Is your feature request related to a problem? Please describe.
I want to package up this library in a docker container that doesn't have access to the internet.
The declaration: EdsrModel.from_pretrained('eugenesiow/edsr-base', scale=2) seems to fetch the pt file from huggingface (https://huggingface.co/eugenesiow/edsr-base/resolve/main/pytorch_model_2x.pt) every time it's called.
I'd rather it read that file from local disk.
Describe the solution you'd like
A README example of loading a pretrained model file from local disk.
Is your feature request related to a problem? Please describe. I want to package up this library in a docker container that doesn't have access to the internet. The declaration:
EdsrModel.from_pretrained('eugenesiow/edsr-base', scale=2)seems to fetch the pt file from huggingface (https://huggingface.co/eugenesiow/edsr-base/resolve/main/pytorch_model_2x.pt) every time it's called. I'd rather it read that file from local disk.Describe the solution you'd like A README example of loading a pretrained model file from local disk.
Describe alternatives you've considered N/A
Additional context N/A