zzg-tju Goto Github PK

-

acon

Official Repsoitory for "Activate or Not: Learning Customized Activation." [CVPR 2021]

arcnn-pytorch

PyTorch implementation of Deep Convolution Networks for Compression Artifacts Reduction (ICCV 2015)

awesome-super-resolution

Collect super-resolution related papers, data, repositories

basicsr

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, etc. Also support StyleGAN2, DFDNet.

basicvsr_iconvsr_pytorch

Unofficial PyTorch code for BasicVSR

caffe2-tutorial

Caffe2 C++/Python tutorial with full demo

classsr

(CVPR2021) ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic

coding-interview-university

A complete computer science study plan to become a software engineer.

cycleisp

Official repository for "CycleISP: Real Image Restoration via Improved Data Synthesis" (CVPR 2020--Oral)

deep-image-prior

Image restoration with neural networks but without learning.

diversebranchblock

Diverse Branch Block: Building a Convolution as an Inception-like Unit

ed_lib

Implementations of edge (ED, EDColor, EDPF), line (EDLines), circle and low eccentric ellipse (EDCircles) detection algorithms.

egvsr

Efficient & Generic Video Super-Resolution

emvd

Efficient Multi-Stage Video Denoising With Recurrent Spatio-Temporal Fusion. CVPR_2021.

expandnets

Implementation of ExpandNets

facial-lips-expression-recognition

. This is a project of facial(lips) experssinion recognition. Features: four kinds of classification: none, openmouth, pouting, smile Model: 3 conv 3 full-connected layers, train_acc:92.82%, valid_acc:94.30%. Required Environment: Dlib, Pytorch, Anaconda3

fbcnn

Towards Flexible Blind JPEG Artifacts Removal (FBCNN, ICCV 2021)

gfpgan

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

ghostnet

[CVPR2020] GhostNet: More Features from Cheap Operations

gitignore

A collection of useful .gitignore templates

hinet

idphoto_change_background

This program is based on the grabcut algorithm, which can replace the background color in the photo of the document with blue or red. However, the resolution of the original image has a certain impact on the matting effect of the algorithm. It is recommended to use an image with a resolution of about 700 * 550. If the distortion is still serious, you can take a screenshot of the original image to this resolution and try again.

ircnn

Learning Deep CNN Denoiser Prior for Image Restoration (CVPR, 2017) (Matlab)

leetcode-master

LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

lesrcnn

Lightweight Image Super-Resolution with Enhanced CNN (Knowledge-Based Systems,2020)

lfd-a-light-and-fast-detector

LFD is a big update upon LFFD. Generally, LFD is a multi-class object detector characterized by lightweight, low inference latency and superior precision. It is for real-world appilcations.

maffsrn

micronet

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

mmediting

OpenMMLab Image and Video Editing Toolbox