Network pretraining issue

[codingidea]

Deep-SAD-PyTorch/src/DeepSAD.py, line 123

The encoder has different layer names than the network. As a result, the ae_net_dict here is an empty dictionary. One possible revision,
ae_net_dict = {k: v for k, v in ae_net_dict.items() if 'encoder' in k}

[davnn]

I've suggested a pull request to fix this #11