1\n\n    return confusion_matrix\n\n# Function to plot confusion matrix\ndef plot_confusion_matrix(confusion_matrix, class_names):\n    plt.figure(figsize=(10, 10))\n    sns.heatmap(confusion_matrix, annot=True, fmt='g', cmap='Blues', xticklabels=class_names, yticklabels=class_names)\n    plt.xlabel('Predicted')\n    plt.ylabel('Actual')\n    plt.title('Confusion Matrix')\n    plt.show()\n\n# Function to plot AP per class\ndef plot_ap_per_class(mean_aps, class_names):\n    plt.figure(figsize=(10, 5))\n    plt.bar(range(len(mean_aps)), list(mean_aps.values()), align='center')\n    plt.xticks(range(len(mean_aps)), class_names, rotation=45)\n    plt.xlabel('Class')\n    plt.ylabel('Average Precision')\n    plt.title('Average Precision per Class')\n    plt.show()\n\n# Function to print class instance sizes\ndef print_class_instance_sizes(data_loader, class_names):\n    class_counts = {cls: 0 for cls in range(len(class_names))}\n    \n    for _, targets, _, _ in data_loader:\n        for target in targets:\n            labels = target['labels'].cpu().numpy()\n            for label in labels:\n                class_counts[label] += 1\n    \n    print(\"Class Instance Sizes:\")\n    for cls, count in class_counts.items():\n        print(f\"{class_names[cls]}: {count} instances\")\n\n# Class names\nclass_names = ['class0', 'class_1', 'class_2', 'class_3', 'class_4']\n\n# Function to count oranges in predictions and ground truth\ndef count_oranges(outputs, targets, confidence_threshold=0.5):\n    \"\"\"\n    Count the total number of oranges predicted and in the ground truth.\n    Class 1 means 1 orange, class 2 means 2 oranges, etc.\n    \n    Args:\n        outputs (list): List of model outputs (predictions).\n        targets (list): List of ground truth targets.\n        confidence_threshold (float): Confidence threshold for filtering predictions.\n    \n    Returns:\n        pred_orange_count (int): Total number of oranges predicted.\n        gt_orange_count (int): Total number of oranges in ground truth.\n    \"\"\"\n    pred_orange_count = 0\n    gt_orange_count = 0\n\n    for output, target in zip(outputs, targets):\n        # Filter predictions based on confidence score\n        pred_scores = output['scores'].cpu().numpy()\n        pred_labels = output['labels'].cpu().numpy()\n        high_confidence_mask = pred_scores >= confidence_threshold\n        pred_labels = pred_labels[high_confidence_mask]\n\n        # Count predicted oranges based on class labels\n        pred_orange_count += pred_labels.sum()  # Sum of class labels = total oranges\n\n        # Count ground truth oranges based on class labels\n        gt_labels = target['labels'].cpu().numpy()\n        gt_orange_count += gt_labels.sum()  # Sum of class labels = total oranges\n\n    return pred_orange_count, gt_orange_count\n\ndef visualize_predictions(images, outputs, targets, image_ids, class_names, confidence_threshold=0.5):\n    \"\"\"\n    Visualize predictions and ground truth bounding boxes with counts and image name.\n    \n    Args:\n        images (list): List of images.\n        outputs (list): List of model outputs (predictions).\n        targets (list): List of ground truth targets.\n        image_ids (list): List of image IDs (names).\n        class_names (list): List of class names.\n        confidence_threshold (float): Confidence threshold for filtering predictions.\n    \"\"\"\n    for i, (image, output, target, image_id) in enumerate(zip(images, outputs, targets, image_ids)):\n        # Convert image to numpy array\n        image = image.permute(1, 2, 0).cpu().numpy()\n        image = (image * 255).astype(np.uint8)\n\n        # Filter predictions based on confidence score\n        pred_boxes = output['boxes'].cpu().numpy()\n        pred_scores = output['scores'].cpu().numpy()\n        pred_labels = output['labels'].cpu().numpy()\n        high_confidence_mask = pred_scores >= confidence_threshold\n        pred_boxes = pred_boxes[high_confidence_mask]\n        pred_labels = pred_labels[high_confidence_mask]\n\n        # Apply Non-Maximum Suppression (NMS) to remove duplicate predictions\n        keep_indices = nms(torch.tensor(pred_boxes), torch.tensor(pred_scores[high_confidence_mask]), iou_threshold=0.5)\n        pred_boxes = pred_boxes[keep_indices]\n        pred_labels = pred_labels[keep_indices]\n\n        # Calculate predicted orange count for this image\n        pred_orange_count = pred_labels.sum()\n\n        # Draw ground truth bounding boxes\n        gt_boxes = target['boxes'].cpu().numpy()\n        gt_labels = target['labels'].cpu().numpy()\n        gt_orange_count = gt_labels.sum()  # Calculate ground truth orange count for this image\n\n        for box, label in zip(gt_boxes, gt_labels):\n            x1, y1, x2, y2 = box.astype(int)\n            cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)\n            cv2.putText(image, f\"GT: {class_names[label]}\", (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)\n\n        # Draw predicted bounding boxes\n        for box, label in zip(pred_boxes, pred_labels):\n            x1, y1, x2, y2 = box.astype(int)\n            cv2.rectangle(image, (x1, y1), (x2, y2), (255, 0, 0), 2)\n            cv2.putText(image, f\"Pred: {class_names[label]} ({label} oranges)\", (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 0), 2)\n\n        # Display the image with counts and image name\n        plt.figure(figsize=(10, 10))\n        plt.imshow(image)\n        plt.axis('off')\n        plt.title(f\"Image: {image_id}\\nPredicted Oranges: {pred_orange_count}, Ground Truth Oranges: {gt_orange_count}\")\n        plt.show()\n\ndef evaluate_and_count_oranges(model, data_loader, device, class_names):\n    \"\"\"\n    Evaluate the model on the validation set and count oranges.\n    \n    Args:\n        model: Trained model.\n        data_loader: DataLoader for the validation set.\n        device: Device to run the model on.\n        class_names: List of class names.\n    \n    Returns:\n        pred_orange_count (int): Total number of oranges predicted.\n        gt_orange_count (int): Total number of oranges in ground truth.\n    \"\"\"\n    model.eval()\n    all_outputs = []\n    all_targets = []\n    all_images = []\n    all_image_ids = []  # Add this line to collect image IDs\n\n    with torch.no_grad():\n        for images, targets, image_ids, _ in data_loader:  # Unpack image_ids here\n            images = list(image.to(device) for image in images)\n            targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n            outputs = model(images)\n            all_outputs.extend(outputs)\n            all_targets.extend(targets)\n            all_images.extend(images)\n            all_image_ids.extend(image_ids)  # Collect image IDs\n\n    # Count oranges in predictions and ground truth\n    pred_orange_count, gt_orange_count = count_oranges(all_outputs, all_targets)\n    print(f\"Total Predicted Oranges: {pred_orange_count}, Total Ground Truth Oranges: {gt_orange_count}\")\n\n    # Visualize some samples\n    visualize_predictions(all_images[:5], all_outputs[:5], all_targets[:5], all_image_ids[:5], class_names)  # Pass image_ids\n\n    return pred_orange_count, gt_orange_count\n\n# Modify the run function to include evaluation and counting\ndef run(fold):\n    summary_loss = AverageMeter()\n    \n    # Split data into training and validation sets\n    df_train = df_folds[df_folds['fold'] != fold]\n    df_valid = df_folds[df_folds['fold'] == fold]\n    \n    # Get data loaders\n    train_dataset = get_train_dataset(df_train)\n    train_data_loader = get_train_data_loader(train_dataset, batch_size=BATCH_SIZE)\n    \n    validation_dataset = get_validation_dataset(df_valid)\n    validation_data_loader = get_validation_data_loader(validation_dataset, batch_size=BATCH_SIZE)\n          \n    # Print class instance sizes for training and validation\n    print(\"Training Class Instance Sizes:\")\n    print_class_instance_sizes(train_data_loader, class_names)\n    \n    print(\"Validation Class Instance Sizes:\")\n    print_class_instance_sizes(validation_data_loader, class_names)\n    \n    # Get GPU device\n    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n    \n    # Get model\n    model = get_model()\n    model = model.to(device)\n    \n    # Get optimizer\n    params = [p for p in model.parameters() if p.requires_grad]\n    if Adam:\n        optimizer = torch.optim.Adam(params, **Adam_config)\n    else:\n        optimizer = torch.optim.SGD(params, **SGD_config)\n        \n    best_precision = 0.01\n    best_epoch = 0\n    train_losses = []\n    val_maps = []\n    \n    for epoch in range(EPOCHS):\n        summary_loss.reset()\n        train_loss = train_fn(train_data_loader, model, optimizer, device, scheduler=None, epoch=epoch)\n        train_losses.append(train_loss.avg)\n        \n        # Evaluate the model on the validation set after each epoch\n        valid_precision = eval_fn(validation_data_loader, model, device, num_classes, class_names)\n        val_maps.append(valid_precision)\n        \n        print(f'|EPOCH {epoch+1}| TRAIN_LOSS {train_loss.avg}| VAL_PRECISION {valid_precision}|')\n        \n        # Save the model with the highest mAP\n        if valid_precision > best_precision:\n            best_precision = valid_precision\n            best_epoch = epoch + 1\n            torch.save(model.state_dict(), f'FRCNN_best_{fold}_epoch_{best_epoch}.pth')\n            print(f'Best model found at epoch {best_epoch} with mAP {best_precision:.4f}')\n    \n    # Save the model at the last epoch\n    torch.save(model.state_dict(), f'FRCNN_last_epoch_{EPOCHS}_{fold}.pth')\n    print(f'Model saved at last epoch {EPOCHS}')\n    \n    # Evaluate the model on the validation set and count oranges\n    print(f\"Evaluating the model on the validation set for fold {fold}...\")\n    pred_orange_count, gt_orange_count = evaluate_and_count_oranges(model, validation_data_loader, device, class_names)\n    print(f\"Fold {fold}: Predicted Oranges = {pred_orange_count}, Ground Truth Oranges = {gt_orange_count}\")\n\n    # Plot training and validation performance\n    plt.figure(figsize=(12, 5))\n    plt.subplot(1, 2, 1)\n    plt.plot(train_losses, label='Training Loss')\n    plt.xlabel('Epoch')\n    plt.ylabel('Loss')\n    plt.title('Training Loss Curve')\n    plt.legend()\n\n    plt.subplot(1, 2, 2)\n    plt.plot(val_maps, label='Validation mAP')\n    plt.xlabel('Epoch')\n    plt.ylabel('mAP')\n    plt.title('Validation mAP Curve')\n    plt.legend()\n\n    plt.tight_layout()\n    plt.show()\n    \n    # Return validation_data_loader and model\n    return validation_data_loader, model\n\n# Execute training and evaluation\nfold_maps = []\nfor fold in range(n_folds):\n    print(f\"Training Fold {fold}...\")\n    validation_data_loader, model = run(fold)  # Unpack returned values\n\n    proceed = input(f\"Fold {fold} completed. Do you want to continue to the next fold? (y/n): \")\n    if proceed.lower() != 'y':\n        print(\"Stopping execution.\")\n        break\n\nprint(f\"Average mAP across folds: {np.mean(fold_maps):.4f}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-19T17:01:56.020673Z","iopub.execute_input":"2025-03-19T17:01:56.02101Z","iopub.status.idle":"2025-03-20T00:52:47.993532Z","shell.execute_reply.started":"2025-03-19T17:01:56.020975Z","shell.execute_reply":"2025-03-20T00:52:47.992493Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nimport torchvision\nimport cv2\nimport numpy as np\nimport matplotlib.pyplot as plt\n\ndef detect_outer_oranges(image_path, model_path, num_classes=4, score_threshold=0.5, iou_threshold=0.5, device=None):\n    \"\"\"\n    Detect oranges from a new image using a saved model, handle nested boxes, and count the total number of outer boxes.\n\n    Args:\n        image_path (str): Path to the input image.\n        model_path (str): Path to the saved Faster R-CNN model.\n        num_classes (int): Number of classes in the dataset.\n        score_threshold (float): Confidence score threshold for predictions.\n        iou_threshold (float): IoU threshold for non-maximum suppression (NMS).\n        device (torch.device): The device to use for inference (CPU or GPU).\n    \n    Returns:\n        int: The total count of oranges based on outer bounding boxes.\n    \"\"\"\n\n    # Load the model\n    if device is None:\n        device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')\n\n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=False, num_classes=num_classes + 1)\n    model.load_state_dict(torch.load(model_path))\n    model.to(device)\n    model.eval()\n\n    # Load and preprocess the image\n    image = cv2.imread(image_path)\n    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n    image_tensor = torch.tensor(image_rgb / 255.0, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(device)\n\n    # Make predictions\n    with torch.no_grad():\n        outputs = model(image_tensor)\n\n    # Get the bounding boxes, scores, and labels from predictions\n    boxes = outputs[0]['boxes']\n    scores = outputs[0]['scores']\n    labels = outputs[0]['labels']\n\n    # Apply score threshold\n    valid_indices = scores >= score_threshold\n    boxes = boxes[valid_indices].cpu().numpy()\n    scores = scores[valid_indices].cpu().numpy()\n    labels = labels[valid_indices].cpu().numpy()\n\n    # Apply non-maximum suppression (NMS)\n    keep_indices = torchvision.ops.nms(torch.tensor(boxes), torch.tensor(scores), iou_threshold)\n    boxes = boxes[keep_indices.numpy()]\n    scores = scores[keep_indices.numpy()]\n    labels = labels[keep_indices.numpy()]\n\n    # Identify and retain only outer boxes\n    outer_boxes = []\n    for i, box1 in enumerate(boxes):\n        x1_min, y1_min, x1_max, y1_max = box1\n        is_outer = True\n        for j, box2 in enumerate(boxes):\n            if i != j:\n                x2_min, y2_min, x2_max, y2_max = box2\n                # Check if box1 is completely inside box2\n                if x1_min >= x2_min and y1_min >= y2_min and x1_max <= x2_max and y1_max <= y2_max:\n                    is_outer = False\n                    break\n        if is_outer:\n            outer_boxes.append((box1, labels[i], scores[i]))\n\n    # Calculate the total count of oranges using only outer boxes\n    total_oranges = int(sum(label for _, label, _ in outer_boxes))\n\n    # Draw the bounding boxes\n    for box, label, score in outer_boxes:\n        x1, y1, x2, y2 = map(int, box)\n        color = (0, 255, 0)  # Green for bounding boxes\n        cv2.rectangle(image, (x1, y1), (x2, y2), color, 2)\n\n        # Draw the class label and score\n        label_text = f'{label}'\n        cv2.putText(image, label_text, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)\n\n        # Print predicted labels and scores\n        print(f'Predicted label: {label}, Score: {score:.2f}, Box: {box}')\n\n    # Display the total count of oranges on the image\n    cv2.putText(image, f'Total Oranges: {total_oranges}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)\n\n    # Display the image with bounding boxes\n    plt.figure(figsize=(10, 10))\n    plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))\n    plt.axis('off')\n    plt.show()\n\n    # Return the total count of oranges\n    return total_oranges\n\n# Example usage\nimage_path = \"/kaggle/input/multiclass-orange-yield-estimation-4756/Oranges Dataset 4756/Images/Vid-1-frame-10-2024.jpg\"\nmodel_path = \"/kaggle/working/FRCNN_last_epoch_50_0.pth\"\ntotal_oranges = detect_outer_oranges(image_path, model_path, num_classes=4)\nprint(f'Total Oranges Detected: {total_oranges}')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-20T01:12:22.261316Z","iopub.execute_input":"2025-03-20T01:12:22.261668Z","iopub.status.idle":"2025-03-20T01:12:23.613865Z","shell.execute_reply.started":"2025-03-20T01:12:22.261635Z","shell.execute_reply":"2025-03-20T01:12:23.61313Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nimport torchvision\nimport cv2\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport requests\nfrom io import BytesIO\nfrom PIL import Image\n\ndef detect_outer_oranges(image_url, model_path, num_classes=4, score_threshold=0.5, iou_threshold=0.5, device=None):\n    \"\"\"\n    Detect oranges from an image URL using a saved model, handle nested boxes, and count the total number of outer boxes.\n\n    Args:\n        image_url (str): URL of the input image.\n        model_path (str): Path to the saved Faster R-CNN model.\n        num_classes (int): Number of classes in the dataset.\n        score_threshold (float): Confidence score threshold for predictions.\n        iou_threshold (float): IoU threshold for non-maximum suppression (NMS).\n        device (torch.device): The device to use for inference (CPU or GPU).\n    \n    Returns:\n        int: The total count of oranges based on outer bounding boxes.\n    \"\"\"\n\n    # Load the model\n    if device is None:\n        device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')\n\n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=False, num_classes=num_classes + 1)\n    model.load_state_dict(torch.load(model_path, map_location=device))\n    model.to(device)\n    model.eval()\n\n    # Download and preprocess the image\n    response = requests.get(image_url)\n    image_pil = Image.open(BytesIO(response.content)).convert('RGB')\n    image_np = np.array(image_pil)\n    image_tensor = torch.tensor(image_np / 255.0, dtype=torch.float32).permute(2, 0, 1).unsqueeze(0).to(device)\n\n    # Make predictions\n    with torch.no_grad():\n        outputs = model(image_tensor)\n\n    # Get the bounding boxes, scores, and labels from predictions\n    boxes = outputs[0]['boxes']\n    scores = outputs[0]['scores']\n    labels = outputs[0]['labels']\n\n    # Apply score threshold\n    valid_indices = scores >= score_threshold\n    boxes = boxes[valid_indices].cpu().numpy()\n    scores = scores[valid_indices].cpu().numpy()\n    labels = labels[valid_indices].cpu().numpy()\n\n    # Apply non-maximum suppression (NMS)\n    keep_indices = torchvision.ops.nms(torch.tensor(boxes), torch.tensor(scores), iou_threshold)\n    boxes = boxes[keep_indices.numpy()]\n    scores = scores[keep_indices.numpy()]\n    labels = labels[keep_indices.numpy()]\n\n    # Identify and retain only outer boxes\n    outer_boxes = []\n    for i, box1 in enumerate(boxes):\n        x1_min, y1_min, x1_max, y1_max = box1\n        is_outer = True\n        for j, box2 in enumerate(boxes):\n            if i != j:\n                x2_min, y2_min, x2_max, y2_max = box2\n                if x1_min >= x2_min and y1_min >= y2_min and x1_max <= x2_max and y1_max <= y2_max:\n                    is_outer = False\n                    break\n        if is_outer:\n            outer_boxes.append((box1, labels[i], scores[i]))\n\n    # Calculate the total count of oranges using only outer boxes\n    total_oranges = int(sum(label for _, label, _ in outer_boxes))\n\n    # Draw the bounding boxes\n    image = cv2.cvtColor(image_np, cv2.COLOR_RGB2BGR)\n    for box, label, score in outer_boxes:\n        x1, y1, x2, y2 = map(int, box)\n        color = (0, 255, 0)  # Green for bounding boxes\n        cv2.rectangle(image, (x1, y1), (x2, y2), color, 2)\n        cv2.putText(image, f'{label}', (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)\n        print(f'Predicted label: {label}, Score: {score:.2f}, Box: {box}')\n\n    cv2.putText(image, f'Total Oranges: {total_oranges}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)\n    plt.figure(figsize=(10, 10))\n    plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))\n    plt.axis('off')\n    plt.show()\n\n    return total_oranges\n\n# Example usage\nimage_url = \"https://rameshwarammarble.wordpress.com/wp-content/uploads/2020/07/5130.jpg\"\nmodel_path = \"/kaggle/working/FRCNN_last_epoch_50_0.pth\"\ntotal_oranges = detect_outer_oranges(image_url, model_path, num_classes=4)\nprint(f'Total Oranges Detected: {total_oranges}')\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-03-20T01:35:17.659513Z","iopub.execute_input":"2025-03-20T01:35:17.659827Z","iopub.status.idle":"2025-03-20T01:35:19.438266Z","shell.execute_reply.started":"2025-03-20T01:35:17.659802Z","shell.execute_reply":"2025-03-20T01:35:19.437414Z"}},"outputs":[],"execution_count":null}]}