Repository Issue Activity (beta)

#516 url to weights listed in clip.py is not available.

#531 Question: Best way to structure multi-label image dataset for custom PPE classification?

#520 Please publish an official build to pypi

#542 i want to create one lens which can i find the SKU thraw the image anyone can find the SKU

#518 setuptools.build_meta error. Cannot install OpenAI CLIP on Windows 10 with PyTorch 2.1.2+cu121

#486 image-text pairs

#532 CLIP compilation problem

#528 Build fails with setuptools 81+ due to pkg_resources removal

#351 does it has c++ version for tokenizer?

#526 Difference between CLIP and OmiCLIP foundation model

#50 YFCC-100M text filtering

#323 Getting overfitted CLIP model while fine-tuning with a large training dataset

#517 modify clip to signal and text multimodal

#199 How to download ViT-L/14 and ViT-L/14@336px? Thank you so much!

#496 Getting error when opening notebooks

#514 Unable to open any of notebooks

#83 CLIP Training Code

#48 Two questions regarding model implementation:

#488 attention mask

#508 I have slight differences between obtaining features on the server and on the local machine.

#515 aaassss

#502 Recall (R@k) way lower than the one obtained in papers

#513 风场取证数据

#512 1

#511 Can I search images in Chinese? I used the following code to extract image features