First commit

data/mmpose_custom/model/top_down.py

+# Copyright (c) OpenMMLab. All rights reserved.
+import os
+import warnings
+
+import mmcv
+import numpy as np
+from PIL import Image
+import torch
+from mmcv.image import imwrite
+from mmcv.utils.misc import deprecated_api_warning
+from mmcv.visualization.image import imshow
+
+from mmpose.core import imshow_bboxes, imshow_keypoints
+from mmpose.models import builder
+from mmpose.models.builder import POSENETS
+# from .base import BasePose
+from mmpose.models.detectors import TopDown
+
+try:
+    from mmcv.runner import auto_fp16
+except ImportError:
+    warnings.warn('auto_fp16 from mmpose will be deprecated from v0.15.0'
+                  'Please install mmcv>=1.1.4')
+    from mmpose.core import auto_fp16
+
+from mmpose.core.post_processing import flip_back
+from data.pipelines.custom_transform import define_colors_gb_mean_sep
+color_dict = define_colors_gb_mean_sep()
+color_list = [v for k, v in color_dict.items()]
+color_list.append((0, 0))
+
+
+@POSENETS.register_module()
+class TopDownCustom(TopDown):
+    """Top-down pose detectors.
+
+    Args:
+        backbone (dict): Backbone modules to extract feature.
+        keypoint_head (dict): Keypoint head to process feature.
+        train_cfg (dict): Config for training. Default: None.
+        test_cfg (dict): Config for testing. Default: None.
+        pretrained (str): Path to the pretrained models.
+        loss_pose (None): Deprecated arguments. Please use
+            `loss_keypoint` for heads instead.
+    """
+    colors = torch.tensor(color_list, dtype=torch.float32, device="cuda")
+
+    def __init__(self,
+                 backbone,
+                 neck=None,
+                 keypoint_head=None,
+                 train_cfg=None,
+                 test_cfg=None,
+                 pretrained=None,
+                 loss_pose=None):
+        super().__init__(
+            backbone=backbone,
+            neck=neck,
+            keypoint_head=keypoint_head,
+            train_cfg=train_cfg,
+            test_cfg=test_cfg,
+            pretrained=pretrained,
+            loss_pose=loss_pose)
+
+    @auto_fp16(apply_to=('img', ))
+    def forward(self,
+                img,
+                target=None,
+                target_weight=None,
+                img_metas=None,
+                return_loss=True,
+                return_heatmap=False,
+                pseudo_test=False,
+                **kwargs):
+        """Calls either forward_train or forward_test depending on whether
+        return_loss=True. Note this setting will change the expected inputs.
+        When `return_loss=True`, img and img_meta are single-nested (i.e.
+        Tensor and List[dict]), and when `resturn_loss=False`, img and img_meta
+        should be double nested (i.e.  List[Tensor], List[List[dict]]), with
+        the outer list indicating test time augmentations.
+
+        Note:
+            - batch_size: N
+            - num_keypoints: K
+            - num_img_channel: C (Default: 3)
+            - img height: imgH
+            - img width: imgW
+            - heatmaps height: H
+            - heatmaps weight: W
+
+        Args:
+            img (torch.Tensor[NxCximgHximgW]): Input images.
+            target (torch.Tensor[NxKxHxW]): Target heatmaps.
+            target_weight (torch.Tensor[NxKx1]): Weights across
+                different joint types.
+            img_metas (list(dict)): Information about data augmentation
+                By default this includes:
+
+                - "image_file: path to the image file
+                - "center": center of the bbox
+                - "scale": scale of the bbox
+                - "rotation": rotation of the bbox
+                - "bbox_score": score of bbox
+            return_loss (bool): Option to `return loss`. `return loss=True`
+                for training, `return loss=False` for validation & test.
+            return_heatmap (bool) : Option to return heatmap.
+
+        Returns:
+            dict|tuple: if `return loss` is true, then return losses. \
+                Otherwise, return predicted poses, boxes, image paths \
+                and heatmaps.
+        """
+        if pseudo_test:
+            return self.forward_pseudo_test(
+            img, img_metas, return_heatmap=return_heatmap, **kwargs)
+        if return_loss:
+            return self.forward_train(img, target, target_weight, img_metas,
+                                      **kwargs)
+        return self.forward_test(
+            img, img_metas, return_heatmap=return_heatmap, **kwargs)
+
+    def forward_test(self, img, img_metas, return_heatmap=False, **kwargs):
+        """Defines the computation performed at every call when testing."""
+        assert img.size(0) == len(img_metas)
+        batch_size, _, img_height, img_width = img.shape
+        if batch_size > 1:
+            assert 'bbox_id' in img_metas[0]
+
+        result = {}
+
+        features = self.backbone(img)
+        if self.with_neck:
+            features = self.neck(features)
+        if self.with_keypoint:
+            output_heatmap = self.keypoint_head.inference_model(
+                features, flip_pairs=None)
+
+        if self.test_cfg.get('flip_test', True):
+            img_flipped = img.flip(3)  # (b, c, h, w)
+            features_flipped = self.backbone(img_flipped)
+            if self.with_neck:
+                features_flipped = self.neck(features_flipped)
+            if self.with_keypoint:
+                output_flipped_heatmap = self.keypoint_head.inference_model(
+                    features_flipped, img_metas[0]['flip_pairs'])
+                output_heatmap = (output_heatmap + output_flipped_heatmap)
+                if self.test_cfg.get('regression_flip_shift', False):
+                    output_heatmap[..., 0] -= 1.0 / img_width
+                output_heatmap = output_heatmap / 2
+
+        if self.with_keypoint:
+            keypoint_result = self.keypoint_head.decode(
+                img_metas, output_heatmap, img_size=[img_width, img_height])
+            result.update(keypoint_result)
+
+            if not return_heatmap:
+                output_heatmap = None
+
+            result['output_heatmap'] = output_heatmap
+
+        return result
+
+    def forward_pseudo_test(self, img, img_metas, return_heatmap=False, **kwargs):
+        """Defines the computation performed at every call when testing."""
+        assert img.size(0) == len(img_metas)
+        batch_size, _, img_height, img_width = img.shape
+        if batch_size > 1:
+            assert 'bbox_id' in img_metas[0]
+
+        result = {}
+
+        output_heatmap = self.decode_images_to_heatmaps_minmax(
+            images=img, resize=False,
+        )
+
+        # add support for flip test
+        if self.test_cfg.get('flip_test', True):
+            image_flip_list = []
+            for batch_idx in range(img.shape[0]):
+                flip_image_dir = os.path.dirname(img_metas[batch_idx]['image_file']) + "_flip"
+                flip_image_name = os.path.basename(img_metas[batch_idx]['image_file'])
+                flip_image_path = os.path.join(flip_image_dir, flip_image_name)
+                image = np.array(Image.open(flip_image_path))
+                image_tensor = torch.from_numpy(image).to(img.device)
+                image_flip_list.append(image_tensor)
+            img_flipped = torch.stack(image_flip_list)  # (b, h, w, 3)
+            if self.with_keypoint:
+                # output_flipped_heatmap = self.keypoint_head.inference_model(
+                #     features_flipped, img_metas[0]['flip_pairs'])
+                output = self.decode_images_to_heatmaps_minmax(
+                    images=img_flipped, resize=False,
+                )
+                flip_pairs = img_metas[0]['flip_pairs']
+                assert flip_pairs is not None
+                output_flipped_heatmap = flip_back(
+                    output,
+                    flip_pairs,
+                    target_type=self.keypoint_head.target_type)
+                # feature is not aligned, shift flipped heatmap for higher accuracy
+                if self.test_cfg.get('shift_heatmap', False):
+                    output_flipped_heatmap[:, :, :, 1:] = output_flipped_heatmap[:, :, :, :-1]
+                output_heatmap = (output_heatmap + output_flipped_heatmap)
+                if self.test_cfg.get('regression_flip_shift', False):
+                    output_heatmap[..., 0] -= 1.0 / img_width
+                output_heatmap = output_heatmap / 2
+
+        if self.with_keypoint:
+            keypoint_result = self.keypoint_head.decode(
+                img_metas, output_heatmap, img_size=[img_width, img_height])
+            result.update(keypoint_result)
+
+            if not return_heatmap:
+                output_heatmap = None
+
+            result['output_heatmap'] = output_heatmap
+
+        return result
+
+    def decode_images_to_heatmaps_minmax(self, images, resize=False):
+        """
+
+        Args:
+            images: (bs, 256, 192, 3)
+            resize: whether to resize to (64, 48)
+
+        Returns:
+            heatmaps: (bs, 17, h, w)
+        """
+        assert images.shape[-1] == 3
+        batch_size, image_height, image_width, _ = images.shape
+        images = images.float()
+
+        # classify each pixel using GB
+        GB = images[..., 1:].view(batch_size, 1, image_height, image_width, 2)  # (bs, 1, 256, 192, 2)
+        colors = TopDown.colors
+        num_classes = colors.shape[0]
+        colors = colors.view(1, -1, 1, 1, 2)
+        dist = torch.abs(GB - colors).sum(-1)  # (bs, 18, 256, 192)
+        dist, indices = torch.min(dist, dim=1)  # (bs, 256, 192)
+        keypoint_mask_list = []
+        for idx in range(num_classes):
+            mask = indices == idx  # (bs, 256, 192)
+            keypoint_mask_list.append(mask)
+
+        R = images[..., 0]  # (bs, 256, 192)
+        heatmap_list = []
+        for idx in range(num_classes):
+            if idx == 17:
+                continue
+            mask = keypoint_mask_list[idx]
+            heatmap = mask * R
+            heatmap_list.append(heatmap.unsqueeze(1))
+        heatmaps = torch.cat(heatmap_list, dim=1)
+
+        if resize:
+            raise NotImplementedError
+
+        return heatmaps.cpu().numpy() / 255.

data/mmpose_custom/tools/dist_test.sh

+#!/usr/bin/env bash
+# Copyright (c) OpenMMLab. All rights reserved.
+
+CONFIG=$1
+CHECKPOINT=$2
+GPUS=$3
+NNODES=${NNODES:-1}
+NODE_RANK=${NODE_RANK:-0}
+PORT=${PORT:-29500}
+MASTER_ADDR=${MASTER_ADDR:-"127.0.0.1"}
+
+PYTHONPATH="$(dirname $0)/..":$PYTHONPATH \
+python -m torch.distributed.launch \
+    --nnodes=$NNODES \
+    --node_rank=$NODE_RANK \
+    --master_addr=$MASTER_ADDR \
+    --nproc_per_node=$GPUS \
+    --master_port=$PORT \
+    $(dirname "$0")/test.py \
+    $CONFIG \
+    $CHECKPOINT \
+    --launcher pytorch \
+    ${@:4}

data/panoptic_coco_categories.json

+[{"supercategory": "person", "color": [220, 20, 60], "isthing": 1, "id": 1, "name": "person"}, {"supercategory": "vehicle", "color": [119, 11, 32], "isthing": 1, "id": 2, "name": "bicycle"}, {"supercategory": "vehicle", "color": [0, 0, 142], "isthing": 1, "id": 3, "name": "car"}, {"supercategory": "vehicle", "color": [0, 0, 230], "isthing": 1, "id": 4, "name": "motorcycle"}, {"supercategory": "vehicle", "color": [106, 0, 228], "isthing": 1, "id": 5, "name": "airplane"}, {"supercategory": "vehicle", "color": [0, 60, 100], "isthing": 1, "id": 6, "name": "bus"}, {"supercategory": "vehicle", "color": [0, 80, 100], "isthing": 1, "id": 7, "name": "train"}, {"supercategory": "vehicle", "color": [0, 0, 70], "isthing": 1, "id": 8, "name": "truck"}, {"supercategory": "vehicle", "color": [0, 0, 192], "isthing": 1, "id": 9, "name": "boat"}, {"supercategory": "outdoor", "color": [250, 170, 30], "isthing": 1, "id": 10, "name": "traffic light"}, {"supercategory": "outdoor", "color": [100, 170, 30], "isthing": 1, "id": 11, "name": "fire hydrant"}, {"supercategory": "outdoor", "color": [220, 220, 0], "isthing": 1, "id": 13, "name": "stop sign"}, {"supercategory": "outdoor", "color": [175, 116, 175], "isthing": 1, "id": 14, "name": "parking meter"}, {"supercategory": "outdoor", "color": [250, 0, 30], "isthing": 1, "id": 15, "name": "bench"}, {"supercategory": "animal", "color": [165, 42, 42], "isthing": 1, "id": 16, "name": "bird"}, {"supercategory": "animal", "color": [255, 77, 255], "isthing": 1, "id": 17, "name": "cat"}, {"supercategory": "animal", "color": [0, 226, 252], "isthing": 1, "id": 18, "name": "dog"}, {"supercategory": "animal", "color": [182, 182, 255], "isthing": 1, "id": 19, "name": "horse"}, {"supercategory": "animal", "color": [0, 82, 0], "isthing": 1, "id": 20, "name": "sheep"}, {"supercategory": "animal", "color": [120, 166, 157], "isthing": 1, "id": 21, "name": "cow"}, {"supercategory": "animal", "color": [110, 76, 0], "isthing": 1, "id": 22, "name": "elephant"}, {"supercategory": "animal", "color": [174, 57, 255], "isthing": 1, "id": 23, "name": "bear"}, {"supercategory": "animal", "color": [199, 100, 0], "isthing": 1, "id": 24, "name": "zebra"}, {"supercategory": "animal", "color": [72, 0, 118], "isthing": 1, "id": 25, "name": "giraffe"}, {"supercategory": "accessory", "color": [255, 179, 240], "isthing": 1, "id": 27, "name": "backpack"}, {"supercategory": "accessory", "color": [0, 125, 92], "isthing": 1, "id": 28, "name": "umbrella"}, {"supercategory": "accessory", "color": [209, 0, 151], "isthing": 1, "id": 31, "name": "handbag"}, {"supercategory": "accessory", "color": [188, 208, 182], "isthing": 1, "id": 32, "name": "tie"}, {"supercategory": "accessory", "color": [0, 220, 176], "isthing": 1, "id": 33, "name": "suitcase"}, {"supercategory": "sports", "color": [255, 99, 164], "isthing": 1, "id": 34, "name": "frisbee"}, {"supercategory": "sports", "color": [92, 0, 73], "isthing": 1, "id": 35, "name": "skis"}, {"supercategory": "sports", "color": [133, 129, 255], "isthing": 1, "id": 36, "name": "snowboard"}, {"supercategory": "sports", "color": [78, 180, 255], "isthing": 1, "id": 37, "name": "sports ball"}, {"supercategory": "sports", "color": [0, 228, 0], "isthing": 1, "id": 38, "name": "kite"}, {"supercategory": "sports", "color": [174, 255, 243], "isthing": 1, "id": 39, "name": "baseball bat"}, {"supercategory": "sports", "color": [45, 89, 255], "isthing": 1, "id": 40, "name": "baseball glove"}, {"supercategory": "sports", "color": [134, 134, 103], "isthing": 1, "id": 41, "name": "skateboard"}, {"supercategory": "sports", "color": [145, 148, 174], "isthing": 1, "id": 42, "name": "surfboard"}, {"supercategory": "sports", "color": [255, 208, 186], "isthing": 1, "id": 43, "name": "tennis racket"}, {"supercategory": "kitchen", "color": [197, 226, 255], "isthing": 1, "id": 44, "name": "bottle"}, {"supercategory": "kitchen", "color": [171, 134, 1], "isthing": 1, "id": 46, "name": "wine glass"}, {"supercategory": "kitchen", "color": [109, 63, 54], "isthing": 1, "id": 47, "name": "cup"}, {"supercategory": "kitchen", "color": [207, 138, 255], "isthing": 1, "id": 48, "name": "fork"}, {"supercategory": "kitchen", "color": [151, 0, 95], "isthing": 1, "id": 49, "name": "knife"}, {"supercategory": "kitchen", "color": [9, 80, 61], "isthing": 1, "id": 50, "name": "spoon"}, {"supercategory": "kitchen", "color": [84, 105, 51], "isthing": 1, "id": 51, "name": "bowl"}, {"supercategory": "food", "color": [74, 65, 105], "isthing": 1, "id": 52, "name": "banana"}, {"supercategory": "food", "color": [166, 196, 102], "isthing": 1, "id": 53, "name": "apple"}, {"supercategory": "food", "color": [208, 195, 210], "isthing": 1, "id": 54, "name": "sandwich"}, {"supercategory": "food", "color": [255, 109, 65], "isthing": 1, "id": 55, "name": "orange"}, {"supercategory": "food", "color": [0, 143, 149], "isthing": 1, "id": 56, "name": "broccoli"}, {"supercategory": "food", "color": [179, 0, 194], "isthing": 1, "id": 57, "name": "carrot"}, {"supercategory": "food", "color": [209, 99, 106], "isthing": 1, "id": 58, "name": "hot dog"}, {"supercategory": "food", "color": [5, 121, 0], "isthing": 1, "id": 59, "name": "pizza"}, {"supercategory": "food", "color": [227, 255, 205], "isthing": 1, "id": 60, "name": "donut"}, {"supercategory": "food", "color": [147, 186, 208], "isthing": 1, "id": 61, "name": "cake"}, {"supercategory": "furniture", "color": [153, 69, 1], "isthing": 1, "id": 62, "name": "chair"}, {"supercategory": "furniture", "color": [3, 95, 161], "isthing": 1, "id": 63, "name": "couch"}, {"supercategory": "furniture", "color": [163, 255, 0], "isthing": 1, "id": 64, "name": "potted plant"}, {"supercategory": "furniture", "color": [119, 0, 170], "isthing": 1, "id": 65, "name": "bed"}, {"supercategory": "furniture", "color": [0, 182, 199], "isthing": 1, "id": 67, "name": "dining table"}, {"supercategory": "furniture", "color": [0, 165, 120], "isthing": 1, "id": 70, "name": "toilet"}, {"supercategory": "electronic", "color": [183, 130, 88], "isthing": 1, "id": 72, "name": "tv"}, {"supercategory": "electronic", "color": [95, 32, 0], "isthing": 1, "id": 73, "name": "laptop"}, {"supercategory": "electronic", "color": [130, 114, 135], "isthing": 1, "id": 74, "name": "mouse"}, {"supercategory": "electronic", "color": [110, 129, 133], "isthing": 1, "id": 75, "name": "remote"}, {"supercategory": "electronic", "color": [166, 74, 118], "isthing": 1, "id": 76, "name": "keyboard"}, {"supercategory": "electronic", "color": [219, 142, 185], "isthing": 1, "id": 77, "name": "cell phone"}, {"supercategory": "appliance", "color": [79, 210, 114], "isthing": 1, "id": 78, "name": "microwave"}, {"supercategory": "appliance", "color": [178, 90, 62], "isthing": 1, "id": 79, "name": "oven"}, {"supercategory": "appliance", "color": [65, 70, 15], "isthing": 1, "id": 80, "name": "toaster"}, {"supercategory": "appliance", "color": [127, 167, 115], "isthing": 1, "id": 81, "name": "sink"}, {"supercategory": "appliance", "color": [59, 105, 106], "isthing": 1, "id": 82, "name": "refrigerator"}, {"supercategory": "indoor", "color": [142, 108, 45], "isthing": 1, "id": 84, "name": "book"}, {"supercategory": "indoor", "color": [196, 172, 0], "isthing": 1, "id": 85, "name": "clock"}, {"supercategory": "indoor", "color": [95, 54, 80], "isthing": 1, "id": 86, "name": "vase"}, {"supercategory": "indoor", "color": [128, 76, 255], "isthing": 1, "id": 87, "name": "scissors"}, {"supercategory": "indoor", "color": [201, 57, 1], "isthing": 1, "id": 88, "name": "teddy bear"}, {"supercategory": "indoor", "color": [246, 0, 122], "isthing": 1, "id": 89, "name": "hair drier"}, {"supercategory": "indoor", "color": [191, 162, 208], "isthing": 1, "id": 90, "name": "toothbrush"}, {"supercategory": "textile", "color": [255, 255, 128], "isthing": 0, "id": 92, "name": "banner"}, {"supercategory": "textile", "color": [147, 211, 203], "isthing": 0, "id": 93, "name": "blanket"}, {"supercategory": "building", "color": [150, 100, 100], "isthing": 0, "id": 95, "name": "bridge"}, {"supercategory": "raw-material", "color": [168, 171, 172], "isthing": 0, "id": 100, "name": "cardboard"}, {"supercategory": "furniture-stuff", "color": [146, 112, 198], "isthing": 0, "id": 107, "name": "counter"}, {"supercategory": "textile", "color": [210, 170, 100], "isthing": 0, "id": 109, "name": "curtain"}, {"supercategory": "furniture-stuff", "color": [92, 136, 89], "isthing": 0, "id": 112, "name": "door-stuff"}, {"supercategory": "floor", "color": [218, 88, 184], "isthing": 0, "id": 118, "name": "floor-wood"}, {"supercategory": "plant", "color": [241, 129, 0], "isthing": 0, "id": 119, "name": "flower"}, {"supercategory": "food-stuff", "color": [217, 17, 255], "isthing": 0, "id": 122, "name": "fruit"}, {"supercategory": "ground", "color": [124, 74, 181], "isthing": 0, "id": 125, "name": "gravel"}, {"supercategory": "building", "color": [70, 70, 70], "isthing": 0, "id": 128, "name": "house"}, {"supercategory": "furniture-stuff", "color": [255, 228, 255], "isthing": 0, "id": 130, "name": "light"}, {"supercategory": "furniture-stuff", "color": [154, 208, 0], "isthing": 0, "id": 133, "name": "mirror-stuff"}, {"supercategory": "structural", "color": [193, 0, 92], "isthing": 0, "id": 138, "name": "net"}, {"supercategory": "textile", "color": [76, 91, 113], "isthing": 0, "id": 141, "name": "pillow"}, {"supercategory": "ground", "color": [255, 180, 195], "isthing": 0, "id": 144, "name": "platform"}, {"supercategory": "ground", "color": [106, 154, 176], "isthing": 0, "id": 145, "name": "playingfield"}, {"supercategory": "ground", "color": [230, 150, 140], "isthing": 0, "id": 147, "name": "railroad"}, {"supercategory": "water", "color": [60, 143, 255], "isthing": 0, "id": 148, "name": "river"}, {"supercategory": "ground", "color": [128, 64, 128], "isthing": 0, "id": 149, "name": "road"}, {"supercategory": "building", "color": [92, 82, 55], "isthing": 0, "id": 151, "name": "roof"}, {"supercategory": "ground", "color": [254, 212, 124], "isthing": 0, "id": 154, "name": "sand"}, {"supercategory": "water", "color": [73, 77, 174], "isthing": 0, "id": 155, "name": "sea"}, {"supercategory": "furniture-stuff", "color": [255, 160, 98], "isthing": 0, "id": 156, "name": "shelf"}, {"supercategory": "ground", "color": [255, 255, 255], "isthing": 0, "id": 159, "name": "snow"}, {"supercategory": "furniture-stuff", "color": [104, 84, 109], "isthing": 0, "id": 161, "name": "stairs"}, {"supercategory": "building", "color": [169, 164, 131], "isthing": 0, "id": 166, "name": "tent"}, {"supercategory": "textile", "color": [225, 199, 255], "isthing": 0, "id": 168, "name": "towel"}, {"supercategory": "wall", "color": [137, 54, 74], "isthing": 0, "id": 171, "name": "wall-brick"}, {"supercategory": "wall", "color": [135, 158, 223], "isthing": 0, "id": 175, "name": "wall-stone"}, {"supercategory": "wall", "color": [7, 246, 231], "isthing": 0, "id": 176, "name": "wall-tile"}, {"supercategory": "wall", "color": [107, 255, 200], "isthing": 0, "id": 177, "name": "wall-wood"}, {"supercategory": "water", "color": [58, 41, 149], "isthing": 0, "id": 178, "name": "water-other"}, {"supercategory": "window", "color": [183, 121, 142], "isthing": 0, "id": 180, "name": "window-blind"}, {"supercategory": "window", "color": [255, 73, 97], "isthing": 0, "id": 181, "name": "window-other"}, {"supercategory": "plant", "color": [107, 142, 35], "isthing": 0, "id": 184, "name": "tree-merged"}, {"supercategory": "structural", "color": [190, 153, 153], "isthing": 0, "id": 185, "name": "fence-merged"}, {"supercategory": "ceiling", "color": [146, 139, 141], "isthing": 0, "id": 186, "name": "ceiling-merged"}, {"supercategory": "sky", "color": [70, 130, 180], "isthing": 0, "id": 187, "name": "sky-other-merged"}, {"supercategory": "furniture-stuff", "color": [134, 199, 156], "isthing": 0, "id": 188, "name": "cabinet-merged"}, {"supercategory": "furniture-stuff", "color": [209, 226, 140], "isthing": 0, "id": 189, "name": "table-merged"}, {"supercategory": "floor", "color": [96, 36, 108], "isthing": 0, "id": 190, "name": "floor-other-merged"}, {"supercategory": "ground", "color": [96, 96, 96], "isthing": 0, "id": 191, "name": "pavement-merged"}, {"supercategory": "solid", "color": [64, 170, 64], "isthing": 0, "id": 192, "name": "mountain-merged"}, {"supercategory": "plant", "color": [152, 251, 152], "isthing": 0, "id": 193, "name": "grass-merged"}, {"supercategory": "ground", "color": [208, 229, 228], "isthing": 0, "id": 194, "name": "dirt-merged"}, {"supercategory": "raw-material", "color": [206, 186, 171], "isthing": 0, "id": 195, "name": "paper-merged"}, {"supercategory": "food-stuff", "color": [152, 161, 64], "isthing": 0, "id": 196, "name": "food-other-merged"}, {"supercategory": "building", "color": [116, 112, 0], "isthing": 0, "id": 197, "name": "building-other-merged"}, {"supercategory": "solid", "color": [0, 114, 143], "isthing": 0, "id": 198, "name": "rock-merged"}, {"supercategory": "wall", "color": [102, 102, 156], "isthing": 0, "id": 199, "name": "wall-other-merged"}, {"supercategory": "textile", "color": [250, 141, 255], "isthing": 0, "id": 200, "name": "rug-merged"}]

docker/Dockerfile

+FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:1.13.1-centos7.6-dtk-23.04-py38-latest
+RUN source /opt/dtk/env.sh
+COPY requirements.txt requirements.txt
+RUN pip3 install -r requirements.txt