hoeflechner
hoeflechner
Hi, i came across this commit, and i am very interested in using CLIP with photoprism! What ist the status of this project?
I have read the CLA Document and I sign the CLA
@Laughing-q thanks for your feedback. I will try to implement as proposed
i switched to ```load_inference_source()``` but for the convertion to PIL i simply used ```Image.fromarray()``` not sure what the advantages and disadvantages are.
@Burhan-Q I used this approach to load the images but as @Laughing-q pointed out it returns a ndarray. clip requires a pil image. So I used PILs function to convert...
@Burhan-Q Clip returns a function that transforms a pil image into its own torch tensor. @Laughing-q was suggesting to write a function that does thesame with a ndarray. For me...
recheck
@glenn-jocher I think this is already streamlined by @Laughing-q. There is an error with the contributers so the cla check fails...
i ran into thesame issue. but the old sync library: https://github.com/FreeOpcUa/python-opcua works with almost thesame code (except all tha awaits...)
i wrote a minimal service that can provide embeddings for the open_clip models. i will use that until ollama can do it. https://github.com/hoeflechner/oclip