xinguanxi

pytorch-ssd

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.

RetinaNet-mxnet

An unofficial implementation of ICCV 2017 RetinaNet (Focal Loss).

torchcv

TorchCV: A PyTorch-Based Framework for Deep Learning in Computer Vision

deep_sort_yolov3

Real-time Multi-person tracker using YOLO v3 and deep_sort with tensorflow

PyramidBox

This repo implements PyramidBox with pytorch

deep_sort

Simple Online Realtime Tracking with a Deep Association Metric

CFENet

Comprehensive Feature Enhancement Module for Single-Shot Object Detector

GaitSet

A flexible, effective and fast cross-view gait recognition network

deep_sort_pytorch

MOT using deepsort and yolov3 with pytorch

CSK

Exploiting the Circulant Structure of Tracking-by-detection with Kernels

dopamine

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

Stabilized-Face-Detection-Bbox

Based on Onet to stabilize Face Detection BoundingBox. Fast, Smooth.

mxnet-101

The code to learn mxnet

FaceKit

[CVPR 2018] Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks

PCN-ncnn

PCN based on ncnn framework.

PCN-opencv

face detector

PocketFlow

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

DeepLearning-500-questions

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

pytorch-classification

Classification with PyTorch.

handong1587.github.io

albumentations

Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

caffe-ssd-mobilenet

包含Caffe-SSD-Mobilenet(DepthwiseConvolution) 和 Caffe-SSD 和 Classification

mAP

mean Average Precision - This code evaluates the performance of your neural net for object recognition.

open_model_zoo

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

openvino

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference

Face-Recognition

Demonstrate Plugin API for TensorRT2.1

vision

Datasets, Transforms and Models specific to Computer Vision

ncnn

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

mmcv

OpenMMLab Computer Vision Foundation

jetson-inference

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