yxgeee / FD-GAN

[NeurIPS-2018] FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification.
https://yxgeee.github.io/projects/fdgan.html
281 stars 80 forks source link

In stage one, does anyone know what is the reason? #10

Closed zhaoshipeng closed 5 years ago

zhaoshipeng commented 5 years ago

Epoch: [0][138/809] Time 31.849 (15.758) Data 30.354 (14.164) Loss 0.702 (0.791) Prec 78.12% (67.82%)
Traceback (most recent call last): File "baseline.py", line 200, in main(parser.parse_args()) File "baseline.py", line 143, in main trainer.train(epoch, train_loader, optimizer, base_lr=args.lr) File "/content/drive/FDGAN/reid/trainers.py", line 28, in train for i, inputs in enumerate(data_loader): File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 322, in next return self._process_next_batch(batch) File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 357, in _process_next_batch raise batch.exc_type(batch.exc_msg) OSError: Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 106, in _worker_loop samples = collate_fn([dataset[i] for i in batch_indices]) File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 106, in samples = collate_fn([dataset[i] for i in batch_indices]) File "/content/drive/FDGAN/reid/utils/data/preprocessor.py", line 46, in getitem return [self._get_single_item(index) for index in indices] File "/content/drive/FDGAN/reid/utils/data/preprocessor.py", line 46, in return [self._get_single_item(index) for index in indices] File "/content/drive/FDGAN/reid/utils/data/preprocessor.py", line 59, in _get_single_item img = Image.open(fpath).convert('RGB') File "/usr/local/lib/python3.6/dist-packages/PIL/Image.py", line 2609, in open fp = builtins.open(filename, "rb") OSError: [Errno 5] Input/output error: '/content/drive/FDGAN/datasets/market1501/images/00000658_02_0001.jpg'

yxgeee commented 5 years ago

Consider about your pytorch version and memory issues.

zhaoshipeng commented 5 years ago

Thinks!

At 2018-11-23 14:29:39, "Yixiao Ge" notifications@github.com wrote:

Consider about your pytorch version and memory issues.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.