Datasets, Transforms and Models specific to Computer Vision

Tensors and Dynamic neural networks in Python with strong GPU acceleration

The fundamental package for scientific computing with Python.

Automated CI toolchain to produce precompiled opencv-python, opencv-python-headless, opencv-contrib-python and opencv-contrib-python-headless packages.

TensorFlow code and pre-trained models for BERT

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

CVNets: A library for training computer vision networks

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

A Command Line Parser

Pre-trained Deep Learning models and demos (high quality and extremely fast)

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

A technical report on convolution arithmetic in the context of deep learning

Graphics SIG organizational information

Working draft of the proposed RISC-V V vector extension

TVM for chips base on Xuantie CPU, an open deep learning compiler stack.

An optimized neural network operator library for chips base on Xuantie CPU.