open_clip and onnx_clip
The ONNX-based implementation is a specialized, lightweight alternative to the open-source PyTorch implementation, designed for environments where PyTorch dependencies are undesirable, rather than a direct competitor for all use cases.
About open_clip
mlfoundations/open_clip
An open source implementation of CLIP.
Supports diverse Vision Transformer and ConvNet architectures trained on large-scale datasets (LAION-2B, DataComp-1B) with published scaling laws, achieving competitive zero-shot ImageNet accuracy up to 85.4%. Integrates with PyTorch, Hugging Face model hub, and timm for image encoders, enabling efficient embedding computation via the clip-retrieval library. Offers flexible model loading from local checkpoints or HuggingFace, with pre-trained weights optimized for both inference and fine-tuning workflows.
About onnx_clip
lakeraai/onnx_clip
An ONNX-based implementation of the CLIP model that doesn't depend on torch or torchvision.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work