amiormu
commented
4 years ago thx! Maybe i had solved this question
I used the following way:
vi /home/tensor/anaconda2/envs/rotated_maskrcnn/lib/python3.6/site-packages/torchvision/datasets/coco.py
and then add this after call PIL:
from PIL import ImageFile ImageFile.LOAD_TRUNCATED_IMAGES = True
I am still running and waiting for bugs. If it runs normally, i will close this issue.
Good luck!
❓ Questions and Help
Hello! Very good job！ However, when I run the code, I can run well at first. But it has a problem after that.
Traceback (most recent call last): File "tools/train_net.py", line 196, in
main()
File "tools/train_net.py", line 189, in main
model = train(cfg, args.local_rank, args.distributed)
File "tools/train_net.py", line 89, in train
arguments,
File "/data/fmy/rotated_maskrcnn-master/maskrcnn_benchmark/engine/trainer.py", line 57, in dotrain
for iteration, (images, targets, ) in enumerate(data_loader, start_iter):
File "/home/tensor/anaconda2/envs/rotated_maskrcnn/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 551, in next
return self._process_next_batch(batch)
File "/home/tensor/anaconda2/envs/rotated_maskrcnn/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 572, in _process_next_batch
OSError: Traceback (most recent call last): File "/home/tensor/anaconda2/envs/rotated_maskrcnn/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in _worker_loop samples = collate_fn([dataset[i] for i in batch_indices]) File "/home/tensor/anaconda2/envs/rotated_maskrcnn/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/tensor/anaconda2/envs/rotated_maskrcnn/lib/python3.6/site-packages/torch/utils/data/dataset.py", line 85, in getitem
return self.datasets[dataset_idx][sample_idx]
File "/data/fmy/rotated_maskrcnn-master/maskrcnn_benchmark/data/datasets/coco.py", line 69, in getitem
img, anno = super(COCODataset, self).getitem(idx)
File "/home/tensor/anaconda2/envs/rotated_maskrcnn/lib/python3.6/site-packages/torchvision/datasets/coco.py", line 117, in getitem
img = Image.open(os.path.join(self.root, path)).convert('RGB')
File "/home/tensor/anaconda2/envs/rotated_maskrcnn/lib/python3.6/site-packages/PIL/Image.py", line 930, in convertvi
self.load()
File "/home/tensor/anaconda2/envs/rotated_maskrcnn/lib/python3.6/site-packages/PIL/ImageFile.py", line 249, in load
"(%d bytes not processed)" % len(b)
OSError: image file is truncated (20 bytes not processed)
I am confused on this error. Can you help me ? Thanks a lot!