freeze CLIP TextEncoder
Ahnsun opened this issue · comments
Hi, the paper pointed out that we should freeze the text encoder of CLIP during training. I wonder how to achieve it and where is the corrresponding code. Thanks!
In my understanding (though I'm not an author), the optimizer selects which parameters to be updated.
https://github.com/isl-org/lang-seg/blob/main/modules/lsegmentation_module.py#L119-L175
Because these lines do not select CLIP parameters (self.net.clip_pretrained), they are frozen.
