{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"markdown","source":"## <u>Introduction</u>\n* Reference Kernel => https://www.kaggle.com/pestipeti/pytorch-starter-fasterrcnn-train.\n* For inference => https://www.kaggle.com/pestipeti/pytorch-starter-fasterrcnn-inference.","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport cv2\nimport os\nimport re\nimport albumentations as A\nimport torch\nimport torchvision\nimport time\n\nfrom torchvision.models.detection.faster_rcnn import FastRCNNPredictor\nfrom torchvision.models.detection import FasterRCNN\nfrom torchvision.models.detection.rpn import AnchorGenerator\nfrom torch.utils.data import DataLoader, Dataset\nfrom torch.utils.data.sampler import SequentialSampler\nfrom PIL import Image\nfrom albumentations.pytorch.transforms import ToTensorV2\nfrom matplotlib import pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"DIR_INPUT = '../input/global-wheat-detection'\nDIR_TRAIN = f\"{DIR_INPUT}/train\"\nDIR_TEST = f\"{DIR_INPUT}/test\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.read_csv(f\"{DIR_INPUT}/train.csv\")\nprint(train_df.shape)\ntrain_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['x'] = -1\ntrain_df['y'] = -1\ntrain_df['w'] = -1\ntrain_df['h'] = -1\n\ndef expand_bbox(x):\n    r = np.array(re.findall(\"([0-9]+[.]?[0-9]*)\", x))\n    if len(r) == 0:\n        r = [-1, -1, -1, -1]\n    return r\n\ntrain_df[['x', 'y', 'w', 'h']] = np.stack(train_df['bbox'].apply(lambda x: expand_bbox(x)))\ntrain_df.drop(columns=['bbox'], inplace=True)\ntrain_df['x'] = train_df['x'].astype(np.float)\ntrain_df['y'] = train_df['y'].astype(np.float)\ntrain_df['w'] = train_df['w'].astype(np.float)\ntrain_df['h'] = train_df['h'].astype(np.float)\n\ntrain_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"image_ids = train_df['image_id'].unique()\nvalid_ids = image_ids[-665:]\ntrain_ids = image_ids[:-665]\nprint(len(train_ids))\nprint(len(valid_ids))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"valid_df = train_df[train_df['image_id'].isin(valid_ids)]\ntrain_df = train_df[train_df['image_id'].isin(train_ids)]\n\nvalid_df.shape, train_df.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class WheatDataset(Dataset):\n    def __init__(self, dataframe, image_dir, transforms=None):\n        super().__init__()\n\n        self.image_ids = dataframe['image_id'].unique()\n        self.df = dataframe\n        self.image_dir = image_dir\n        self.transforms = transforms\n        \n    def __getitem__(self, index: int):\n\n        image_id = self.image_ids[index]\n        records = self.df[self.df['image_id'] == image_id]\n        \n#         image = Image.open(f\"{self.image_dir}/{image_id}.jpg\")\n#         image = image.convert('RGB')\n#         image = np.array(image)\n        image = cv2.imread(f\"{self.image_dir}/{image_id}.jpg\", cv2.IMREAD_COLOR).astype(np.float32)\n#         image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB).astype(np.float32)\n        image /= 255.0\n    \n        boxes = records[['x', 'y', 'w', 'h']].values\n        boxes[:, 2] = boxes[:, 0] + boxes[:, 2]\n        boxes[:, 3] = boxes[:, 1] + boxes[:, 3]\n        \n        area = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])\n        area = torch.as_tensor(area, dtype=torch.float32)\n\n        # there is only one class\n        labels = torch.ones((records.shape[0],), dtype=torch.int64)\n        \n        # suppose all instances are not crowd\n        iscrowd = torch.zeros((records.shape[0],), dtype=torch.int64)\n        \n        target = {}\n        target['boxes'] = boxes\n        target['labels'] = labels\n        # target['masks'] = None\n        target['image_id'] = torch.tensor([index])\n        target['area'] = area\n        target['iscrowd'] = iscrowd\n\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            \n            target['boxes'] = torch.stack(tuple(map(torch.tensor, zip(*sample['bboxes'])))).permute(1, 0)\n#         image = np.transpose((2, 0, 1), image)\n\n        return image, target, image_id\n\n    def __len__(self) -> int:\n        return self.image_ids.shape[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Albumentations\nfrom albumentations import (\n    HorizontalFlip, IAAPerspective, ShiftScaleRotate, CLAHE, RandomRotate90,\n    Transpose, ShiftScaleRotate, Blur, OpticalDistortion, GridDistortion, HueSaturationValue,\n    IAAAdditiveGaussianNoise, GaussNoise, MotionBlur, MedianBlur, IAAPiecewiseAffine,\n    IAASharpen, IAAEmboss, RandomBrightnessContrast, Flip, OneOf, Compose\n)\n\ndef get_train_transform():\n    return A.Compose([\n        A.Flip(0.5),\n        A.RandomRotate90(0.5),\n        MotionBlur(p=0.2),\n        MedianBlur(blur_limit=3, p=0.1),\n        Blur(blur_limit=3, p=0.1),\n        ToTensorV2(p=1.0)\n    ], bbox_params={'format': 'pascal_voc', 'label_fields': ['labels']})\n\ndef get_valid_transform():\n    return A.Compose([\n        ToTensorV2(p=1.0)\n    ], bbox_params={'format': 'pascal_voc', 'label_fields': ['labels']})","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## <u>Create the Model</u>","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# load a model; pre-trained on COCO\nmodel = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True, min_size=512)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"num_classes = 2  # 1 class (wheat) + background\n\n# get the number of input features for the classifier\nin_features = model.roi_heads.box_predictor.cls_score.in_features\n\n# replace the pre-trained head with a new one\nmodel.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class Averager:\n    def __init__(self):\n        self.current_total = 0.0\n        self.iterations = 0.0\n\n    def send(self, value):\n        self.current_total += value\n        self.iterations += 1\n\n    @property\n    def value(self):\n        if self.iterations == 0:\n            return 0\n        else:\n            return 1.0 * self.current_total / self.iterations\n\n    def reset(self):\n        self.current_total = 0.0\n        self.iterations = 0.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def collate_fn(batch):\n    return tuple(zip(*batch))\n\ntrain_dataset = WheatDataset(train_df, DIR_TRAIN, get_train_transform())\nvalid_dataset = WheatDataset(valid_df, DIR_TRAIN, get_valid_transform())\n\n\n# split the dataset in train and test set\nindices = torch.randperm(len(train_dataset)).tolist()\n\ntrain_data_loader = DataLoader(\n    train_dataset,\n    batch_size=8,\n    shuffle=False,\n    num_workers=4,\n    collate_fn=collate_fn\n)\n\nvalid_data_loader = DataLoader(\n    valid_dataset,\n    batch_size=8,\n    shuffle=False,\n    num_workers=4,\n    collate_fn=collate_fn\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## <u>Sample</u>","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"images, targets, image_ids = next(iter(train_data_loader))\nimages = list(image.to(device) for image in images)\ntargets = [{k: v.to(device) for k, v in t.items()} for t in targets]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for i in range(5):\n    boxes = targets[i]['boxes'].cpu().numpy().astype(np.int32)\n    sample = images[i].permute(1,2,0).cpu().numpy()\n    fig, ax = plt.subplots(1, 1, figsize=(16, 8))\n\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.set_axis_off()\n    plt.imshow(sample)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## <u>Train</u>","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"model.to(device)\nparams = [p for p in model.parameters() if p.requires_grad]\noptimizer = torch.optim.SGD(params, lr=0.001, momentum=0.9, weight_decay=0.0005)\nlr_scheduler = None\n\nnum_epochs = 30","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loss_hist = Averager()\nitr = 1\n\nfor epoch in range(num_epochs):\n    start = time.time()\n    loss_hist.reset()\n    \n    for images, targets, image_ids in train_data_loader:\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\n        losses = sum(loss for loss in loss_dict.values())\n        loss_value = losses.item()\n\n        loss_hist.send(loss_value)\n\n        optimizer.zero_grad()\n        losses.backward()\n        optimizer.step()\n\n        if itr % 50 == 0:\n            print(f\"Iteration #{itr} loss: {loss_value}\")\n\n        itr += 1\n    \n    # update the learning rate\n    if lr_scheduler is not None:\n        lr_scheduler.step()\n\n    print(f\"Epoch #{epoch} loss: {loss_hist.value}\")   \n    end = time.time()\n    print(f\"Took {(end - start) / 60} minutes for epoch {epoch}\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images, targets, image_ids = next(iter(valid_data_loader))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"images = list(img.to(device) for img in images)\ntargets = [{k: v.to(device) for k, v in t.items()} for t in targets]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"boxes = targets[1]['boxes'].cpu().numpy().astype(np.int32)\nsample = images[1].permute(1,2,0).cpu().numpy()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.eval()\ncpu_device = torch.device(\"cpu\")\n\noutputs = model(images)\noutputs = [{k: v.to(cpu_device) for k, v in t.items()} for t in outputs]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(1, 1, figsize=(16, 8))\n\nfor box in boxes:\n    cv2.rectangle(sample,\n                  (box[0], box[1]),\n                  (box[2], box[3]),\n                  (220, 0, 0), 3)\n    \nax.set_axis_off()\nax.imshow(sample)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"torch.save(model.state_dict(), 'fasterrcnn_resnet50_fpn.pth')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}