记录pytorch训练yolov3出错
错误如下：
Model Summary: 222 layers, 6.15291e+07 parameters, 6.15291e+07 gradients
Caching labels (5547 found, 0 missing, 19 empty, 0 duplicate, for 5566 images): 100%|█| 5566/5566 [00:00<00:00, 75
Caching labels (2381 found, 0 missing, 5 empty, 0 duplicate, for 2386 images): 100%|█| 2386/2386 [00:00<00:00, 766
Using 8 dataloader workers
Starting training for 300 epochs...
Epoch gpu_mem GIoU obj cls total targets img_size
246/299 4.26G 2.09 0.81 2.11 5.01 10 416: 100%|█| 696/696 [03:01<00:00, 3
Class Images Targets P R mAP@0.5 F1: 0%| | 0/150 [00:00<?, ?it/s]
Traceback (most recent call last):
File "train.py", line 469, in <module>
train() # train normally
File "train.py", line 357, in train
dataloader=testloader)
File "/home/aistudio/facemask1/test.py", line 77, in test
for batch_i, (imgs, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
File "/opt/conda/envs/facemask/lib/python3.7/site-packages/tqdm/std.py", line 1127, in __iter__
for obj in iterable:
File "/opt/conda/envs/facemask/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 345, in __next__
data = self._next_data()
File "/opt/conda/envs/facemask/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 856, in _next_data
return self._process_data(data)
File "/opt/conda/envs/facemask/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 881, in _process_data
data.reraise()
File "/opt/conda/envs/facemask/lib/python3.7/site-packages/torch/_utils.py", line 394, in reraise
raise self.exc_type(msg)
cv2.error: Caught error in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/opt/conda/envs/facemask/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/opt/conda/envs/facemask/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/opt/conda/envs/facemask/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/aistudio/facemask1/utils/datasets.py", line 432, in __getitem__
img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
File "/home/aistudio/facemask1/utils/datasets.py", line 630, in letterbox
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
cv2.error: OpenCV(4.2.0) /io/opencv/modules/core/src/copy.cpp:1421: error: (-215:Assertion failed) top >= 0 && bottom >= 0 && left >= 0 && right >= 0 && _src.dims() <= 2 in function 'copyMakeBorder'
错误原因是数据集有一个图片出现错误，因为验证时第一个图片就没有成功，于是在2007_val.txt中删除了第一个图片的路径，最终成功运行
（5.13更新）感谢评论区学霸 qq_39878661的回答，以下引用原话：
问题根源还是在于该目录下的val.shapes文件没有更新，只是删除验证文件val.txt里第一个路径后，软件自动就会重新计算和更新val.shapes文件了，这个文件包含了验证文件val.txt里的每一个图片的长宽尺寸，格式就是纯文本的，可以直接打开查看
代码是github上ultralytics的yolov3
附上代码作者相关问题的回答连接
下图是提问者的回答，想知道他是怎么回溯这个图片路径的，求大佬评论区告知，感谢！
博主小白一枚，如果有更好的解决方法欢迎评论区交流，感激不尽