How to resume training from latest checkpoint of Headnerf model?

YudongGuo / AD-NeRF

This repository contains a PyTorch implementation of "AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis".

MIT License

1.03k stars 175 forks source link

How to resume training from latest checkpoint of Headnerf model? #86

Open RAJA-PARIKSHAT opened 2 years ago

RAJA-PARIKSHAT commented 2 years ago

I was training headnerf from scratch for 400K iterations, but unfortunately, my server got down, and training stopped. Now I have got a checkpoint at 310K iteration. So how should I resume training from that checkpoint? @YudongGuo

e4s2022 commented 2 years ago

AFAIK, re-execute the training script would resume from the latest checkpoint, see https://github.com/YudongGuo/AD-NeRF/blob/9fdcd7e1352aa74e26baa8e60c862f9fbd7933bf/NeRFs/HeadNeRF/run_nerf.py#L275-L305