Joshua Peterson
Joshua Peterson
Which scores in the table are from your code? Do you have the commands to reproduce them exactly?
Using keras 2.2.0. I tried both the new and old weights in the main 28-8 script, and neither load correctly. `ValueError: Layer #0 (named "conv2d_1" in the current model) was...
The new code only works with the hdf5 dataset. Is it possible to have a more abstract dataloader, and have the option of h5 or raw image files? I was...
Some of the sample images looked washed out. I suspect that the min/max pixel values of the real samples versus the generated ones are different. It fluctuates wildly on every...
Why are the default batch sizes used? The original paper uses 16 for sizes 4x4 to 128x128, which should be faster (overall) than what is currently used.
Any latent_size other than 512 throws an error
also hardcoded to 2 in dataloader
how is this different from https://github.com/titu1994/Wide-Residual-Networks/ exactly? also can you upload your final weights?