Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

A curated list of resources for Learning with Noisy Labels

This repo consists of collection of papers and repos on the topic of deep learning by noisy labels / label noise.

机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

Torchreid: Deep learning person re-identification in PyTorch.

开源易用的中文离线OCR，识别率媲美大厂，并且提供了易用的web页面及web的接口，方便人类日常工作使用或者其他程序来调用~

Abandoned Object Dataset

👜 Abandoned object detection for visual surveillance

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

Resources for the Udacity/Didi $100k competition

The Udacity open source self-driving car project

Convert between visual object detection datasets

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

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

Visual Object Tagging Tool: An electron app for building end to end Object Detection Models from Images and Videos.

An eyeglass face dataset collected and cleaned for face recognition evaluation, CCBR 2018.

A CLI for Kubeflow.

[CVPR 2018] Look at Boundary: A Boundary-Aware Face Alignment Algorithm

Caffe: a Fast framework for deep learning. Custom version with built-in sparse inputs, segmentation, object detection, class weights, and custom layers

SSH: Single Stage Headless Face Detector

works in real-time with detection and recognition accuracy up to 99.8% for Chinese license plates: 100 ms/plate

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

a small build system with a focus on speed

A slightly cleaner wash list of MS-Celeb-1M

Caffe implementation of FAIR paper "Focal Loss for Dense Object Detection" for SSD.

Configure Caffe in one hour for Windows users.

This repository implements a demo of the networks described in "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper.

Convert MXNet model to Caffe model

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

State-of-the-art 2D and 3D Face Analysis Project