Some questions on training downstream face parsing tasks

FacePerceiver / FaRL

FaRL for Facial Representation Learning [Official, CVPR 2022]

https://arxiv.org/abs/2112.03109

MIT License

375 stars 22 forks source link

Some questions on training downstream face parsing tasks #17

Open winner-4 opened 1 year ago

winner-4 commented 1 year ago

Has anyone used the author's pre-trained model to train a downstream task for face parsing? RuntimeError: CUDA error: device-side assert triggered when using multi-GPU training. Has anyone encountered this? Also I want to convert pth model to onnx model, has anyone done it?