Example of inference with open_clip about open_clip

[mitchellnw]

Thought it might be easier to just re-use OpenAI's interface here https://github.com/openai/CLIP

If you have an open_clip checkpoint saved at the path open_clip_checkpoint_pth you can run the following code to store an OpenAI CLIP compatible checkpoint at clip_checkpoint_pth

import torch
open_clip_cp = torch.load(open_clip_checkpoint_pth)
open_clip_sd = {k[7:]:v for k, v in open_clip_cp['state_dict'].items()}
torch.save(open_clip_sd, clip_checkpoint_pth)

now you can use OpenAI's API

import clip
model = clip.load(clip_checkpoint_pth)

[rom1504]

Could be nice to add that info in the readme

[mitchellnw]

good point will do