Closed weiaicunzai closed 1 year ago
@weiaicunzai My suggestion is not to use mixed precision for 3d networks as there can be a performance drop with unknown reasons: https://github.com/pytorch/pytorch/issues/63313. I have also experienced related issues.
@weiaicunzai My suggestion is not to use mixed precision for 3d networks as there can be a performance drop with unknown reasons: pytorch/pytorch#63313. I have also experienced related issues.
Thanks for your reply, Does "3D networks" include 3D Transformers? Or simply 3D CNNs? Thanks.
3D CNNs. Not sure for the 3D transformer case.
3D CNNs. Not sure for the 3D transformer case.
Thanks.
Hi, guys. thanks for your great work. I am new to mmaction2, and I have noticed that FP16 training is not fully supported (e.g. https://github.com/open-mmlab/mmaction2/issues/1993, https://github.com/open-mmlab/mmaction2/issues/1510 , https://github.com/open-mmlab/mmaction2/issues/1769) as other open-mmlab libraries (e.g. mmsegmentation).
So, could you please tell me what is the best practice for me to use FP16 training in my own project ? Thanks in advance.