main.py can read 8 bit grey picture and report error while train dataset horse2zebra
taichu012 opened this issue · comments
While in source code main.py， below line can't procedure gray picture（8 bit color deep） in horse2zebra dataset(after unzip horse2zebra dataset, I find some picture is gray with 8 bit deep in trainB), and get err.
self.B_input[i] = image_tensor.reshape((batch_size,img_height, img_width, img_layer))
ValueError: cannot reshape array of size 65536 into shape (1,256,256,3)
One workaround way is to remove all gray picture in horse2zebra\trainB hasing 8 bits color depth manually. But its better to let main.py can do it self by some better way. thanks
Yeah, you are correct. There are some grey scale images. We manually removed those images (couple of commands). I will correct the code and update the issue. Thanks for your input.
Corrected the code. Closing the issue.