Intel® Optimization for Chainer*, a Chainer module providing numpy like API and DNN acceleration using MKL-DNN.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Faster generation with text-to-image diffusion models.

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

👾 A library of state-of-the-art pretrained models for Natural Language Processing (NLP)

Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Reference implementations of training benchmarks

Training v0.5 results

Datasets, Transforms and Models specific to Computer Vision

OneDNN Verbose Toolkit

Model Zoo for Intel® Architecture: contains Intel optimizations for running deep learning workloads on Intel® Xeon® Scalable processors

Using https://github.com/facebookresearch/ClassyVision to implement Resnext3d