Network pretraining issue

lukasruff / Deep-SAD-PyTorch

A PyTorch implementation of Deep SAD, a deep Semi-supervised Anomaly Detection method.

MIT License

338 stars 98 forks source link

Network pretraining issue #9

Open codingidea opened 4 years ago

codingidea commented 4 years ago

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 commented 3 years ago

I've suggested a pull request to fix this https://github.com/lukasruff/Deep-SAD-PyTorch/pull/11