Visualizer for neural network, deep learning and machine learning models

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Open standard for machine learning interoperability

Set up deep learning environment in a single command line.

YOLOv3 in PyTorch > ONNX > CoreML > iOS

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

YOLOv5 in PyTorch > ONNX > CoreML > iOS

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://nervanasystems.github.io/distiller

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

Deep Learning Visualization Toolkit（『飞桨』深度学习可视化工具 ）

A collection of pre-trained, state-of-the-art models in the ONNX format

Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms

Tengine is a lite, high performance, modular inference engine for embedded device

PyTorch ,ONNX and TensorRT implementation of YOLOv4

nGraph - open source C++ library, compiler and runtime for Deep Learning

Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.

ONNX-TensorRT: TensorRT backend for ONNX

Tensorflow Backend for ONNX

Multi Model Server is a tool for serving neural net models for inference

Translate - a PyTorch Language Library

Convert TensorFlow models to ONNX

Samples and Tools for Windows ML.

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

PyTorch to Keras model convertor

Machine learning framework for both deep learning and traditional algorithms

PyTorch implementation of the YOLO (You Only Look Once) v2

ONNXMLTools enables conversion of models to ONNX

onnx-go gives the ability to import a pre-trained neural network within Go without being linked to a framework or library.

Fast and accurate face landmark detection library using PyTorch; Support 68-point semi-frontal and 39-point profile landmark detection; Support both coordinate-based and heatmap-based inference; Up to 100FPS landmark inference on CPU.