ccliangxd Goto Github PK

celebamask-hq

A large-scale face dataset for face parsing, recognition, generation and editing.

contrastive-unpaired-translation

Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)

deblur-gan

Keras implementation of "DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks"

deblurgan

Image Deblurring using Generative Adversarial Networks

deblurgan-pytorch

An easy-to-read implementation of DeblurGAN

deblurgan-tf

Tensorflow implementation of DeblurGAN(Blind Motion Deblurring Using Conditional Adversarial Networks)

deblurganv2

[ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang

django

The Web framework for perfectionists with deadlines.

esc-50

ESC-50: Dataset for Environmental Sound Classification

face-parsing.pytorch

Using modified BiSeNet for face parsing in PyTorch

gitskills

hdtf

the dataset and code for "Flow-guided One-shot Talking Face Generation with a High-resolution Audio-visual Dataset"

hello-algorithm

🙈🙉🙊 本项目包括：1、我写的三十万字图解算法题典 2、100 张 IT 相关超清思维导图 3、100 篇大厂面经汇总 4、各语言编程电子书 100 本 5、English version supported !!! 🚀🚀 国人项目上榜首不易，右上角助力一波！干就对了，奥利给 ！🚀🚀

hello-world

just another repository

learngit

news-duplicated

文本去重算法，研究自推荐系统中新闻的去重，采用了雅虎的Near-duplicates and shingling算法，服务端用c实现，客户端用java实现，利用thrift框架进行通信，为了提高扩展性，去重可以在服务端实现，服务器也提供了计算的接口，方便客户端自己扩展

onlinedetector

Online Object Detection System Based On Deep Learning

pytorch-cyclegan-and-pix2pix

Image-to-Image Translation in PyTorch

pytorch-hed

a reimplementation of Holistically-Nested Edge Detection in PyTorch

stylegan_xl

StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

unpaired-portrait-drawing

Code for Unpaired Portrait Drawing Generation via Asymmetric Cycle Mapping (CVPR 2020)

vision

Datasets, Transforms and Models specific to Computer Vision

white-box-cartoonization

Official tensorflow implementation for CVPR2020 paper “Learning to Cartoonize Using White-box Cartoon Representations”