Wide-Residual-Networks

Wide-Residual-Networks copied to clipboard

BTW, we should use preact (resnet -V2 style), rather than post-act(V1 style).

rederyang

According to the definition of momentum in keras doc, the momentum of BN layers should be 0.9, which is not the default momentum value of BN layer of pytorch (0.1).

rederyang

Have you tried applying time schedule to improve the performance as in the article?

rederyang

In the function `create_wide_residual_network`, ``` x = initial_conv(ip) nb_conv = 4 ``` After the `initial_conv`, why the nb_conv equals 4 rather than 1?

rederyang

both new and old weights don't load

3

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...

jcpeterson

The model is missing the weight decay of 0.0005 described in the paper. This could be the cause of lower model accuracy than expected

tayden