search

NVlabs / few-shot-vid2vid

Pytorch implementation for few-shot photorealistic video-to-video translation.
Other
1.79k stars 276 forks source link

About train and test #64

Closed deucalionAlpha closed 3 years ago

deucalionAlpha commented 3 years ago

Apparently,The training scale is very large. I adjusted the number of epochs, hoping to train the model to be tested as soon as possible, but the following error was reported during the test.

image

The results of the test are as follows

image

So,how to adjust the training model scale correctly? Or please share a model that can be tested, thank you! !

tcwang0509 commented 3 years ago

This repo is now deprecated. Please refer to the new Imaginaire repo: https://github.com/NVlabs/imaginaire.