{"cells":[{"metadata":{},"cell_type":"markdown","source":"I tried Object Detection using [@sandorkonya](https://www.kaggle.com/sandorkonya)'s [wonderful Dataset](https://www.kaggle.com/sandorkonya/23k-tracheostomy-tube-annotated-on-chest-xray).  \n\nAnd this kernel is based on [@shonenkov](https://www.kaggle.com/shonenkov)'s [notebook](https://www.kaggle.com/shonenkov/training-efficientdet)."},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true,"_kg_hide-input":true,"_kg_hide-output":true},"cell_type":"code","source":"!pip install --no-deps '../input/timm-package/timm-0.1.26-py3-none-any.whl' > /dev/null\n!pip install --no-deps '../input/pycocotools/pycocotools-2.0-cp37-cp37m-linux_x86_64.whl' > /dev/null","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true,"_kg_hide-output":true},"cell_type":"code","source":"import sys\nsys.path.insert(0, \"../input/timm-efficientdet-pytorch\")\nsys.path.insert(0, \"../input/omegaconf\")\nsys.path.insert(0, \"../input/weightedboxesfusion\")\nimport torch\nimport os\nfrom datetime import datetime\nimport time\nimport random\nimport cv2\nimport pandas as pd\nimport numpy as np\nimport albumentations as A\nimport matplotlib.pyplot as plt\nfrom albumentations.pytorch.transforms import ToTensorV2\nfrom sklearn.model_selection import GroupKFold\nfrom torch.utils.data import Dataset,DataLoader\nfrom torch.utils.data.sampler import SequentialSampler, RandomSampler\nfrom ensemble_boxes import *\nimport gc\nfrom effdet import get_efficientdet_config, EfficientDet, DetBenchEval\nfrom glob import glob\n\nSEED = 42\n\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\n\nseed_everything(SEED)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.read_json('../input/23k-tracheostomy-tube-annotated-on-chest-xray/tracheostomy_tube.json').T.reset_index(drop=True)\ndf['x'] = df.regions.apply(lambda x : x[0]['shape_attributes']['x'])\ndf['y'] = df.regions.apply(lambda x : x[0]['shape_attributes']['y'])\ndf['w'] = df.regions.apply(lambda x : x[0]['shape_attributes']['width'])\ndf['h'] = df.regions.apply(lambda x : x[0]['shape_attributes']['height'])\ndf = df.loc[:,['filename','x','y','w','h']]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df2 = pd.read_csv('../input/ranzcr-clip-catheter-line-classification/train.csv')\ndf2 = df2.rename(columns={'StudyInstanceUID': 'filename'})\ndf2.filename = df2.filename.apply(lambda x : f'{x}.jpg')\ndf2 = df2.loc[:,['filename','PatientID']]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.merge(df, df2, on='filename')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Fold = GroupKFold(n_splits=5)\nfor n, (train_index, val_index) in enumerate(Fold.split(df, groups=df['PatientID'].values)):\n    df.loc[val_index, 'fold'] = n\ndf['fold'] = df['fold'].astype(int)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Albumentations"},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_train_transforms():\n    return A.Compose(\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.Resize(height=512, width=512, p=1),\n            A.Cutout(num_holes=5, max_h_size=32, max_w_size=32, fill_value=0, p=0.3),\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":{},"cell_type":"markdown","source":"## Dataset"},{"metadata":{"trusted":true},"cell_type":"code","source":"TRAIN_ROOT_PATH = '../input/ranzcr-clip-catheter-line-classification/train'\n\nclass DatasetRANZCR(Dataset):\n\n    def __init__(self, image_ids,dataframe, transforms=None, test=False):\n        super().__init__()\n\n        self.image_ids = image_ids\n        self.dataframe = dataframe\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 = self.load_image_and_boxes(index)\n\n        # there is only one class\n        labels = torch.ones((boxes.shape[0],), dtype=torch.int64)\n        \n        target = {}\n        target['boxes'] = boxes\n        target['labels'] = labels\n        target['image_id'] = torch.tensor([index])\n\n        if self.transforms:\n            for i in range(10):\n                sample = self.transforms(**{\n                    'image': image,\n                    'bboxes': target['boxes'],\n                    'labels': 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                    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.dataframe[self.dataframe['filename'] == image_id]\n        boxes = records[['x', 'y', 'w', 'h']].values\n        boxes[:, 2] = boxes[:, 0] + boxes[:, 2]\n        boxes[:, 3] = boxes[:, 1] + boxes[:, 3]\n        return image, boxes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fold_id = 0\ntrain_df = df[df.fold!=fold_id]\nval_df = df[df.fold==fold_id]\n\n\ntrain_dataset = DatasetRANZCR(\n    image_ids=train_df.filename.values,\n    dataframe=train_df,\n    transforms=get_train_transforms(),\n    test=False,\n)\n\nvalidation_dataset = DatasetRANZCR(\n    image_ids=val_df.filename.values,\n    dataframe=val_df,\n    transforms=get_valid_transforms(),\n    test=True,\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, axes = plt.subplots(3, 3, figsize=(20,20))\naxes = axes.flatten()\nfor i,ax in enumerate(axes):\n    image, target, image_id = train_dataset[i]\n    boxes = target['boxes'].cpu().numpy().astype(np.int32)\n    numpy_image = image.permute(1,2,0).cpu().numpy()\n    for box in boxes:\n        cv2.rectangle(numpy_image, (box[1], box[0]), (box[3],  box[2]), (0, 1, 0), 2)\n    ax.imshow(numpy_image)\n    ax.axis('off')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Fitter"},{"metadata":{"trusted":true},"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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import warnings\n\nwarnings.filterwarnings(\"ignore\")\n\nclass 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    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'\\n{timestamp}\\nLR: {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        t = time.time()\n        for step, (images, targets, image_ids) in enumerate(val_loader):\n            if self.config.verbose:\n                if step % self.config.verbose_step == 0:\n                    print(\n                        f'Val Step {step}/{len(val_loader)}, ' + \\\n                        f'summary_loss: {summary_loss.avg:.5f}, ' + \\\n                        f'time: {(time.time() - t):.5f}', end='\\r'\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        t = time.time()\n        for step, (images, targets, image_ids) in enumerate(train_loader):\n            if self.config.verbose:\n                if step % self.config.verbose_step == 0:\n                    print(\n                        f'Train Step {step}/{len(train_loader)}, ' + \\\n                        f'summary_loss: {summary_loss.avg:.5f}, ' + \\\n                        f'time: {(time.time() - t):.5f}', end='\\r'\n                    )\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":"class TrainConfig:\n    num_workers = 2\n    batch_size = 4 \n    n_epochs = 3 # n_epochs = 40\n    lr = 0.0002\n\n    folder = 'effdet5'\n\n    # -------------------\n    verbose = True\n    verbose_step = 1\n    # -------------------\n\n    # --------------------\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.OneCycleLR\n#     scheduler_params = dict(\n#         max_lr=0.001,\n#         epochs=n_epochs,\n#         steps_per_epoch=int(len(train_dataset) / batch_size),\n#         pct_start=0.1,\n#         anneal_strategy='cos', \n#         final_div_factor=10**5\n#     )\n    \n    SchedulerClass = torch.optim.lr_scheduler.ReduceLROnPlateau\n    scheduler_params = dict(\n        mode='min',\n        factor=0.5,\n        patience=1,\n        verbose=False, \n        threshold=0.0001,\n        threshold_mode='abs',\n        cooldown=0, \n        min_lr=1e-8,\n        eps=1e-08\n    )\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=TrainConfig.batch_size,\n        sampler=RandomSampler(train_dataset),\n        pin_memory=False,\n        drop_last=True,\n        num_workers=TrainConfig.num_workers,\n        collate_fn=collate_fn,\n    )\n    val_loader = torch.utils.data.DataLoader(\n        validation_dataset, \n        batch_size=TrainConfig.batch_size,\n        num_workers=TrainConfig.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=TrainConfig)\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=False)\n    checkpoint = torch.load('../input/efficientdet/efficientdet_d5-ef44aea8.pth')\n    net.load_state_dict(checkpoint)\n    config.num_classes = 1\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":"def make_predictions(images, score_threshold=0.22):\n    images = images.cuda().float()\n    predictions = []\n    with torch.no_grad():\n        det = net(images, torch.tensor([1]*images.shape[0]).float().cuda())\n        for i in range(images.shape[0]):\n            boxes = det[i].detach().cpu().numpy()[:,:4]    \n            scores = det[i].detach().cpu().numpy()[:,4]\n            indexes = np.where(scores > score_threshold)[0]\n            boxes = boxes[indexes]\n            boxes[:, 2] = boxes[:, 2] + boxes[:, 0]\n            boxes[:, 3] = boxes[:, 3] + boxes[:, 1]\n            predictions.append({\n                'boxes': boxes[indexes],\n                'scores': scores[indexes],\n            })\n    return [predictions]\n\ndef run_wbf(predictions, image_index, image_size=512, iou_thr=0.44, skip_box_thr=0.43, weights=None):\n    boxes = [(prediction[image_index]['boxes']/(image_size-1)).tolist()  for prediction in predictions]\n    scores = [prediction[image_index]['scores'].tolist()  for prediction in predictions]\n    labels = [np.ones(prediction[image_index]['scores'].shape[0]).tolist() for prediction in predictions]\n    boxes, scores, labels = weighted_boxes_fusion(boxes, scores, labels, weights=None, iou_thr=iou_thr, skip_box_thr=skip_box_thr)\n    boxes = boxes*(image_size-1)\n    return boxes, scores, labels","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def load_net(checkpoint_path):\n    config = get_efficientdet_config('tf_efficientdet_d5')\n    net = EfficientDet(config, pretrained_backbone=False)\n\n    config.num_classes = 1\n    config.image_size=512\n    net.class_net = HeadNet(config, num_outputs=config.num_classes, norm_kwargs=dict(eps=.001, momentum=.01))\n\n    checkpoint = torch.load(checkpoint_path)\n    net.load_state_dict(checkpoint['model_state_dict'])\n\n    del checkpoint\n    gc.collect()\n\n    net = DetBenchEval(net, config)\n    net.eval();\n    return net.cuda()\n\nnet = load_net('effdet5/best-checkpoint-002epoch.bin')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, axes = plt.subplots(3, 3, figsize=(20,20))\naxes = axes.flatten()\nfor i,ax in enumerate(axes):\n    images = validation_dataset[i][0]\n    predictions = make_predictions(images[None])\n    images = images.permute(1,2,0).cpu().numpy()\n    boxes, scores, labels = run_wbf(predictions, image_index=0)\n    boxes = boxes.astype(np.int32).clip(min=0, max=511)\n    for box in boxes:\n        cv2.rectangle(images, (box[0], box[1]), (box[2], box[3]), (1, 0, 0), 1)\n    ax.imshow(images)\n    ax.axis('off')\nplt.show()","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}