A Machine Learning framework from scratch in Pure Mojo 🔥

The Mojo Programming Language

Structured state space sequence models

Open Neural Network Exchange to C compiler.

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Official PyTorch Implementation of Rank & Sort Loss for Object Detection and Instance Segmentation [ICCV2021]

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

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

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

A PyTorch Implementation of Single Shot Scale-invariant Face Detector.

C++ GPU/CPU API for caffe2

A PyTorch implementation of MobileNet V2 architecture and pretrained model.

Fast parallel CTC.

https://torch.ch