Open momo1986 opened 5 years ago
Facing a similar issue for Weizmann Action Dataset on batch sizes larger than 64
The accepted batch size depends on the dataset and your config. Weizmann Action Dataset has 72 videos and since the drop_last=True in image loader and in video_loader, the max batch size is the dataset length.
To solve the issue, you can duplicate the data to cover your needed batch size (e.g. batch_size = 128, 72*2 > 128). Note that simply setting drop_last=False will not solve your issue.
I solve the problem by edit the file of 'data.py' at line 22. from:' if cache is not None and os.path.exitsis(cache): to :'if (cache is not None) and (os.path.getsize(cache) != 0):'
because: the cache file maybe is a 0 byte files and meanwhile, it can not open to write
I try to use it in Python3.
However, the error is reported:
Here is the code