Runtime error when training: Torch grad

Ldhlwh / DFMGAN

[AAAI 2023] Official implementation of "Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation".

https://arxiv.org/abs/2303.02389

Other

83 stars 11 forks source link

Runtime error when training: Torch grad #3

Closed QasimWani closed 1 year ago

QasimWani commented 1 year ago

Describe the bug When I run train.py (stage I), I get the following error: RuntimeError: derivative for aten::grid_sampler_2d_backward is not implemented

This happens in accumulate_gradients.

Thought it was related to nvidia (cuda) but now suspect internal torch issue.

Torch version: 2.0.1
cuda version: cuda_11.8.r11.8
Ubuntu OS
Running 1 GPU A10 on LambdaLabs.
python version: 3.8.10

Thoughts??? Time-sensitive issue 🙏🏼

Ldhlwh commented 1 year ago

Hello @QasimWani ,

Suppose it is due to pytorch (and/or cuda?) version, try setting up an environment following https://github.com/NVlabs/stylegan2-ada-pytorch#requirements