This is the official Pytorch implementation for our paper "Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement."

Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.

人像卡通化探索项目 (photo-to-cartoon translation project)

quantize aware training package for NCNN on pytorch

Includes: Learning data augmentation strategies for object detection | GridMask data augmentation | Augmentation for small object detection in Numpy. Use RetinaNet with ResNet-18 to test these meth…

EasyQuant(EQ) is an efficient and simple post-training quantization method via effectively optimizing the scales of weights and activations.

Try out different pruning-approaches on lightweight Backbones.

model compression based on pytorch (1、quantization: 8/4/2bits(dorefa)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular and group convolutional channel pruning；3、 group convolution …

身份证图片生成工具 generate an id card picture

提供对YOLOv3及Tiny的多种剪枝版本，以适应不同的需求。

工程与学术笔记

This page is for the SlimYOLOv3: Narrower, Faster and Better for UAV Real-Time Applications

Improve yolo with latest paper

Context-driven data augmentation for Object Detection (ECCV'18)

基于深度学习106点人脸标定算法 Open Source Face Landmark

Repository for experiments on MSCOCO for Unsupervised Hard Example Mining from Videos for Improved Object Detection(https://arxiv.org/abs/1808.04285)

CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras

LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)

Learn OpenCV : C++ and Python Examples

能够在移动端使用的关键词语音识别，其实用的是分类方法来完成的

An End-to-End Architecture for Keyword Spotting and Voice Activity Detection