运行出现bug 这么解决

[sharp-xiang]

Before Asking

• I have read the README carefully. 我已经仔细阅读了README上的操作指引。

• I want to train my custom dataset, and I have read the tutorials for finetune on your data carefully and organize my dataset correctly; 我想训练自定义数据集，我已经仔细阅读了训练自定义数据的教程，以及按照正确的目录结构存放数据集。

• I have pulled the latest code of main branch to run again and the problem still existed. 我已经拉取了主分支上最新的代码，重新运行之后，问题仍不能解决。

Search before asking

• I have searched the DAMO-YOLO issues and found no similar questions.

Question

[Bug]: TypeError: Caught TypeError in DataLoader worker process 0. Original Traceback (most recent call last): File "/data/Disk_B/minrui/anaconda3/envs/mmdetection/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop data = fetcher.fetch(index) File "/data/Disk_B/minrui/anaconda3/envs/mmdetection/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/data/Disk_B/minrui/anaconda3/envs/mmdetection/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/data/Disk_B/minrui/DAMO-YOLO-master/damo/dataset/datasets/mosaic_wrapper.py", line 226, in getitem img, labels, segments, img_id = self._dataset.pull_item(idx) File "/data/Disk_B/minrui/DAMO-YOLO-master/damo/dataset/datasets/coco.py", line 97, in pull_item obj_mask += mask TypeError: 'int' object is not iterable

Additional

[ksv87]

make sure that the files are instances_train 2017.json and instances_val2017.json segmentation tags are set to [] (not int) or fix the code here:

DAMO-YOLO/damo/dataset/datasets/coco.py

Lines 92 to 103 in 319572e

	obj_masks = []
	for obj in anno:
	obj_mask = []
	if 'segmentation' in obj:
	for mask in obj['segmentation']:
	obj_mask += mask
	if len(obj_mask) > 0:
	obj_masks.append(obj_mask)
	seg_masks = [
	np.array(obj_mask, dtype=np.float32).reshape(-1, 2)
	for obj_mask in obj_masks
	]