{"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_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# DETR(Detection Transformer)实验平台\n你可以在这里获得：\n\n1.自定义数据集的详细说明\n\n2.完整的训练和推理流程\n\n3.实验结果可视化\n\n基于以上，你可以从以下几个角度开始你的创新：\n\n1.修改BackBone\n\n2.修改损失函数\n\n3.更换优化器\n\n4.修改位置编码的方式\n\n...\n\n![](https://cdn.analyticsvidhya.com/wp-content/uploads/2020/05/Screenshot-from-2020-05-27-17-48-38.png)\n\n特别感谢：https://www.kaggle.com/code/tanulsingh077/end-to-end-object-detection-with-transformers-detr","metadata":{}},{"cell_type":"code","source":"!git clone https://github.com/facebookresearch/detr.git   #cloning github repo of detr to import its unique loss","metadata":{"_kg_hide-output":true,"execution":{"iopub.status.busy":"2023-03-07T01:04:53.603849Z","iopub.execute_input":"2023-03-07T01:04:53.604183Z","iopub.status.idle":"2023-03-07T01:04:56.035196Z","shell.execute_reply.started":"2023-03-07T01:04:53.604129Z","shell.execute_reply":"2023-03-07T01:04:56.034053Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport numpy as np \nimport pandas as pd \nfrom datetime import datetime\nimport time\nimport random\nfrom tqdm.autonotebook import tqdm\n\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#sklearn\nfrom sklearn.model_selection import StratifiedKFold\n\n#CV\nimport cv2\n\n################# DETR FUCNTIONS FOR LOSS######################## \nimport sys\nsys.path.append('./detr/')\n\nfrom detr.models.matcher import HungarianMatcher\nfrom detr.models.detr import SetCriterion\n#################################################################\n\n#Albumenatations\nimport albumentations as A\nimport matplotlib.pyplot as plt\nfrom albumentations.pytorch.transforms import ToTensorV2\n\n#Glob\nfrom glob import glob","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","execution":{"iopub.status.busy":"2023-03-07T01:04:56.037410Z","iopub.execute_input":"2023-03-07T01:04:56.037789Z","iopub.status.idle":"2023-03-07T01:04:59.155034Z","shell.execute_reply.started":"2023-03-07T01:04:56.037735Z","shell.execute_reply":"2023-03-07T01:04:59.154132Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Utils\n\n* AverageMeter - class for averaging loss,metric,etc over epochs","metadata":{}},{"cell_type":"code","source":"class AverageMeter(object):\n    \"\"\"Computes and stores the average and current value\"\"\"\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":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.156493Z","iopub.execute_input":"2023-03-07T01:04:59.156914Z","iopub.status.idle":"2023-03-07T01:04:59.164472Z","shell.execute_reply.started":"2023-03-07T01:04:59.156866Z","shell.execute_reply":"2023-03-07T01:04:59.163547Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Configuration\n\nBasic configuration for this model","metadata":{}},{"cell_type":"code","source":"n_folds = 5\nseed = 42\nnum_classes = 2\nnum_queries = 100\nnull_class_coef = 0.5\nBATCH_SIZE = 16\nLR = 2e-5\nEPOCHS = 100","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.165841Z","iopub.execute_input":"2023-03-07T01:04:59.166447Z","iopub.status.idle":"2023-03-07T01:04:59.175913Z","shell.execute_reply.started":"2023-03-07T01:04:59.166367Z","shell.execute_reply":"2023-03-07T01:04:59.175018Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.179498Z","iopub.execute_input":"2023-03-07T01:04:59.180008Z","iopub.status.idle":"2023-03-07T01:04:59.187601Z","shell.execute_reply.started":"2023-03-07T01:04:59.179953Z","shell.execute_reply":"2023-03-07T01:04:59.186768Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"seed_everything(seed)","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.190870Z","iopub.execute_input":"2023-03-07T01:04:59.191454Z","iopub.status.idle":"2023-03-07T01:04:59.201705Z","shell.execute_reply.started":"2023-03-07T01:04:59.191231Z","shell.execute_reply":"2023-03-07T01:04:59.200903Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Preparing the Data\n\n* For preparation of data I use code from Alex's awesome kernel [here](https://www.kaggle.com/shonenkov/training-efficientdet)\n* The data can be split into any number of folds as you want , split is stratified based on number of boxes and source","metadata":{}},{"cell_type":"code","source":"import pandas as pd\n\ndef change(csvfile):\n    # 读取csv文件\n    df = pd.read_csv(csvfile)\n\n    # 将image_name列改名为image_id并删除元素的.png后缀\n    df['image_id'] = df['image_name'].apply(lambda x: x.split('.')[0])\n    df.drop(columns=['image_name'], inplace=True)\n\n\n    df['width'] = df['image_width']\n    df.drop(columns=['image_width'], inplace=True)\n    df['height'] = df['image_height']\n    df.drop(columns=['image_height'], inplace=True)\n\n    # 将bbox_x, bbox_y, bbox_width, bbox_height组合成list写入bbox列\n    df['bbox'] = df[['bbox_x', 'bbox_y', 'bbox_width', 'bbox_height']].values.tolist()\n\n    # 删除bbox_x, bbox_y, bbox_width, bbox_height这四列\n    df.drop(columns=['bbox_x', 'bbox_y', 'bbox_width', 'bbox_height'], inplace=True)\n    df['source'] = df['label_name']\n    df.drop(columns=['label_name'], inplace=True)\n\n    return df","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.203298Z","iopub.execute_input":"2023-03-07T01:04:59.203935Z","iopub.status.idle":"2023-03-07T01:04:59.214607Z","shell.execute_reply.started":"2023-03-07T01:04:59.203619Z","shell.execute_reply":"2023-03-07T01:04:59.213826Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"marking = change('/kaggle/input/new-bees/bees.csv')\n\nmarking","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.215509Z","iopub.execute_input":"2023-03-07T01:04:59.216128Z","iopub.status.idle":"2023-03-07T01:04:59.268140Z","shell.execute_reply.started":"2023-03-07T01:04:59.215866Z","shell.execute_reply":"2023-03-07T01:04:59.267361Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"bboxs = np.stack(marking['bbox'].apply(lambda x: np.array(x)))\nfor i, column in enumerate(['x', 'y', 'w', 'h']):\n    marking[column] = bboxs[:,i]\nmarking.drop(columns=['bbox'], inplace=True)","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.271073Z","iopub.execute_input":"2023-03-07T01:04:59.271375Z","iopub.status.idle":"2023-03-07T01:04:59.282439Z","shell.execute_reply.started":"2023-03-07T01:04:59.271323Z","shell.execute_reply":"2023-03-07T01:04:59.281762Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# marking = pd.read_csv('../input/global-wheat-detection/train.csv')\n\n# bboxs = np.stack(marking['bbox'].apply(lambda x: np.fromstring(x[1:-1], sep=',')))\n# for i, column in enumerate(['x', 'y', 'w', 'h']):\n#     marking[column] = bboxs[:,i]\n# marking.drop(columns=['bbox'], inplace=True)","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.285968Z","iopub.execute_input":"2023-03-07T01:04:59.286262Z","iopub.status.idle":"2023-03-07T01:04:59.292246Z","shell.execute_reply.started":"2023-03-07T01:04:59.286212Z","shell.execute_reply":"2023-03-07T01:04:59.291297Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"marking.head()","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.294914Z","iopub.execute_input":"2023-03-07T01:04:59.295173Z","iopub.status.idle":"2023-03-07T01:04:59.308373Z","shell.execute_reply.started":"2023-03-07T01:04:59.295130Z","shell.execute_reply":"2023-03-07T01:04:59.307408Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Creating Folds\nskf = StratifiedKFold(n_splits=n_folds, shuffle=True, random_state=seed)\n\ndf_folds = marking[['image_id']].copy()\ndf_folds.loc[:, 'bbox_count'] = 1\ndf_folds = df_folds.groupby('image_id').count()\ndf_folds.loc[:, 'source'] = marking[['image_id', 'source']].groupby('image_id').min()['source']\ndf_folds.head()","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.309781Z","iopub.execute_input":"2023-03-07T01:04:59.310286Z","iopub.status.idle":"2023-03-07T01:04:59.361576Z","shell.execute_reply.started":"2023-03-07T01:04:59.310097Z","shell.execute_reply":"2023-03-07T01:04:59.360557Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"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)\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","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.362805Z","iopub.execute_input":"2023-03-07T01:04:59.363256Z","iopub.status.idle":"2023-03-07T01:04:59.386441Z","shell.execute_reply.started":"2023-03-07T01:04:59.363212Z","shell.execute_reply":"2023-03-07T01:04:59.385727Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_folds.head()","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.387961Z","iopub.execute_input":"2023-03-07T01:04:59.388589Z","iopub.status.idle":"2023-03-07T01:04:59.400500Z","shell.execute_reply.started":"2023-03-07T01:04:59.388269Z","shell.execute_reply":"2023-03-07T01:04:59.399451Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Augmentations\n\n* As suggested by aleksendra in her kernel ,augentations will play a major role and hence took her up advice and use awesome augmentations , cut-mix and other will be included in future versions","metadata":{}},{"cell_type":"code","source":"def get_train_transforms():\n    return A.Compose([A.OneOf([A.HueSaturationValue(hue_shift_limit=0.2, sat_shift_limit= 0.2, val_shift_limit=0.2, p=0.9),\n                               \n                      A.RandomBrightnessContrast(brightness_limit=0.2, contrast_limit=0.2, p=0.9)],p=0.9),\n                      \n                      A.ToGray(p=0.01),\n                      \n                      A.HorizontalFlip(p=0.5),\n                      \n                      A.VerticalFlip(p=0.5),\n                      \n                      A.Resize(height=512, width=512, p=1),\n                      \n                      A.Cutout(num_holes=8, max_h_size=64, max_w_size=64, fill_value=0, p=0.5),\n                      \n                      ToTensorV2(p=1.0)],\n                      \n                      p=1.0,\n                     \n                      bbox_params=A.BboxParams(format='coco',min_area=0, min_visibility=0,label_fields=['labels'])\n                      )\n\ndef get_valid_transforms():\n    return A.Compose([A.Resize(height=512, width=512, p=1.0),\n                      ToTensorV2(p=1.0)], \n                      p=1.0, \n                      bbox_params=A.BboxParams(format='coco',min_area=0, min_visibility=0,label_fields=['labels'])\n                      )","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.402496Z","iopub.execute_input":"2023-03-07T01:04:59.402794Z","iopub.status.idle":"2023-03-07T01:04:59.412736Z","shell.execute_reply.started":"2023-03-07T01:04:59.402750Z","shell.execute_reply":"2023-03-07T01:04:59.411883Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Creating Dataset\n\n* I hope you have the video by now , DETR accepts data in coco format which is (x,y,w,h)(for those who do not know there are two formats coco and pascal(smin,ymin,xmax,ymax) which are widely used) . So now we need to prepare data in that format","metadata":{}},{"cell_type":"code","source":"DIR_TRAIN = '/kaggle/input/new-bees/bees'\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        \n    def __len__(self) -> int:\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        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        # DETR takes in data in coco format \n        boxes = records[['x', 'y', 'w', 'h']].values\n        \n        #Area of bb\n        area = boxes[:,2]*boxes[:,3]\n        area = torch.as_tensor(area, dtype=torch.float32)\n        \n        # AS pointed out by PRVI It works better if the main class is labelled as zero\n        labels =  np.zeros(len(boxes), dtype=np.int32)\n\n        \n        if self.transforms:\n            sample = {\n                'image': image,\n                'bboxes': boxes,\n                'labels': labels\n            }\n            sample = self.transforms(**sample)\n            image = sample['image']\n            boxes = sample['bboxes']\n            labels = sample['labels']\n            \n            \n        #Normalizing BBOXES\n            \n        _,h,w = image.shape\n#         print(sample['bboxes'])\n#         ss\n        boxes = A.augmentations.bbox_utils.normalize_bboxes(sample['bboxes'],rows=h,cols=w)\n        target = {}\n        target['boxes'] = torch.as_tensor(boxes,dtype=torch.float32)\n        target['labels'] = torch.as_tensor(labels,dtype=torch.long)\n        target['image_id'] = torch.tensor([index])\n        target['area'] = area\n        \n        return image, target, image_id","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.414369Z","iopub.execute_input":"2023-03-07T01:04:59.414865Z","iopub.status.idle":"2023-03-07T01:04:59.429921Z","shell.execute_reply.started":"2023-03-07T01:04:59.414690Z","shell.execute_reply":"2023-03-07T01:04:59.428961Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"A.augmentations.bbox_utils.normalize_bboxes([[5.0, 112.0, 344.0, 264.0]],rows=1000,cols=1000)","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.431348Z","iopub.execute_input":"2023-03-07T01:04:59.432045Z","iopub.status.idle":"2023-03-07T01:04:59.445677Z","shell.execute_reply.started":"2023-03-07T01:04:59.431832Z","shell.execute_reply":"2023-03-07T01:04:59.444245Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model\n\n* Initial DETR model is trained on coco dataset , which has 91 classes + 1 background class , hence we need to modify it to take our own number of classes\n* Also DETR model takes in 100 queries ie ,it outputs total of 100 bboxes for every image , we can very well change that too","metadata":{}},{"cell_type":"code","source":"from torchvision.models import resnet50\nclass DETRdemo(nn.Module):\n    \"\"\"\n    Demo DETR implementation.\n\n    Demo implementation of DETR in minimal number of lines, with the\n    following differences wrt DETR in the paper:\n    * learned positional encoding (instead of sine)\n    * positional encoding is passed at input (instead of attention)\n    * fc bbox predictor (instead of MLP)\n    The model achieves ~40 AP on COCO val5k and runs at ~28 FPS on Tesla V100.\n    Only batch size 1 supported.\n    \"\"\"\n    def __init__(self, num_classes, hidden_dim=256, nheads=8,\n                 num_encoder_layers=6, num_decoder_layers=6):\n        super().__init__()\n\n        # create ResNet-50 backbone\n        self.backbone = resnet50()\n        del self.backbone.fc\n\n        # create conversion layer\n        self.conv = nn.Conv2d(2048, hidden_dim, 1)\n\n        # create a default PyTorch transformer\n        self.transformer = nn.Transformer(\n            hidden_dim, nheads, num_encoder_layers, num_decoder_layers)\n\n        # prediction heads, one extra class for predicting non-empty slots\n        # note that in baseline DETR linear_bbox layer is 3-layer MLP\n        self.linear_class = nn.Linear(hidden_dim, num_classes)\n        self.linear_bbox = nn.Linear(hidden_dim, 4)\n\n        # output positional encodings (object queries)\n        self.query_pos = nn.Parameter(torch.rand(100, hidden_dim))\n\n        # spatial positional encodings\n        # note that in baseline DETR we use sine positional encodings\n        self.row_embed = nn.Parameter(torch.rand(50, hidden_dim // 2))\n        self.col_embed = nn.Parameter(torch.rand(50, hidden_dim // 2))\n\n    def forward(self, inputs):\n        # propagate inputs through ResNet-50 up to avg-pool layer\n        x = self.backbone.conv1(inputs)\n        x = self.backbone.bn1(x)\n        x = self.backbone.relu(x)\n        x = self.backbone.maxpool(x)\n\n        x = self.backbone.layer1(x)\n        x = self.backbone.layer2(x)\n        x = self.backbone.layer3(x)\n        x = self.backbone.layer4(x)\n        \n        # convert from 2048 to 256 feature planes for the transformer\n        h = self.conv(x)\n        \n        \n        # construct positional encodings\n        H, W = h.shape[-2:]\n        pos = torch.cat([\n            self.col_embed[:W].unsqueeze(0).repeat(H, 1, 1),\n            self.row_embed[:H].unsqueeze(1).repeat(1, W, 1),\n        ], dim=-1).flatten(0, 1).unsqueeze(1)\n        \n        # propagate through the transformer\n        h = self.transformer(pos + 0.1 * h.flatten(2).permute(2, 0, 1),\n                             self.query_pos.unsqueeze(1).repeat(1, inputs.size(0), 1)).transpose(0, 1)\n#         print(h.shape)\n        # finally project transformer outputs to class labels and bounding boxes\n        return {'pred_logits': self.linear_class(h), \n                'pred_boxes': self.linear_bbox(h).sigmoid()}","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.447527Z","iopub.execute_input":"2023-03-07T01:04:59.448063Z","iopub.status.idle":"2023-03-07T01:04:59.464326Z","shell.execute_reply.started":"2023-03-07T01:04:59.447885Z","shell.execute_reply":"2023-03-07T01:04:59.463444Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# correct\nnum_classes = 5\nmodel = DETRdemo(num_classes).cuda()\nout = model(torch.randn(3,3,200,200).cuda())\nout['pred_logits'].shape,out['pred_boxes'].shape","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:04:59.466156Z","iopub.execute_input":"2023-03-07T01:04:59.467020Z","iopub.status.idle":"2023-03-07T01:05:05.235002Z","shell.execute_reply.started":"2023-03-07T01:04:59.466591Z","shell.execute_reply":"2023-03-07T01:05:05.233998Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Matcher and Bipartite Matching Loss\n\nNow we make use of the unique loss that the model uses and for that we need to define the matcher. DETR calcuates three individual losses :\n* Classification Loss for labels(its weight can be set by loss_ce)\n* Bbox Loss (its weight can be set by loss_bbox)\n* Loss for Background class","metadata":{}},{"cell_type":"code","source":"'''\ncode taken from github repo detr , 'code present in engine.py'\n'''\n\nmatcher = HungarianMatcher()\n\nweight_dict = weight_dict = {'loss_ce': 1, 'loss_bbox': 1 , 'loss_giou': 1}\n\nlosses = ['labels', 'boxes', 'cardinality']","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:05:05.236517Z","iopub.execute_input":"2023-03-07T01:05:05.236950Z","iopub.status.idle":"2023-03-07T01:05:05.244471Z","shell.execute_reply.started":"2023-03-07T01:05:05.236891Z","shell.execute_reply":"2023-03-07T01:05:05.243484Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Training Function\n\nTraining of DETR is unique and different from FasteRRcnn  and EfficientDET , as we train the criterion as well , the training function can be viewed here : https://github.com/facebookresearch/detr/blob/master/engine.py","metadata":{}},{"cell_type":"code","source":"def train_fn(data_loader,model,criterion,optimizer,device,scheduler,epoch):\n    model.train()\n    criterion.train()\n    \n    summary_loss = AverageMeter()\n    \n    tk0 = tqdm(data_loader, total=len(data_loader))\n    \n    for step, (images, targets, image_ids) in enumerate(tk0):\n        \n        \n        images = list(image.unsqueeze(0).to(device) for image in images)\n        images = torch.cat(images, 0)\n#         print(torch.cat(images, 0).shape)\n        targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n        \n\n        output = model(images)\n        \n        loss_dict = criterion(output, targets)\n        weight_dict = criterion.weight_dict\n        \n        losses = sum(loss_dict[k] * weight_dict[k] for k in loss_dict.keys() if k in weight_dict)\n        \n        optimizer.zero_grad()\n\n        losses.backward()\n        optimizer.step()\n        if scheduler is not None:\n            scheduler.step()\n        \n        summary_loss.update(losses.item(),BATCH_SIZE)\n        tk0.set_postfix(loss=summary_loss.avg)\n        \n    return summary_loss","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:05:05.245983Z","iopub.execute_input":"2023-03-07T01:05:05.246680Z","iopub.status.idle":"2023-03-07T01:05:05.265403Z","shell.execute_reply.started":"2023-03-07T01:05:05.246517Z","shell.execute_reply":"2023-03-07T01:05:05.264309Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Eval Function","metadata":{}},{"cell_type":"code","source":"def eval_fn(data_loader, model,criterion, device):\n    model.eval()\n    criterion.eval()\n    summary_loss = AverageMeter()\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            images = list(image.unsqueeze(0).to(device) for image in images)\n            images = torch.cat(images, 0)\n            targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\n            output = model(images)\n        \n            loss_dict = criterion(output, targets)\n            weight_dict = criterion.weight_dict\n        \n            losses = sum(loss_dict[k] * weight_dict[k] for k in loss_dict.keys() if k in weight_dict)\n            \n            summary_loss.update(losses.item(),BATCH_SIZE)\n            tk0.set_postfix(loss=summary_loss.avg)\n    \n    return summary_loss","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:05:05.267190Z","iopub.execute_input":"2023-03-07T01:05:05.268032Z","iopub.status.idle":"2023-03-07T01:05:05.280673Z","shell.execute_reply.started":"2023-03-07T01:05:05.267669Z","shell.execute_reply":"2023-03-07T01:05:05.279659Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Engine","metadata":{}},{"cell_type":"code","source":"def collate_fn(batch):\n    return tuple(zip(*batch))","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:05:05.282101Z","iopub.execute_input":"2023-03-07T01:05:05.283907Z","iopub.status.idle":"2023-03-07T01:05:05.295476Z","shell.execute_reply.started":"2023-03-07T01:05:05.283603Z","shell.execute_reply":"2023-03-07T01:05:05.294367Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def run(fold):\n    \n    df_train = df_folds[df_folds['fold'] != fold]\n    df_valid = df_folds[df_folds['fold'] == fold]\n    \n    train_dataset = WheatDataset(\n    image_ids=df_train.index.values,\n    dataframe=marking,\n    transforms=get_train_transforms()\n    )\n\n    valid_dataset = WheatDataset(\n    image_ids=df_valid.index.values,\n    dataframe=marking,\n    transforms=get_valid_transforms()\n    )\n    \n    train_data_loader = DataLoader(\n    train_dataset,\n    batch_size=BATCH_SIZE,\n    shuffle=False,\n    num_workers=4,\n    collate_fn=collate_fn\n    )\n\n    valid_data_loader = DataLoader(\n    valid_dataset,\n    batch_size=BATCH_SIZE,\n    shuffle=False,\n    num_workers=4,\n    collate_fn=collate_fn\n    )\n    \n    device = torch.device('cuda')\n    model = DETRdemo(num_classes)\n    model = model.to(device)\n    criterion = SetCriterion(num_classes-1, matcher, weight_dict, eos_coef = null_class_coef, losses=losses)\n    criterion = criterion.to(device)\n    \n\n    optimizer = torch.optim.AdamW(model.parameters(), lr=LR)\n    \n    best_loss = 10**5\n    for epoch in range(EPOCHS):\n        train_loss = train_fn(train_data_loader, model,criterion, optimizer,device,scheduler=None,epoch=epoch)\n        valid_loss = eval_fn(valid_data_loader, model,criterion, device)\n        \n        print('|EPOCH {}| TRAIN_LOSS {}| VALID_LOSS {}|'.format(epoch+1,train_loss.avg,valid_loss.avg))\n        \n        if valid_loss.avg < best_loss:\n            best_loss = valid_loss.avg\n            print('Best model found for Fold {} in Epoch {}........Saving Model'.format(fold,epoch+1))\n            torch.save(model.state_dict(), f'detr_best_{fold}.pth')","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:05:05.297305Z","iopub.execute_input":"2023-03-07T01:05:05.297904Z","iopub.status.idle":"2023-03-07T01:05:05.313026Z","shell.execute_reply.started":"2023-03-07T01:05:05.297723Z","shell.execute_reply":"2023-03-07T01:05:05.311908Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"run(fold=0)","metadata":{"execution":{"iopub.status.busy":"2023-03-07T01:05:05.314765Z","iopub.execute_input":"2023-03-07T01:05:05.315292Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Sample\n\n* I know we might be naive to visualize the model ouput just after one epoch but lets do that and see what are the results like","metadata":{}},{"cell_type":"code","source":"def view_sample(df_valid,model,device):\n    '''\n    Code taken from Peter's Kernel \n    https://www.kaggle.com/pestipeti/pytorch-starter-fasterrcnn-train\n    '''\n    valid_dataset = WheatDataset(image_ids=df_valid.index.values,\n                                 dataframe=marking,\n                                 transforms=get_valid_transforms()\n                                )\n     \n    valid_data_loader = DataLoader(\n                                    valid_dataset,\n                                    batch_size=BATCH_SIZE,\n                                    shuffle=False,\n                                   num_workers=4,\n                                   collate_fn=collate_fn)\n    \n    images, targets, image_ids = next(iter(valid_data_loader))\n    _,h,w = images[0].shape # for de normalizing images\n    \n#     images = list(img.to(device) for img in images)\n    images = list(image.unsqueeze(0).to(device) for image in images)\n    images = torch.cat(images, 0)\n    targets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n    \n    boxes = targets[0]['boxes'].cpu().numpy()\n    boxes = [np.array(box).astype(np.int32) for box in A.augmentations.bbox_utils.denormalize_bboxes(boxes,h,w)]\n    sample = images[0].permute(1,2,0).cpu().numpy()\n    \n    model.eval()\n    model.to(device)\n    cpu_device = torch.device(\"cpu\")\n    \n    with torch.no_grad():\n        outputs = model(images)\n        \n    outputs = [{k: v.to(cpu_device) for k, v in outputs.items()}]\n    \n    fig, ax = plt.subplots(1, 1, figsize=(16, 8))\n    \n    # 红色真实框\n    for box in boxes:\n        cv2.rectangle(sample,\n                  (int(box[0]), int(box[1])),\n                  (int(box[2])+int(box[0]), int(box[3])+int(box[1])),\n                  (220, 0, 0), 2)\n        \n\n    oboxes = outputs[0]['pred_boxes'][0].detach().cpu().numpy()\n    oboxes = [np.array(box).astype(np.int32) for box in A.augmentations.bbox_utils.denormalize_bboxes(oboxes,h,w)]\n    prob   = outputs[0]['pred_logits'][0].softmax(1).detach().cpu().numpy()[:,0]\n    \n    # 蓝色预测框\n    for box,p in zip(oboxes,prob):\n        \n        if p >0:\n            color = (0,0,220) #if p>0.5 else (0,0,0)\n            cv2.rectangle(sample,\n                  (int(box[0]), int(box[1])),\n                  (int(box[2]+box[0]), int(box[3]+box[1])),\n                  color, 2)\n    \n    ax.set_axis_off()\n    ax.imshow(sample)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = DETRdemo(num_classes=num_classes)\nmodel.load_state_dict(torch.load(\"./detr_best_0.pth\"))\nview_sample(df_folds[df_folds['fold'] == 3],model=model,device=torch.device('cuda'))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"view_sample(df_folds[df_folds['fold'] == 2],model=model,device=torch.device('cuda'))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 自定义数据集\n\nhttps://www.makesense.ai/\n![image.png](attachment:2cbcb187-9370-409f-96b3-d109b523037e.png)\n导出的CSV文件经过下面的change函数返回格式一致的df（对应上面的marking）","metadata":{},"attachments":{"2cbcb187-9370-409f-96b3-d109b523037e.png":{"image/png":"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"}}},{"cell_type":"code","source":"import pandas as pd\n\ndef change(csvfile):\n    # 读取csv文件\n    df = pd.read_csv('1.csv')\n\n    # 将image_name列改名为image_id并删除元素的.png后缀\n    df['image_id'] = df['image_name'].apply(lambda x: x.split('.')[0])\n    df.drop(columns=['image_name'], inplace=True)\n\n\n    df['width'] = df['image_width']\n    df.drop(columns=['image_width'], inplace=True)\n    df['height'] = df['image_height']\n    df.drop(columns=['image_height'], inplace=True)\n\n    # 将bbox_x, bbox_y, bbox_width, bbox_height组合成list写入bbox列\n    df['bbox'] = df[['bbox_x', 'bbox_y', 'bbox_width', 'bbox_height']].values.tolist()\n\n    # 删除bbox_x, bbox_y, bbox_width, bbox_height这四列\n    df.drop(columns=['bbox_x', 'bbox_y', 'bbox_width', 'bbox_height'], inplace=True)\n    df['source'] = df['label_name']\n    df.drop(columns=['label_name'], inplace=True)\n\n    return df\n\n# change('1.csv').head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 绘制矩形框","metadata":{}},{"cell_type":"code","source":"import cv2\nimport matplotlib.pyplot as plt\n\ndef show(img_path, rectangle_lists=[[30, 20, 393, 359]]): # x,y,w,h  支持同时绘制多个\n    # 读取图片\n    img = cv2.imread(img_path)\n\n    # 获取图片的尺寸\n    height, width, _ = img.shape\n    \n    for rectangle in rectangle_lists:\n        # 计算矩形的大小\n        rect_width = int(rectangle[2])  # 横向\n        rect_height = int(rectangle[3])\n\n        # 计算矩形的左上角坐标\n        x = int(rectangle[0])\n        y = int(rectangle[1])\n\n        # 在图片中心绘制矩形\n        cv2.rectangle(img, (x, y), (x + int(rect_width), y + int(rect_height)), (0, 0, 255), 2)\n#         cv2.rectangle(img, (32, 115), (507, 462), (0, 0, 255), 2)\n\n        # 在矩形框左上角添加文字\n#         text = 'wheat'\n#         cv2.putText(img, text, (x, y-10), cv2.FONT_HERSHEY_PLAIN, 2, (0, 0, 255), 1)\n\n    # 用matplotlib显示图片\n    plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))\n    plt.show()\n\nshow('/kaggle/input/new-bees/bees/bee0.jpg',[[210,133,254,364]])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}