Zhuofan Zong

icon company The Chinese University of Hong Kong icon location Hong Kong icon location PhD student at MMLab, CUHK

Results 2 issues of Zhuofan Zong

Does intermediate fine-tuning on IN21K improve downstream performance?

1 comment

For example, Merged-38M MIM pretraining -> IN21K finetuning -> downstream task finetuning

UnboundLocalError: local variable 'param_name_auto' referenced before assignment

The model hash of model "uvr5_weights/2_HP-UVR.pth" is "d41d8cd98f00b204e9800998ecf8427e". It cannot match any option in `uvr5_pack/utils.py`.