Toke Faurby

Adding COCOB to TF contrib

5

I was just wondering if you will try to add this to the official TF repo?

AlexNet results

1

As I understand it all images in the paper are using the small (not AlexNet) architecture, since the adversarial loss makes the images look much nicer. I was hoping it...

Hi Do you have any training performance of this implementation that you can share? And do you achieve similar performance to the original paper?

How was number of trainable parameters calculated?

5

I have tried to re-implement the architecture described in the paper exactly, just in TensorFlow. But don't get the correct number of trainable parameters. I can't find where this is...

Error in paper? Figure 1

3

I am wondering if there isn't an error in Figure 1. In order to get m=256 in the last conv. layer there must be a skip connection around the last...