Open s0966066980 opened 5 months ago
I fixed this problem in a separate branch but I don't know if STAR is adding torch 2 support officially.
https://github.com/ZhenglinZhou/STAR/pull/11/commits/026d90ecb8ce48fd827fd3b11a289cd13d5d96bd
I guess we could just put in this single issue?
Update: Ah this fix was merged into STAR. https://github.com/ZhenglinZhou/STAR/pull/11 It should work now?
我在一個單獨的分支中修復了這個問題,但我不知道 STAR 是否正式添加了 torch 2 支援。
我想我們可以只放入這一期嗎?
更新:啊這個修復已合併到 STAR 中。#11現在應該可以了嗎?
I will later use the torch=1.8 version and replace it with cuda=11.4 because there are too many problems in cuda11.8. Thank you for your help.
Can anyone solve the problem of normal training when pytorch>1.9?