DRNET icon indicating copy to clipboard operation
DRNET copied to clipboard

verified publisher icon ap229997
→

Metadata

PyTorch implementation of the NIPS 2017 paper - Unsupervised Learning of Disentangled Representations from Video

Results 1 DRNET issues
Sort by recently updated
recently updated
newest added

Why the rec_loss returned from function train_main_network() is divided by args.batch_size in main.py?

1. Why the rec_loss returned from function train_main_network() is divided by args.batch_size in main.py? As we know, nn.MSELoss() already returns the mean loss by default. `line 183: return sim_loss.data/args.batch_size, rec_loss.data/args.batch_size`...

Dawn90 avatar Dawn90

← Metadata

47
Stars
11
Forks
Watchers

Owner

verified publisher icon ap229997

Metadata

PyTorch implementation of the NIPS 2017 paper - Unsupervised Learning of Disentangled Representations from Video

Back