Use ffmpeg and NVCodec to hardware decode video or video stream. in DNN inference system

FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

Base on retinaface and centerface modefied. frame work depend on pytorch.

Object detection, 3D detection, and pose estimation using center point detection:

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

Google Brain AutoML

ONNX-TensorRT: TensorRT backend for ONNX

DBFace is a real-time, single-stage detector for face detection, with faster speed and higher accuracy

wider face验证集的测评代码

Safety helmet wearing detect dataset, with pretrained model

在Windows上的 ONNX 转 TensorRT 解决方案

light weight C++ httpserver and httpclient based on mongoose, also support websocket

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

A PyTorch implementation of EfficientNet

Reference models and tools for Cloud TPUs.

CC for Caffe，基于Caffe改造的深度学习框架，为Caffe添加基于C++的网络构建、友好的Train和Inference框架

Latex code for making neural networks diagrams

Visualizer for neural network, deep learning and machine learning models

ResNet-20/32/44/56/110 on CIFAR-10 with Caffe

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

Video Object Segmentation with Re-identification

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

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Hybrid CPU/GPU implementation of the A3C algorithm for deep reinforcement learning.

Caffe models in TensorFlow

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, …

Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.