Closed xiaobao886 closed 3 years ago
It happens when the script didn't load your dataset correctly. It detected zero images in the dataset and got the error. You probably didn't structure your dataset correctly.
@PeterL1n I have the same problem when running train_refine.py, but there is no problem when running train_base.py with the same dataset. I want to know what kind of dataset requirements train_refine.py has?
@xiaobao886 I have the same problem when running train_refine.py, have you found a solution?
When I execute the train, The following error occurred
Traceback (most recent call last): File "C:/Users/lijunwen/BackgroundMattingV2-master/train_base.py", line 265, in
train()
File "C:/Users/lijunwen/BackgroundMattingV2-master/train_base.py", line 142, in train
for i, ((true_pha, true_fgr), true_bgr) in enumerate(tqdm(dataloader_train)):
File "C:\anaconda\envs\bgmattev2\lib\site-packages\tqdm\std.py", line 1171, in iter
for obj in iterable:
File "C:\anaconda\envs\bgmattev2\lib\site-packages\torch\utils\data\dataloader.py", line 435, in next
data = self._next_data()
File "C:\anaconda\envs\bgmattev2\lib\site-packages\torch\utils\data\dataloader.py", line 475, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "C:\anaconda\envs\bgmattev2\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "C:\anaconda\envs\bgmattev2\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "C:\Users\lijunwen\BackgroundMattingV2-master\dataset\zip.py", line 17, in getitem
x = tuple(d[idx % len(d)] for d in self.datasets)
File "C:\Users\lijunwen\BackgroundMattingV2-master\dataset\zip.py", line 17, in
x = tuple(d[idx % len(d)] for d in self.datasets)
ZeroDivisionError: integer division or modulo by zero
Is this a question of training background image?