narayansundararajan123

> We also have experienced similar issues for some datasets. To the best of my knowledge this is caused by either > > 1. some numerical instabilty of the loss...

> i've managed to solve collapsed black output problem by: > > 1. adding dropouts to residual blocks (on training phase only): > > ``` > def residual_block(x, dim, k=3,...

Thanks so much! Will try and let you know.

> @narayansundararajan123 ok, let's try these quick updates for original code: > > `module.py`, in `decoder()` > > ``` > def residule_block(x, dim, ks=3, s=1, dropout=False, name='res'): > p =...

Thanks. I also noticed beyond 210000 iterations when the model likely goes off, I am also getting RuntimeWarning: invalid value encountered in reduce return umr_maximum(a, axis, None, out, keepdims, initial)...

thanks! changing python to python3 seems to have worked for the previous error. Now am running into AttributeError: module 'tensorflow' has no attribute 'Graph'.

apologize for the silence - got the whole thing working now. thanks!