lucasjinreal / yolov7_d2

🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥
GNU General Public License v3.0
3.13k stars 483 forks source link

No such file or directory: 'datasets\\coco/annotations/instances_train2017.json' #197

Closed shoayi closed 1 year ago

shoayi commented 1 year ago

hi! I configure the following parameters in the file train_custom_datasets.py

DATASET_ROOT = "./datasets/single_woodmask/" ANN_ROOT = os.path.join(DATASET_ROOT, "annotations") TRAIN_PATH = os.path.join(DATASET_ROOT, "train2017") VAL_PATH = os.path.join(DATASET_ROOT, "val2017") TRAIN_JSON = os.path.join(ANN_ROOT, "instances_train2017.json") VAL_JSON = os.path.join(ANN_ROOT, "instances_val2017.json") register_coco_instances("single_woodmask_train", {}, TRAIN_JSON, TRAIN_PATH) register_coco_instances("single_woodmask_val", {}, VAL_JSON, VAL_PATH)

But it still reports the following error: Traceback (most recent call last): File "J:/myproject/car_wood/yolov7_d2-main/train_custom_datasets.py", line 114, in args=(args,), File "g:\detectron2\detectron2\detectron2\engine\launch.py", line 82, in launch main_func(args) File "J:/myproject/car_wood/yolov7_d2-main/train_custom_datasets.py", line 101, in main trainer = Trainer(cfg) File "g:\detectron2\detectron2\detectron2\engine\defaults.py", line 378, in init data_loader = self.build_train_loader(cfg) File "J:\myproject\car_wood\yolov7_d2-main\train_det.py", line 34, in build_train_loader return build_detection_train_loader(cfg, mapper=cls.custom_mapper) File "g:\detectron2\detectron2\detectron2\config\config.py", line 207, in wrapped explicit_args = _get_args_from_config(from_config, args, *kwargs) File "g:\detectron2\detectron2\detectron2\config\config.py", line 245, in _get_args_from_config ret = from_config_func(args, **kwargs) File "g:\detectron2\detectron2\detectron2\data\build.py", line 350, in _train_loader_from_config proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN if cfg.MODEL.LOAD_PROPOSALS else None, File "g:\detectron2\detectron2\detectron2\data\build.py", line 241, in get_detection_dataset_dicts dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in names] File "g:\detectron2\detectron2\detectron2\data\build.py", line 241, in dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in names] File "g:\detectron2\detectron2\detectron2\data\catalog.py", line 58, in get return f() File "g:\detectron2\detectron2\detectron2\data\datasets\coco.py", line 500, in DatasetCatalog.register(name, lambda: load_coco_json(json_file, image_root, name)) File "g:\detectron2\detectron2\detectron2\data\datasets\coco.py", line 69, in load_coco_json coco_api = COCO(json_file) File "D:\software\anaconda\Anaconda3\envs\yolov7-mask\lib\site-packages\pycocotools\coco.py", line 81, in init with open(annotation_file, 'r') as f: FileNotFoundError: [Errno 2] No such file or directory: 'datasets\coco/annotations/instances_train2017.json'

Process finished with exit code 1

How can I fix this error?Thank you!

sori1234 commented 1 year ago

We also got the same error. Could you please tell me how to solve it?

brmarkus commented 1 year ago

Have you downloaded the Coco data (like from the Coco 2017 challenge, e.g. "https://cocodataset.org/#download")?