{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Jacob Morin - COS 432"},{"metadata":{},"cell_type":"markdown","source":"This notebook trains the weights for a Faster R-CNN network and inference is done in a separate notebook."},{"metadata":{},"cell_type":"markdown","source":"Based on https://www.kaggle.com/pestipeti/pytorch-starter-fasterrcnn-train\n\n\nAugmentation inspired by https://www.kaggle.com/nvnnghia/awesome-augmentation\n\n\nand https://www.kaggle.com/c/global-wheat-detection/discussion/172418\n\n\npseudo labeling based on https://www.kaggle.com/nvnnghia/fasterrcnn-pseudo-labeling"},{"metadata":{},"cell_type":"markdown","source":"Most of my time on this project went into implementing mosaic, mixup, and general image augmentation. The structure of the network was unchanged as this notebook is based upon a Faster R-CNN implementation from torchvision with a pretrained resnet50. After I implemented the augmentation that I wanted I modified the pseudo labeling notebook above to include the augmentation from this notebook for it's retraining step."},{"metadata":{"trusted":true},"cell_type":"code","source":"! pip install --upgrade albumentations\n#!pip install freeze","execution_count":null,"outputs":[]},{"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 math\nimport random\n\nfrom PIL import Image\n\nimport albumentations as A\nfrom albumentations.pytorch.transforms import ToTensorV2\n\nimport ast\nimport torch\nimport torchvision\n\nfrom torchvision.models.detection.faster_rcnn import FastRCNNPredictor\nfrom torchvision.models.detection import FasterRCNN\nfrom torchvision.models.detection.rpn import AnchorGenerator\n\nfrom torch.utils.data import DataLoader, Dataset\nfrom torch.utils.data.sampler import SequentialSampler\n\nfrom matplotlib import pyplot as plt\n\nDIR_INPUT = '/kaggle/input/global-wheat-detection'\nDIR_TRAIN = f'{DIR_INPUT}/train'\nDIR_TEST = f'{DIR_INPUT}/test'\n\nDIR_WEIGHTS = '/kaggle/input/rcnn12151'    #My pretrained wights directory\n\nWEIGHTS_FILE = f'{DIR_WEIGHTS}/fasterrcnn_resnet50_fpn-12151.pth'    #My pretrained wights","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.read_csv(f'{DIR_INPUT}/train.csv')\ntrain_df.shape","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)","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]","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)]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"valid_df.shape, train_df.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class WheatDataset(Dataset):\n\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        self.mix = False #Enable to turn on mixup\n        \n\n    def __getitem__(self, index: int):\n            \n        rnd = random.random()\n        #rnd = .4\n        if self.mix:\n            if rnd< 0.33:\n                # Load mosaic image\n                image, target, image_id = load_mosaic(self, index)\n\n            elif (rnd > 0.33 and rnd < 0.66):\n                image, target, image_id = load_mixup(self, index)\n\n            else:\n                # Load image normally\n                image, target, image_id = load_image(self, index,)\n        \n        else:\n            if rnd< 0.5:\n                # Load mosaic image\n                image, target, image_id = load_mosaic(self, index)\n\n            else:\n                # Load image normally\n                image, target, image_id = load_image(self, index,)\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":"def load_image(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'{self.image_dir}/{image_id}.jpg', cv2.IMREAD_COLOR)\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        sampleTrans = self.transforms(**sample)\n        \n        #make sure there is at least one box in a sample, break the code otherwise\n        while len(sampleTrans['bboxes'])==0:\n            #print(\"No boxes, rerun\")\n            sampleTrans = self.transforms(**sample)\n\n        #for loop to remove excessively narrow boxes, effectively only along the edges after albumentations\n        bs = sampleTrans['bboxes']\n        thresh = 4.5\n        pix = 15;\n        #print(bs)\n        for box in bs:\n            #print(box)\n            height = box[2]-box[0]\n            width = box[3]-box[1]\n            prop = height/width\n            #print(prop)\n            if( (height<pix or width< pix or prop>thresh or prop<(1/thresh)) and len(bs)>1):\n                #print('remove {0}'.format(box))\n                bs.remove(box)\n\n        if(len(bs)>=1):\n            sampleTrans['bboxes'] = bs\n        \n        sample = sampleTrans\n        \n        image = sample['image']\n\n        target['boxes'] = torch.stack(tuple(map(torch.tensor, zip(*sample['bboxes'])))).permute(1, 0)\n\n    return image, target, image_id","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def load_mixup(self, index):\n    # loads 2 images\n    imglist = []\n    idlist = []\n    allboxes = [[0,0,0,0]]\n    \n    for i in range(2):\n        if(i == 0):\n            #load initial image normally\n            image_id = self.image_ids[index]\n            \n        else:\n            #load random next image\n            image_id = self.image_ids[random.randint(0, len(self.image_ids) - 1)]\n\n        records = self.df[self.df['image_id'] == image_id]\n        boxes = records[['x', 'y', 'w', 'h']].values\n        #print(boxes)\n        boxes[:, 2] = boxes[:, 0] + boxes[:, 2] \n        boxes[:, 3] = boxes[:, 1] + boxes[:, 3]\n        \n        allboxes = np.vstack((allboxes, boxes))\n\n        image = cv2.imread(f'{self.image_dir}/{image_id}.jpg', cv2.IMREAD_COLOR)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB).astype(np.float32)\n        image /= 255.0\n        imglist.append(image)\n    \n        \n    #print(allboxes)\n    allboxes = allboxes[1:]\n    \n    #combine the two images\n    mix_img = np.add(imglist[0],(imglist[1]))/2\n        \n    #print(mix_img)\n        \n    area = (allboxes[:, 3] - allboxes[:, 1]) * (allboxes[:, 2] - allboxes[:, 0])\n    area = torch.as_tensor(area, dtype=torch.float32)\n\n    # there is only one class\n    labels = torch.ones((allboxes.shape[0],), dtype=torch.int64)\n\n    # suppose all instances are not crowd\n    iscrowd = torch.zeros((allboxes.shape[0],), dtype=torch.int64)\n\n    target = {}\n    target['boxes'] = allboxes\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    sample = {\n            'image': mix_img,\n            'bboxes': target['boxes'],\n            'labels': labels\n        }\n    \n    if self.transforms:\n        \n        sampleTrans = self.transforms(**sample)\n        \n        while len(sampleTrans['bboxes'])==0:\n            #print(\"No boxes, rerun\")\n            sampleTrans = self.transforms(**sample)\n               \n        #for loop to remove excessively narrow boxes, effectively only along the edges after albumentations\n        bs = sampleTrans['bboxes']\n        thresh = 4.5\n        pix = 15;\n        #print(bs)\n        for box in bs:\n            #print(box)\n            height = box[2]-box[0]\n            width = box[3]-box[1]\n            prop = height/width\n            #print(prop)\n            if( (height<pix or width< pix or prop>thresh or prop<(1/thresh)) and len(bs)>1):\n                #print('remove {0}'.format(box))\n                bs.remove(box)\n\n        if(len(bs)>=1):\n            sampleTrans['bboxes'] = bs\n            \n        sample = sampleTrans\n        \n        mix_img = sample['image']\n        \n        target['boxes'] = torch.stack(tuple(map(torch.tensor, zip(*sample['bboxes'])))).permute(1, 0)\n            \n    return mix_img, target, image_id","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def load_mosaic(self, index):\n    # loads images in a mosaic by loading them into a 2x2 grid first, then cropping to move the center\n    imglist = []\n    idlist = []\n    allboxes = [[0,0,0,0]]\n    \n    for i in range(4):\n        if(i == 0):\n            #load initial image normally\n            image_id = self.image_ids[index]\n            \n            padw, padh = 0, 0\n            \n        else:\n            #load random next image\n            image_id = self.image_ids[random.randint(0, len(self.image_ids) - 1)]\n            \n            if(i==1):\n                padw, padh = 1024, 0\n            if(i==2):\n                padw, padh = 0, 1024\n            if(i==3):\n                padw, padh = 1024, 1024\n                \n        #idlist.append(image_id)\n        records = self.df[self.df['image_id'] == image_id]\n        boxes = records[['x', 'y', 'w', 'h']].values\n        boxes[:, 0] = boxes[:, 0] + padw\n        boxes[:, 1] = boxes[:, 1] + padh\n        boxes[:, 2] = boxes[:, 0] + boxes[:, 2] \n        boxes[:, 3] = boxes[:, 1] + boxes[:, 3]\n        \n        #print(boxes)\n        \n        allboxes = np.vstack((allboxes, boxes))\n\n        image = cv2.imread(f'{self.image_dir}/{image_id}.jpg', cv2.IMREAD_COLOR)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB).astype(np.float32)\n        image /= 255.0\n        imglist.append(image)\n    \n        \n    #print(allboxes)\n    allboxes = allboxes[1:]\n    grid_img = make_grid(imglist)\n\n    area = (allboxes[:, 3] - allboxes[:, 1]) * (allboxes[:, 2] - allboxes[:, 0])\n    area = torch.as_tensor(area, dtype=torch.float32)\n\n    # there is only one class\n    labels = torch.ones((allboxes.shape[0],), dtype=torch.int64)\n\n    # suppose all instances are not crowd\n    iscrowd = torch.zeros((allboxes.shape[0],), dtype=torch.int64)\n\n    target = {}\n    target['boxes'] = allboxes\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    sample = {\n            'image': grid_img,\n            'bboxes': target['boxes'],\n            'labels': labels\n        }\n    aug = crop_mosaic()\n    sample = aug(**sample)\n    \n    if self.transforms:\n        \n        sampleTrans = self.transforms(**sample)\n        \n        while len(sampleTrans['bboxes'])==0:\n            #print(\"No boxes, rerun\")\n            sampleTrans = self.transforms(**sample)\n               \n        #for loop to remove excessively narrow boxes, effectively only along the edges after albumentations\n        bs = sampleTrans['bboxes']\n        thresh = 4.5\n        pix = 15;\n        #print(bs)\n        for box in bs:\n            #print(box)\n            height = box[2]-box[0]\n            width = box[3]-box[1]\n            prop = height/width\n            #print(prop)\n            if( (height<pix or width< pix or prop>thresh or prop<(1/thresh)) and len(bs)>1):\n                #print('remove {0}'.format(box))\n                bs.remove(box)\n\n        if(len(bs)>=1):\n            sampleTrans['bboxes'] = bs\n            \n        sample = sampleTrans\n        \n        grid_img = sample['image']\n        \n        target['boxes'] = torch.stack(tuple(map(torch.tensor, zip(*sample['bboxes'])))).permute(1, 0)\n            \n    return grid_img, target, image_id","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def crop_mosaic():\n    return A.Compose([\n        A.RandomSizedCrop (min_max_height=[800,1200], height=1024, width=1024, w2h_ratio=1.0, interpolation=1, always_apply=True, p=1.0),\n        #ToTensorV2(p=1.0)\n    ], bbox_params={'format': 'pascal_voc', 'label_fields': ['labels']})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def make_grid(imagelist):\n    #stacks the 4 images in the list to form a 2x2 grid\n    lrt = np.hstack((imagelist[0],imagelist[1]))\n    lrb = np.hstack((imagelist[2],imagelist[3]))\n    grid_image = np.vstack((lrt,lrb))\n    #print(grid_image.shape)\n    return grid_image","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Albumentations\ndef get_train_transform():\n    return A.Compose([\n        \n        A.Flip(0.5),\n        A.ShiftScaleRotate (shift_limit=0.0, scale_limit=0.0, rotate_limit=10, interpolation=1, border_mode=cv2.BORDER_CONSTANT, value=None, mask_value=None, always_apply=False, p=.5),\n        A.RandomSizedCrop (min_max_height=[768,1024], height=1024, width=1024, w2h_ratio=1.0, interpolation=1, always_apply=False, p=.5),\n        A.ColorJitter (brightness=0.3, contrast=0.2, saturation=0.1, hue=0.1, always_apply=False, p=.5),\n        \n        ToTensorV2(p=1.0)\n    ], bbox_params={'format': 'pascal_voc', 'label_fields': ['labels']})\n\ndef get_valid_transform():\n    return A.Compose([\n        #A.Resize(512, 512),\n        ToTensorV2(p=1.0)\n    ], bbox_params={'format': 'pascal_voc', 'label_fields': ['labels']})\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Create the model"},{"metadata":{"trusted":true},"cell_type":"code","source":"isPretrained = False #Enable to load previously train weights\nnum_classes = 2  # 1 class (wheat) + background","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# load a model; pre-trained on COCO or load it with weights from previous training\nif isPretrained:\n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)\n    \n    # get number of input features for the classifier\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    \nelse:\n    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=False, pretrained_backbone=False)\n\n    # get number of input features for the classifier\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    # Load the trained weights\n    model.load_state_dict(torch.load(WEIGHTS_FILE))","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\n","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=6,\n    shuffle=True,\n    num_workers=4,\n    collate_fn=collate_fn\n)\n\nvalid_data_loader = DataLoader(\n    valid_dataset,\n    batch_size=3,\n    shuffle=True,\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":"# Sample"},{"metadata":{"trusted":true},"cell_type":"code","source":"images, targets, image_ids = next(iter(train_data_loader))\nfig, ax = plt.subplots(6, 1, figsize=(160, 80))\n\n#print(len(images))\n\nfor i in range(6):\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    boxes = targets[i]['boxes'].cpu().numpy().astype(np.int32)\n    sample = images[i].permute(1,2,0).cpu().numpy()\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[i].imshow(sample)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#error (uncomment to make execution stop after samples)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Train"},{"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=0.005, momentum=0.9, weight_decay=0.0005)\n#optimizer = torch.optim.Adadelta(params, lr=.001, rho=0.9, eps=1e-06, weight_decay=0)\n#optimizer = torch.optim.Adam(params, lr=0.005, betas=(0.9, 0.999), eps=1e-08, weight_decay=0.0005, amsgrad=False)\n#lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=3, gamma=0.1)\n#lr_scheduler = torch.optim.lr_scheduler.CyclicLR(optimizer, base_lr=0.001, max_lr=0.05, cycle_momentum=False)\nlr_scheduler = None\n\nnum_epochs = 5","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loss_hist = Averager()\nitr = 1\n\nfor epoch in range(num_epochs):\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        for param_group in optimizer.param_groups:\n                print(\"Current learning rate is: {}\".format(param_group['lr']))\n\n    print(f\"Epoch #{epoch} loss: {loss_hist.value}\")   ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#sample_ids = ['aac893a91','51f1be19e','f5a1f0358','796707dd7','51b3e36ab','348a992bb','cc3532ff6','2fd875eaa','cb8d261a3','53f253011',]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_id = '1ef16dab1'\n\ntrain_df = pd.read_csv(f'{DIR_INPUT}/train.csv')\ntrain_df.shape\n\nbox_data = np.stack(train_df['bbox'].apply(lambda x: ast.literal_eval(x)))\ntrain_df[['x', 'y', 'w', 'h']] = pd.DataFrame(box_data).astype(np.float32)\n\ngt_boxes = train_df[train_df['image_id'] == sample_id][['x', 'y', 'w', 'h']].values\ngt_boxes = gt_boxes.astype(np.int)\n\n# Ground-truth boxes of our sample\ngt_boxes","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"#Test results may not align with the image, pay more attention to the location of red vs blue boxes and less to the images."},{"metadata":{"trusted":true},"cell_type":"code","source":"images, targets, image_ids = next(iter(valid_data_loader))\nfig, ax = plt.subplots(3, 1, figsize=(160, 80))\n\nimages = list(img.to(device) for img in images)\ntargets = [{k: v.to(device) for k, v in t.items()} for t in targets]\n\nmodel.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]\n\n#print(len(images))\n\nfor i in range(3):\n\n    \n    sample_id = image_ids[i]\n    \n    sample = cv2.imread(f'{DIR_TRAIN}/{sample_id}.jpg', cv2.IMREAD_COLOR)\n    sample = cv2.cvtColor(sample, cv2.COLOR_BGR2RGB)\n\n    gt_boxes = train_df[train_df['image_id'] == sample_id][['x', 'y', 'w', 'h']].values\n    gt_boxes = gt_boxes.astype(np.int)\n\n    boxes = outputs[i]['boxes'].data.cpu().numpy()\n\n    for box in boxes:\n        cv2.rectangle(sample,\n                      (box[0], box[1]),\n                      (box[2], box[3]),\n                      (220, 0, 0), 2)\n        \n    for gt_box in gt_boxes:\n        cv2.rectangle(sample,\n                      (gt_box[0], gt_box[1]),\n                      (gt_box[0] + gt_box[2], gt_box[1] + gt_box[3]),\n                      (0, 0, 220), 2)\n\n    ax[i].imshow(sample)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"torch.save(model.state_dict(), 'fasterrcnn_resnet50_fpn2.pth')","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}