carpedm20 / carpedm20/DCGAN-tensorflow

Best way of using the discriminator for predicting labels

Open
#240 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
JavaScript
Stars
7.2k
Forks
2.6k
PR merge metrics
No merged PRs in 30d

Description

As discussed here (https://github.com/carpedm20/DCGAN-tensorflow/issues/132) the discriminator requires y to be concat to both input and h0 layer.

If one was to use a trained discriminator to generate test labels, how would you go about doing this?

It might be worthwhile adding this functionality to the MNIST example

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.