i am stuck with this problem. I have generated handwritten digit using GANs. And now I want to evaluate how accurate my generated handwritten digits are. Is there any way??
Asked
Active
Viewed 537 times
1 Answers
2
The most common ways to evaluate the network is to either show the visual output as in the original gan paper (http://papers.nips.cc/paper/5423-generative-adversarial-nets) or by showing on how well they do for semi-supervised learning (http://papers.nips.cc/paper/6125-improved-techniques-for-training-gans.pdf). This means using GANs to improve classification performance for the case, where only little data is available .

Thomas Pinetz
- 6,948
- 2
- 27
- 46