OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

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

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step

Deep Learning API and Server in C++14 support for PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE

FeatherCNN is a high performance inference engine for convolutional neural networks.

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Bolt is a deep learning library with high performance and heterogeneous flexibility.

A caffe implementation of MobileNet-YOLO detection network

LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)

TensorRT for Yolov3

A real-time object detection framework of Yolov3/v4 based on caffe

This is a fast caffe implementation of ShuffleNet.

A deep learning based algorithm to detect rotated object, for example, objects in remote sensing images

A REST API for Caffe using Docker and Go

Caffe for Sparse and Low-rank Deep Neural Networks

Minimal runtime core of Caffe, Forward only, GPU support and Memory efficiency.

opencv 4.5+ with dnn module for php 7/8

Implementation for <Large-Margin Softmax Loss for Convolutional Neural Networks> in ICML'16.

Optimized (for size and speed) Caffe lib for iOS and Android with out-of-the-box demo APP.