xiezheng-cs

SwinIR

SwinIR: Image Restoration Using Swin Transformer (official repository)

DBSN

Unpaired Learning of Deep Image Denoising

Deep-Learning-on-Image-Denoising-An-overview

Deep Learning on Image Denoising: An overview (Neural Networks, 2020)

Denoising-Comparison

SR_Mobile_Quantization

Winner solution of mobile AI (CVPRW 2021).

ACNet

Asymmetric CNN for image super-resolution (IEEE Transactions on Systmes, Man, and Cybernetics: Systems 2021)

aimet

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

ECBSR

Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices, ACM Multimedia 2021

Self-Guided-Network-for-Fast-Image-Denoising

The PyTorch implementation of ICCV 2019 paper SGN

TFace

A trusty face analysis research platform developed by Tencent Youtu Lab

ncnnqat

quantize aware training package for NCNN on pytorch

AugLy

A data augmentations library for audio, image, text, and video.

MetaDistil

Code for ACL 2022 paper "BERT Learns to Teach: Knowledge Distillation with Meta Learning".

sparseml

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

AFA

PyTorch implementation for "Towards Effective Deep Transfer via Attentive Feature Alignment" (NN2021)

MLP-Mixer-pytorch

Unofficial implementation of MLP-Mixer: An all-MLP Architecture for Vision

g-mlp-pytorch

Implementation of gMLP, an all-MLP replacement for Transformers, in Pytorch

res-mlp-pytorch

Implementation of ResMLP, an all MLP solution to image classification, in Pytorch

mlp-mixer-pytorch

An All-MLP solution for Vision, from Google AI

TensorRT

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

ai-deadlines

:alarm_clock: AI conference deadline countdowns

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

mmpretrain

OpenMMLab Pre-training Toolbox and Benchmark

AutoDL

Automated Deep Learning without ANY human intervention. 1'st Solution for AutoDL challenge@NeurIPS.

image-classification-codebase

Image Classification Codebase with PyTorch

imgaug

Image augmentation for machine learning experiments.

yolov5-face

YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)

NN-CUDA-Example

Several simple examples for popular neural network toolkits calling custom CUDA operators.

pytorch-cifar-models

Pretrained models on CIFAR10/100 in PyTorch

RepVGG

RepVGG: Making VGG-style ConvNets Great Again