You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
You can safely ignore the downloaded weights because the they are only used in the model initialization and you reload your own weights using load_state_dict.
If you do not want to download original weights, simply use pyiqa.create_metric('musiq-ava', pretrained=False).
Hi, if i want load weight by path
i load weight from https://github.com/chaofengc/IQA-PyTorch/releases/tag/v0.1-weights
but still the model is downloaded from the link
i wanna load weight from own path
u hardcode path url in model for example
https://github.com/chaofengc/IQA-PyTorch/blob/main/pyiqa/archs/clip_model.py#L15
The text was updated successfully, but these errors were encountered: