grad_norm (line 32) should be before optimizer.step() (line 35)

emited / VariationalRecurrentNeuralNetwork

Pytorch implementation of the Variational Recurrent Neural Network (VRNN).

282 stars 70 forks source link

Open maximilianigl opened 6 years ago

maximilianigl commented 6 years ago

Or am I wrong?

emited commented 6 years ago

You are right again ! Don't hesitate if you want to send in a PR to correct this.

Cheers