Batch size implementation missing in data loader

[aplusc98]

Although we can pass a batch size argument in the main bicycle-gan.py code In the data_loader.py there is no implementation to fetch the respective batches..rather it always fetches a batch size of 1. Hence leading to this error.

Cannot feed value of shape (1, x) for Tensor u'input_images:0', which has shape '(2, x)'

Whenever a non-default batch is taken.

[xyp8023]

I found the same problem but I got the error saying "Cannot feed value of shape (1, x) for Tensor u'z:0', which has shape '(2, x)' ", which is saying the latent vector was only fetched a batch size of 1. I am not sure if the input images are fetched with batch size of 2 in this case, if they are, maybe the problem is not in the data_loader.py.