Open zhouwei5113 opened 2 years ago
Exactly! I think that's the only necessary change. Let me know how it goes :)
I found a default learning rate 3e-3 when using train_finetune.py, which is a suggested learning rate for both image and text encoder, right? @Zasder3
Exactly! I think that's the only necessary change. Let me know how it goes :)
Training on chinese dataset is very difficult to converge...
Bit late to this! An lr that I use frequently is 1e-4
, that or something in that family typically gives good results.
Hopefully future users will be able to benefit from your experiments.
@zhouwei5113 @Zasder3 Hi, maybe you can refer to this repo! https://github.com/OFA-Sys/Chinese-CLIP
How to use clip on chinese dataset? Should I change txt_encoder pretrain model with a chinese version?