Adversarial_Autoencoder icon indicating copy to clipboard operation
Adversarial_Autoencoder copied to clipboard

Published 20 hours ago • verified publisher icon Naresh1318

Reproducing quantitative results

Open thadikari opened this issue 7 years ago • 0 comments

Hi Naresh1318,

Thank you very much for the code. I ran your implementation and was able to get the reported results in README.md. However my question is, have you been able to reach an error rate of 1.90 (±0:10)% for MNIST 100 labels (as reported in original paper)? Even after 5000 epochs the lowest I get is somewhat around 5%.

thadikari avatar Mar 12 '18 13:03 thadikari