dmonn/dcgan-oreilly

Notebook for O'Reilly's "Deep Convolutional Generative Adversarial Networks"

dcgan-oreilly's Issues

how to use the trained model to generate new images

Hi Dominic,

Regarding the GAN code, how to use the trained model to generate new images, what kind of modifications have to be made on the code you shared.

Thanks,

final code block runs, no output?

Hiya,

Really appreciate this notebook. I've got a folder of resized images, 64 x 64, that I'm trying to feed through this. Everything seems to go well, final block runs, but then finishes, without output. I suspect maybe this is a function of my original input images somehow?

I got an error when I try to run The CelebA Dataset part.

I have this error when I try to run the CelebA Dataset part: "ValueError: zero-size array to reduction operation minimum which has no identity". It is exactly in "...\numpy\core_methods.py", line 32, in _amin return umr_minimum(a, axis, None, out, keepdims, initial)".

FileNotFoundError: [Errno 2] No such file or directory: './data/img_align_celeba.zip'

Hi, I'm having trouble with the helper function. Basically I copied the code and saved the .py file and manually imported it. However, I get the error mentioned in the title.

What am I doing wrong?

Thanks

How do I change output shape?

I'm very new to tensorflow and I somehow run this model but how do I change the output shape 28x28 to a bigger value?