Hi-Yan

acuity-dataset

Acuity Dataset scripts and examples

adversarial

Code and hyperparameters for the paper "Generative Adversarial Networks"

CameraSR

Camera Lens Super-Resolution in CVPR 2019

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

OpenVINO-model-server

Inference model server implementation with Intel performance optimizations and TensorFlow Serving API

PocketFlow

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

spacy-models

💫 Models for the spaCy Natural Language Processing (NLP) library

tensorflow

An Open Source Machine Learning Framework for Everyone

tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

Hi-Yan/awesome-AutoML-and-Lightweight-Models

A list of high-quality (newest) AutoML works and lightweight models including 1.) Neural Architecture Search, 2.) Lightweight Structures, 3.) Model Compression, Quantization and Acceleration, 4.) Hyperparameter Optimization, 5.) Automated Feature Engineering.

Hi-Yan/Awesome-Knowledge-Distillation

Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2020)。

Hi-Yan/AWNet-Attentive-Wavelet-Network-for-Image-ISP

Runner-Up solution in AIM 2020 Learned Image ISP challenge (ECCVW 2020)

Hi-Yan/BackgroundMattingV2

Real-Time High-Resolution Background Matting

Hi-Yan/boostBM3D_betterPatchMatching

% This is an implementation of a boosted BM3D in our WACV 2019 paper: "Good Similar Patches for Image Denoising."

Hi-Yan/cineform-sdk

The GoPro® CineForm video codec SDK.

Hi-Yan/CnC_Remastered_Collection

Hi-Yan/computervision-recipes

Best Practices, code samples, and documentation for Computer Vision.

Hi-Yan/davs2

An open-source decoder of AVS2-P2/IEEE1857.4 video coding standard

Hi-Yan/DeepLearning-500-questions

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

Hi-Yan/dl_accelerator

Deep Learning Accelerator Based on Eyeriss V2 Architecture with custom RISC-V extended instructions

Hi-Yan/FairNAS

FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search

Hi-Yan/FALSR

Fast, Accurate and Lightweight Super-Resolution models

Hi-Yan/fritz-models

Train and deploy machine learning models for mobile apps with Fritz AI.

Hi-Yan/ImageStackAlignator

Implementation of Google's Handheld Multi-Frame Super-Resolution algorithm (from Pixel 3 and Pixel 4 camera)

Hi-Yan/ImageTools

这是一款图像相关的工具软件，扩展性好。目前集成有镜头计算器、抖动测试工具、看图工具、RAW图编辑（ISP算法的实现）、PQtools直接生成代码、多视频对比等功能。可以方便的进行后期算法的验证

Hi-Yan/IMDN

Lightweight Image Super-Resolution with Information Multi-distillation Network (ACM MM 2019)

Hi-Yan/ISP-based-on-responses-prediction-model

Study on Methodology and Technology of Digital Camera Image signal Processing Based on Raw Responses Prediction Model

Hi-Yan/kvazaar

An open-source HEVC encoder

Hi-Yan/letsGAN

The 1st National Aritificial Intelligence Chanllenge. Our team LetsGAN

Hi-Yan/libonnx

A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

Hi-Yan/LibRaw

LibRaw is a library for reading RAW files from digital cameras

Hi-Yan/lyhue1991.github.io

Hi-Yan/mmsr

Open MMLab Image and Video Super-Resolution Toolbox, , including SRResNet, SRGAN, ESRGAN, EDVR, etc.

Hi-Yan/model-compression-1

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 structure；4、batch-normalization folding for binary value of feature(A))

Hi-Yan/nnom

A higher-level Neural Network library for microcontrollers.

Hi-Yan/openHEVC

HEVC decoder

Hi-Yan/SVT-HEVC

SVT HEVC encoder. Scalable Video Technology (SVT) is a software-based video coding technology that is highly optimized for Intel® Xeon® processors. Using the open source SVT-HEVC encoder, it is possible to spread video encoding processing across multiple Intel® Xeon® processors to achieve a real advantage of processing efficiency.

Hi-Yan/vmaf

Perceptual video quality assessment based on multi-method fusion.

Hi-Yan/x266

Hardware implement of HEVC/WC