data/datasets/object_detection/coco2017.py

from ..ab_dataset import ABDataset
from typing import Dict, List, Optional
from torchvision.transforms import Compose
from .yolox_data_util.api import get_default_yolox_coco_dataset, get_yolox_coco_dataset_with_caption, remap_dataset, ensure_index_start_from_1_and_successive, coco_train_val_split
import os

from ..registery import dataset_register


categories = [{"supercategory": "person","id": 1,"name": "person"},{"supercategory": "vehicle","id": 2,"name": "bicycle"},{"supercategory": "vehicle","id": 3,"name": "car"},{"supercategory": "vehicle","id": 4,"name": "motorcycle"},{"supercategory": "vehicle","id": 5,"name": "airplane"},{"supercategory": "vehicle","id": 6,"name": "bus"},{"supercategory": "vehicle","id": 7,"name": "train"},{"supercategory": "vehicle","id": 8,"name": "truck"},{"supercategory": "vehicle","id": 9,"name": "boat"},{"supercategory": "outdoor","id": 10,"name": "traffic light"},{"supercategory": "outdoor","id": 11,"name": "fire hydrant"},{"supercategory": "outdoor","id": 13,"name": "stop sign"},{"supercategory": "outdoor","id": 14,"name": "parking meter"},{"supercategory": "outdoor","id": 15,"name": "bench"},{"supercategory": "animal","id": 16,"name": "bird"},{"supercategory": "animal","id": 17,"name": "cat"},{"supercategory": "animal","id": 18,"name": "dog"},{"supercategory": "animal","id": 19,"name": "horse"},{"supercategory": "animal","id": 20,"name": "sheep"},{"supercategory": "animal","id": 21,"name": "cow"},{"supercategory": "animal","id": 22,"name": "elephant"},{"supercategory": "animal","id": 23,"name": "bear"},{"supercategory": "animal","id": 24,"name": "zebra"},{"supercategory": "animal","id": 25,"name": "giraffe"},{"supercategory": "accessory","id": 27,"name": "backpack"},{"supercategory": "accessory","id": 28,"name": "umbrella"},{"supercategory": "accessory","id": 31,"name": "handbag"},{"supercategory": "accessory","id": 32,"name": "tie"},{"supercategory": "accessory","id": 33,"name": "suitcase"},{"supercategory": "sports","id": 34,"name": "frisbee"},{"supercategory": "sports","id": 35,"name": "skis"},{"supercategory": "sports","id": 36,"name": "snowboard"},{"supercategory": "sports","id": 37,"name": "sports ball"},{"supercategory": "sports","id": 38,"name": "kite"},{"supercategory": "sports","id": 39,"name": "baseball bat"},{"supercategory": "sports","id": 40,"name": "baseball glove"},{"supercategory": "sports","id": 41,"name": "skateboard"},{"supercategory": "sports","id": 42,"name": "surfboard"},{"supercategory": "sports","id": 43,"name": "tennis racket"},{"supercategory": "kitchen","id": 44,"name": "bottle"},{"supercategory": "kitchen","id": 46,"name": "wine glass"},{"supercategory": "kitchen","id": 47,"name": "cup"},{"supercategory": "kitchen","id": 48,"name": "fork"},{"supercategory": "kitchen","id": 49,"name": "knife"},{"supercategory": "kitchen","id": 50,"name": "spoon"},{"supercategory": "kitchen","id": 51,"name": "bowl"},{"supercategory": "food","id": 52,"name": "banana"},{"supercategory": "food","id": 53,"name": "apple"},{"supercategory": "food","id": 54,"name": "sandwich"},{"supercategory": "food","id": 55,"name": "orange"},{"supercategory": "food","id": 56,"name": "broccoli"},{"supercategory": "food","id": 57,"name": "carrot"},{"supercategory": "food","id": 58,"name": "hot dog"},{"supercategory": "food","id": 59,"name": "pizza"},{"supercategory": "food","id": 60,"name": "donut"},{"supercategory": "food","id": 61,"name": "cake"},{"supercategory": "furniture","id": 62,"name": "chair"},{"supercategory": "furniture","id": 63,"name": "couch"},{"supercategory": "furniture","id": 64,"name": "potted plant"},{"supercategory": "furniture","id": 65,"name": "bed"},{"supercategory": "furniture","id": 67,"name": "dining table"},{"supercategory": "furniture","id": 70,"name": "toilet"},{"supercategory": "electronic","id": 72,"name": "tv"},{"supercategory": "electronic","id": 73,"name": "laptop"},{"supercategory": "electronic","id": 74,"name": "mouse"},{"supercategory": "electronic","id": 75,"name": "remote"},{"supercategory": "electronic","id": 76,"name": "keyboard"},{"supercategory": "electronic","id": 77,"name": "cell phone"},{"supercategory": "appliance","id": 78,"name": "microwave"},{"supercategory": "appliance","id": 79,"name": "oven"},{"supercategory": "appliance","id": 80,"name": "toaster"},{"supercategory": "appliance","id": 81,"name": "sink"},{"supercategory": "appliance","id": 82,"name": "refrigerator"},{"supercategory": "indoor","id": 84,"name": "book"},{"supercategory": "indoor","id": 85,"name": "clock"},{"supercategory": "indoor","id": 86,"name": "vase"},{"supercategory": "indoor","id": 87,"name": "scissors"},{"supercategory": "indoor","id": 88,"name": "teddy bear"},{"supercategory": "indoor","id": 89,"name": "hair drier"},{"supercategory": "indoor","id": 90,"name": "toothbrush"}]
classes = [i['name'] for i in categories]

@dataset_register(
    name='COCO2017', 
    classes=classes, 
    task_type='Object Detection',
    object_type='Generic Object',
    class_aliases=[],
    shift_type=None
)
class COCO2017(ABDataset):
    def create_dataset(self, root_dir: str, split: str, transform: Optional[Compose], 
                       classes: List[str], ignore_classes: List[str], idx_map: Optional[Dict[int, int]]):
        assert transform is None, \
            'The implementation of object detection datasets is based on YOLOX (https://github.com/Megvii-BaseDetection/YOLOX) ' \
            'where normal `torchvision.transforms` is not supported. You can re-implement the dataset to override default data aug.'

        if split == 'val':
            split = 'test'
        
        root_dir = os.path.join(root_dir, 'train2017' if split != 'test' else 'val2017')
        ann_json_file_path = os.path.join(root_dir, 'coco_ann.json')
        assert os.path.exists(ann_json_file_path), \
            f'Please put the COCO annotation JSON file in root_dir: `{root_dir}/coco_ann.json`.'
            
        ann_json_file_path = ensure_index_start_from_1_and_successive(ann_json_file_path)

        ann_json_file_path = remap_dataset(ann_json_file_path, ignore_classes, idx_map)

        if split != 'test':
            ann_json_file_path = coco_train_val_split(ann_json_file_path, split)

        # print('coco debug fixed ann_json_file_path')
        # ann_json_file_path = '/data/zql/datasets/coco2017/coco/annotations/instances_val2017.json'

        
        dataset = get_default_yolox_coco_dataset(root_dir, ann_json_file_path, train=(split == 'train'))
        
        
        return dataset

@dataset_register(
    name='MM-COCO2017', 
    classes=classes, 
    task_type='MM Object Detection',
    object_type='Generic Object',
    class_aliases=[],
    shift_type=None
)
class MM_COCO2017(ABDataset):
    def create_dataset(self, root_dir: str, split: str, transform: Optional[Compose], 
                       classes: List[str], ignore_classes: List[str], idx_map: Optional[Dict[int, int]]):
        # assert transform is None, \
        #     'The implementation of object detection datasets is based on YOLOX (https://github.com/Megvii-BaseDetection/YOLOX) ' \
        #     'where normal `torchvision.transforms` is not supported. You can re-implement the dataset to override default data aug.'

        if split == 'val':
            split = 'test'
        
        root_dir = os.path.join(root_dir, 'train2017' if split != 'test' else 'val2017')
        ann_json_file_path = os.path.join(root_dir, 'coco_ann.json')
        
        assert os.path.exists(ann_json_file_path), \
            f'Please put the COCO annotation JSON file in root_dir: `{root_dir}/coco_ann.json`.'
            
        ann_json_file_path = ensure_index_start_from_1_and_successive(ann_json_file_path)

        ann_json_file_path = remap_dataset(ann_json_file_path, ignore_classes, idx_map)

        if split != 'test':
            ann_json_file_path = coco_train_val_split(ann_json_file_path, split)

        # print('coco debug fixed ann_json_file_path')
        # ann_json_file_path = '/data/zql/datasets/coco2017/coco/annotations/instances_val2017.json'
        self.ann_json_file_path_for_split = '/data/zql/datasets/coco2017/val2017/coco_ann.json'
        
        dataset = get_yolox_coco_dataset_with_caption(root_dir, ann_json_file_path, transform=transform, train=(split == 'train'))
        self.num_classes = 80
        
        return dataset