LyraWang
commented
4 years ago the problem is caused by missing the regroup step while using the REDS_trainval_keys.pkl which is proposed by the author
Closed LyraWang closed 4 years ago
LyraWang
commented
4 years ago the problem is caused by missing the regroup step while using the REDS_trainval_keys.pkl which is proposed by the author
Traceback (most recent call last): File "train.py", line 196, in
main()
File "train.py", line 153, in main
for _, train_data in enumerate(train_loader):
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 582, in next
return self._process_next_batch(batch)
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 608, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
AttributeError: Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/_utils/worker.py", line 99, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/_utils/worker.py", line 99, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/xxx/EDVR-master/codes/data/REDS_dataset.py", line 155, in getitem
img_GT = util.read_img(self.GT_env, key, (3, 720, 1280))
File "/home/xxx/EDVR-master/codes/data/util.py", line 77, in read_img
img = _read_img_lmdb(env, path, size)
File "/home/xxx/EDVR-master/codes/data/util.py", line 62, in _read_img_lmdb
img_flat = np.frombuffer(buf, dtype=np.uint8)
AttributeError: 'NoneType' object has no attribute 'buffer'
I used the train_sharp_wval.lmdb as dataroot_GT and the train_sharp_bicubic_wval.lmdb as dataroot_LQ and in the fucntion '_read_img_lmdb', the images read from lmdb were saved, and I found some of them are broken--maybe half of its pixels are black, and some are ok
how can I solve this problem?