I’m noticing some issues with performance when alternating between training and evaluation. Here is what I’m doing (for a VAE like model):
- Train model for a few epochs
- Test model using
.eval()
underwith torch.nograd()
- Train model some more (resetting
.train()
)
Two observations:
- I’ve noticed the reconstructions can degrade
- The training loss increases (worse) initially than recovers after a few iterations
I’m using the latest stable versions of PyTorch and Pyro.
Are there any special commands to implement this right? Is it an issue that I’m executing this in a Jupyter Notebook?
Thanks for any help.