{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install --no-deps '../input/timm-package/timm-0.1.26-py3-none-any.whl'\n!pip install --no-deps '../input/pycocotools/pycocotools-2.0-cp37-cp37m-linux_x86_64.whl'\n# !pip install effdet","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import sys\nsys.path.insert(0, \"../input/timm-efficientdet-pytorch\")\nsys.path.insert(0, \"../input/omegaconf\")\n\nimport json\nimport numpy as np\nimport pandas as pd\nimport cv2\nimport os\nimport re\nfrom datetime import datetime\nimport time\nimport random\n\nfrom PIL import Image\nfrom tqdm import tqdm\nfrom glob import glob\nimport albumentations as A\nfrom albumentations.pytorch.transforms import ToTensorV2\n\nimport torch\nimport torchvision\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 Dataset,DataLoader\nfrom torch.utils.data.sampler import SequentialSampler, RandomSampler\nfrom sklearn.model_selection import StratifiedKFold\n\n\nfrom matplotlib import pyplot as plt\nimport warnings\nwarnings.filterwarnings(\"ignore\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.DataFrame(columns = ['id','x1','y1','x2','y2','classname'])\nidx = 0\nfor dirname, _, filenames in os.walk('../input/face-mask-detection-dataset/Medical mask/Medical mask/Medical Mask/annotations'):\n    for filename in filenames:\n        d = json.load(open(os.path.join(dirname, filename)))\n        id = d['FileName']\n        for l in d['Annotations']:\n            df.loc[idx , :] = [id] + l['BoundingBox'] + [l['classname']]\n            idx += 1\nclass_map = dict(zip(df['classname'].unique(),list(range(1,21))))\nprint(df['classname'].unique())\npd.DataFrame(df['classname'].unique(),columns = ['classname']).to_csv('classname.csv',index=False)\ndf['class'] = df['classname'].apply(lambda x : class_map[x])\n# df['id'] = df['id'].astype(np.str)\ndf[['x1','y1','x2','y2']] = df[['x1','y1','x2','y2']].astype(np.float)\ndf = df.drop(index = df[df['x1']==df['x2']].index)\ndf.to_csv('train.csv',index=False)\n# df = pd.read_csv('../input/facemask/train.csv')\ndf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# df = pd.read_csv('../input/facemask/FaceMask.csv')\n# df = df.rename(columns = {'classname':'class'})\n# df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"skf = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)\n\ndf_folds = df[['id']].copy()\ndf_folds.loc[:, 'bbox_count'] = 0\ndf_folds = df_folds.groupby('id').count()\ndf_folds.loc[:, 'fold'] = 0\n\nfor fold_number, (train_index, val_index) in enumerate(skf.split(X=df_folds.index, y=df_folds.bbox_count)):\n    df_folds.loc[df_folds.iloc[val_index].index, 'fold'] = fold_number\n    \n# df_folds.to_csv('train_folds.csv',index=False)\n# df_folds = pd.read_csv('../input/facemask/train_folds.csv')\ndf_folds","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_train_transforms():\n    return A.Compose(\n        [\n#             A.RandomSizedCrop(min_max_height=(256, 256), height=1024, width=1024, p=0.5),\n            \n            A.OneOf([\n                A.HueSaturationValue(hue_shift_limit=0.2, sat_shift_limit= 0.2, \n                                     val_shift_limit=0.2, p=0.9),\n                A.RandomBrightnessContrast(brightness_limit=0.2, \n                                           contrast_limit=0.2, p=0.9),\n            ],p=0.9),\n            A.ToGray(p=0.01),\n            A.HorizontalFlip(p=0.5),\n            A.VerticalFlip(p=0.01),\n            A.Resize(height=512, width=512, p=1),\n            A.RandomSizedBBoxSafeCrop(512, 512, erosion_rate=0.0, interpolation=1, p=1.0),\n            A.Cutout(num_holes=20, max_h_size=32, max_w_size=32, fill_value=0, p=0.5),\n            A.Blur(blur_limit=5, p=0.5),\n            A.ShiftScaleRotate(shift_limit=0.0625,scale_limit=0.1, rotate_limit=20 ,p=0.5),\n            ToTensorV2(p=1.0),\n        ], \n        p=1.0, \n        bbox_params=A.BboxParams(\n            format='pascal_voc',\n            min_area=0, \n            min_visibility=0,\n            label_fields=['labels']\n        )\n    )\n\ndef get_valid_transforms():\n    return A.Compose(\n        [\n            A.Resize(height=512, width=512, p=1.0),\n            ToTensorV2(p=1.0),\n        ], \n        p=1.0, \n        bbox_params=A.BboxParams(\n            format='pascal_voc',\n            min_area=0, \n            min_visibility=0,\n            label_fields=['labels']\n        )\n    )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"TRAIN_ROOT_PATH = '../input/face-mask-detection-dataset/Medical mask/Medical mask/Medical Mask/images'\n\nclass DatasetRetriever(Dataset):\n\n    def __init__(self, marking, image_ids, transforms=None, test=False):\n        super().__init__()\n\n        self.image_ids = image_ids\n        self.marking = marking\n        self.transforms = transforms\n        self.test = test\n\n    def __getitem__(self, index: int):\n        image_id = self.image_ids[index]\n        image, boxes, labels = self.load_image_and_boxes(index)\n        \n#         if self.test or random.random() > 0.5:\n#             image, boxes = self.load_image_and_boxes(index)\n#         else:\n#             image, boxes = self.load_cutmix_image_and_boxes(index)\n        \n        target = {}\n        target['boxes'] = boxes\n        target['labels'] = labels\n\n        if self.transforms:\n            for i in range(10):\n                sample = self.transforms(**{\n                    'image': image,\n                    'bboxes': target['boxes'],\n                    'labels': target['labels']\n                })\n                if len(sample['bboxes']) > 0:\n                    image = sample['image']\n                    target['boxes'] = torch.stack(tuple(map(torch.tensor, zip(*sample['bboxes'])))).permute(1, 0)\n                    target['boxes'][:,[0,1,2,3]] = target['boxes'][:,[1,0,3,2]]  #yxyx: be warning\n                    target['labels'] = torch.tensor(sample['labels'])\n                    break\n\n        return image, target, image_id\n\n    def __len__(self) -> int:\n        return self.image_ids.shape[0]\n\n    def load_image_and_boxes(self, index):\n        image_id = self.image_ids[index]\n        image = cv2.imread(f'{TRAIN_ROOT_PATH}/{image_id}', cv2.IMREAD_COLOR)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB).astype(np.float32)\n        image /= 255.0\n        records = self.marking[self.marking['id'] == image_id]\n        boxes = records[['x1', 'y1', 'x2', 'y2']].values\n        return image, boxes , records['class']\n\n#     def load_cutmix_image_and_boxes(self, index, imsize=1024):\n#         \"\"\" \n#         This implementation of cutmix author:  https://www.kaggle.com/nvnnghia \n#         Refactoring and adaptation: https://www.kaggle.com/shonenkov\n#         \"\"\"\n#         w, h = imsize, imsize\n#         s = imsize // 2\n    \n#         xc, yc = [int(random.uniform(imsize * 0.25, imsize * 0.75)) for _ in range(2)]  # center x, y\n#         indexes = [index] + [random.randint(0, self.image_ids.shape[0] - 1) for _ in range(3)]\n\n#         result_image = np.full((imsize, imsize, 3), 1, dtype=np.float32)\n#         result_boxes = []\n\n#         for i, index in enumerate(indexes):\n#             image, boxes = self.load_image_and_boxes(index)\n#             if i == 0:\n#                 x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc  # xmin, ymin, xmax, ymax (large image)\n#                 x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h  # xmin, ymin, xmax, ymax (small image)\n#             elif i == 1:  # top right\n#                 x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc\n#                 x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h\n#             elif i == 2:  # bottom left\n#                 x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)\n#                 x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, max(xc, w), min(y2a - y1a, h)\n#             elif i == 3:  # bottom right\n#                 x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)\n#                 x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)\n#             result_image[y1a:y2a, x1a:x2a] = image[y1b:y2b, x1b:x2b]\n#             padw = x1a - x1b\n#             padh = y1a - y1b\n\n#             boxes[:, 0] += padw\n#             boxes[:, 1] += padh\n#             boxes[:, 2] += padw\n#             boxes[:, 3] += padh\n\n#             result_boxes.append(boxes)\n\n#         result_boxes = np.concatenate(result_boxes, 0)\n#         np.clip(result_boxes[:, 0:], 0, 2 * s, out=result_boxes[:, 0:])\n#         result_boxes = result_boxes.astype(np.int32)\n#         result_boxes = result_boxes[np.where((result_boxes[:,2]-result_boxes[:,0])*(result_boxes[:,3]-result_boxes[:,1]) > 0)]\n#         return result_image, result_boxes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fold_number = 0\n\ntrain_dataset = DatasetRetriever(\n    image_ids=df_folds[df_folds['fold'] != fold_number].index.values,\n    marking=df,\n    transforms=get_train_transforms(),\n    test=False,\n)\n\nvalidation_dataset = DatasetRetriever(\n    image_ids=df_folds[df_folds['fold'] == fold_number].index.values,\n    marking=df,\n    transforms=get_valid_transforms(),\n    test=True,\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig=plt.figure(figsize=(30, 30))\ncolumns = 4\nrows = 3\n\nc_map = dict(zip(list(range(1,21)),pd.read_csv('../input/facemask/classname.csv')['classname'].unique()))\n\nfor i in range(1, columns*rows +1):\n    image, target, image_id = train_dataset[i]\n    boxes = target['boxes'].cpu().numpy().astype(np.int32)\n    classnames = target['labels'].cpu().numpy()\n    numpy_image = image.permute(1,2,0).cpu().numpy()\n    for j, box in enumerate(boxes):\n        cv2.rectangle(numpy_image, (box[1], box[0]), (box[3],  box[2]), (0, 255, 0), 3)\n#         cv2.putText(numpy_image , c_map[classnames[j]] , (int(box[0]),int(box[1])), cv2.FONT_HERSHEY_SIMPLEX, 1, (0,255,0), 2)\n    fig.add_subplot(rows, columns, i)\n    plt.imshow(numpy_image)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class AverageMeter(object):\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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class TrainGlobalConfig:\n    num_workers = 8\n    batch_size = 4\n    n_epochs = 20\n    lr = 0.001\n\n    folder = 'effdet'\n    verbose = True\n    verbose_step = 1\n    step_scheduler = False  # do scheduler.step after optimizer.step\n    validation_scheduler = True  # do scheduler.step after validation stage loss\n    \n    SchedulerClass = torch.optim.lr_scheduler.ReduceLROnPlateau\n    scheduler_params = dict(\n        mode='min',\n        factor=0.25,\n        patience=2,\n        verbose=False, \n        threshold=0.0001,\n        threshold_mode='abs',\n        cooldown=0, \n        min_lr=1e-8,\n        eps=1e-08\n    )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class Fitter:\n    \n    def __init__(self, model, device, config):\n        self.config = config\n        self.epoch = 0\n\n        self.base_dir = f'./{config.folder}'\n        if not os.path.exists(self.base_dir):\n            os.makedirs(self.base_dir)\n        \n        self.log_path = f'{self.base_dir}/log.txt'\n        self.best_summary_loss = 10**5\n\n        self.model = model\n        self.device = device\n\n        param_optimizer = list(self.model.named_parameters())\n        no_decay = ['bias', 'LayerNorm.bias', 'LayerNorm.weight']\n        optimizer_grouped_parameters = [\n            {'params': [p for n, p in param_optimizer if not any(nd in n for nd in no_decay)], 'weight_decay': 0.001},\n            {'params': [p for n, p in param_optimizer if any(nd in n for nd in no_decay)], 'weight_decay': 0.0}\n        ] \n\n        self.optimizer = torch.optim.AdamW(self.model.parameters(), lr=config.lr)\n        self.scheduler = config.SchedulerClass(self.optimizer, **config.scheduler_params)\n        self.log(f'Fitter prepared. Device is {self.device}')\n        \n#         self.load('../input/face-mask-efficientdet/effdet/last-checkpoint.bin')\n\n    def fit(self, train_loader, validation_loader):\n        for e in range(self.config.n_epochs):\n            if self.config.verbose:\n                lr = self.optimizer.param_groups[0]['lr']\n                timestamp = datetime.utcnow().isoformat()\n                self.log(f'LR: {lr}')\n\n            t = time.time()\n            summary_loss = self.train_one_epoch(train_loader)\n\n            self.log(f'[RESULT]: Train. Epoch: {self.epoch}, summary_loss: {summary_loss.avg:.5f}, time: {(time.time() - t):.5f}')\n            self.save(f'{self.base_dir}/last-checkpoint.bin')\n\n            t = time.time()\n            summary_loss = self.validation(validation_loader)\n\n            self.log(f'[RESULT]: Val. Epoch: {self.epoch}, summary_loss: {summary_loss.avg:.5f}, time: {(time.time() - t):.5f}')\n            if summary_loss.avg < self.best_summary_loss:\n                self.best_summary_loss = summary_loss.avg\n                self.model.eval()\n                self.save(f'{self.base_dir}/best-checkpoint-{str(self.epoch).zfill(3)}epoch.bin')\n                for path in sorted(glob(f'{self.base_dir}/best-checkpoint-*epoch.bin'))[:-3]:\n                    os.remove(path)\n\n            if self.config.validation_scheduler:\n                self.scheduler.step(metrics=summary_loss.avg)\n\n            self.epoch += 1\n\n    def validation(self, val_loader):\n        self.model.eval()\n        summary_loss = AverageMeter()\n        \n        tk0 =  tqdm(enumerate(val_loader),total = len(validation_dataset)/TrainGlobalConfig.batch_size)\n        for step, (images, targets, image_ids) in tk0:\n            if self.config.verbose:\n                if step % self.config.verbose_step == 0:\n                    tk0.set_postfix( loss = summary_loss.avg)\n                    \n            with torch.no_grad():\n                images = torch.stack(images)\n                batch_size = images.shape[0]\n                images = images.to(self.device).float()\n                boxes = [target['boxes'].to(self.device).float() for target in targets]\n                labels = [target['labels'].to(self.device).float() for target in targets]\n\n                loss, _, _ = self.model(images, boxes, labels)\n                summary_loss.update(loss.detach().item(), batch_size)\n\n        return summary_loss\n\n    def train_one_epoch(self, train_loader):\n        self.model.train()\n        summary_loss = AverageMeter()\n        \n        tk0 =  tqdm(enumerate(train_loader),total = int(len(train_dataset)/TrainGlobalConfig.batch_size))\n        for step, (images, targets, image_ids) in tk0:\n            if self.config.verbose:\n                if step % self.config.verbose_step == 0:\n                    tk0.set_postfix( loss = summary_loss.avg)\n            \n            images = torch.stack(images)\n            images = images.to(self.device).float()\n            batch_size = images.shape[0]\n            boxes = [target['boxes'].to(self.device).float() for target in targets]\n            labels = [target['labels'].to(self.device).float() for target in targets]\n\n            self.optimizer.zero_grad()\n            \n            loss, _, _ = self.model(images, boxes, labels)\n            \n            loss.backward()\n\n            summary_loss.update(loss.detach().item(), batch_size)\n\n            self.optimizer.step()\n\n            if self.config.step_scheduler:\n                self.scheduler.step()\n\n        return summary_loss\n    \n    def save(self, path):\n        self.model.eval()\n        torch.save({\n            'model_state_dict': self.model.model.state_dict(),\n            'optimizer_state_dict': self.optimizer.state_dict(),\n            'scheduler_state_dict': self.scheduler.state_dict(),\n            'best_summary_loss': self.best_summary_loss,\n            'epoch': self.epoch,\n        }, path)\n\n    def load(self, path):\n        checkpoint = torch.load(path)\n        self.model.model.load_state_dict(checkpoint['model_state_dict'])\n        self.optimizer.load_state_dict(checkpoint['optimizer_state_dict'])\n        self.scheduler.load_state_dict(checkpoint['scheduler_state_dict'])\n        self.best_summary_loss = checkpoint['best_summary_loss']\n        self.epoch = checkpoint['epoch'] + 1\n        \n    def log(self, message):\n        if self.config.verbose:\n            print(message)\n        with open(self.log_path, 'a+') as logger:\n            logger.write(f'{message}\\n')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def collate_fn(batch):\n    return tuple(zip(*batch))\n\ndef run_training():\n    device = torch.device('cuda:0')\n    net.to(device)\n\n    train_loader = torch.utils.data.DataLoader(\n        train_dataset,\n        batch_size=TrainGlobalConfig.batch_size,\n#         sampler=RandomSampler(train_dataset),\n        shuffle=True,\n        pin_memory=False,\n        drop_last=True,\n        num_workers=TrainGlobalConfig.num_workers,\n        collate_fn=collate_fn,\n    )\n    val_loader = torch.utils.data.DataLoader(\n        validation_dataset, \n        batch_size=TrainGlobalConfig.batch_size,\n        num_workers=TrainGlobalConfig.num_workers,\n        shuffle=False,\n#         sampler=SequentialSampler(validation_dataset),\n        pin_memory=False,\n        collate_fn=collate_fn,\n    )\n\n    fitter = Fitter(model=net, device=device, config=TrainGlobalConfig)\n    fitter.fit(train_loader, val_loader)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from effdet import get_efficientdet_config, EfficientDet, DetBenchTrain\nfrom effdet.efficientdet import HeadNet\n\ndef get_net():\n    config = get_efficientdet_config('tf_efficientdet_d5')\n    net = EfficientDet(config, pretrained_backbone=True)\n#     checkpoint = torch.load('../input/efficientdet/efficientdet_d5-ef44aea8.pth')\n#     net.load_state_dict(checkpoint)\n    config.num_classes = 20\n    config.image_size = 512\n    net.class_net = HeadNet(config, num_outputs=config.num_classes, norm_kwargs=dict(eps=.001, momentum=.01))\n    return DetBenchTrain(net, config)\n\nnet = get_net()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"run_training()","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}