Jon Roosevelt

yeah, same thing happened to me as well. In my case, the model collapsed very early on at `16*16 fade in`. ( I used default value for all the hyper-parameters...

@oneHuster you can fix that by changing [line 74 in models/base_model.py](https://github.com/github-pengge/PyTorch-progressive_growing_of_gans/blob/master/models/base_model.py#L74) to the following: ``` vals = torch.mean(vals, dim=1, keepdim=True) ```

Thanks for adding this feature. But I couldn't find documentations on this topic. Posting my LDAP configs here. Hopefully it helps. **Livy config** ```bash # LDAP livy.server.auth.type = ldap livy.server.auth.ldap.url...