David Marx

imagining usage... ``` import perceptors as pct pct.available_models() # list all models pct.available_models('clip') # pattern match clip_rn50 = pct.Perceptor('clip_rn50') # load a model clip_vit16 = pct.Perceptor('clip_vit16') # load another #...

100%, I already encountered this issue with other CLIP providers too. I tracked down the code snippet in the original openai release that calculates this, but I like the idea...

This is a great idea. I've noticed that there seem to be two "families" of CLIP implementations: codebases based on openai/CLIP, and codebases based on huggingface's CLIP. Rather than changing...

supported languages

image resolution

> multimodal-comparators yeah, it's an improvement > problem of mmc is it's not googleable I guess... you'd think the same would be true for "timm" but they don't seem to...

maybe we could do some sort of riff on "multimodality" in general? Maybe something to do with synaesthesia? (speaking of making it a spelling challenge..) * synesthete * synthesize *...