grad_scaler.scale(loss).backward

taichi-dev / taichi-nerfs

Implementations of NeRF variants based on Taichi + PyTorch

Apache License 2.0

734 stars 49 forks source link

grad_scaler.scale(loss).backward #53

Open lixinhaiyk opened 1 year ago

lixinhaiyk commented 1 year ago

https://github.com/taichi-dev/taichi-nerfs/blob/3752d03ad806994ca1aa406313ba0df9fc35d5f3/train.py#L180 hi,thanks for your amazing work,however,when I run the line grad_scaler.scale(loss).backward() ,it stop without any prompt in debug env. In the command line env, it says"./scripts/train_nsvf_lego.sh: line 12: 3368608 Segmentation fault".

Linyou commented 1 year ago

Hi @lixinhaiyk! Could you please share your environment information, such as the version of taichi and GPU? Please note that the current version of taichi-nerfs requires taichi-1.6, so ensure that you have upgraded your taichi.