GuideWsp

GuideWsp

Geek Repo

Company:TCL Research (WuHan)

Location:Wuhan

Home Page:GuideWsp.github.io

Github PK Tool:Github PK Tool

GuideWsp's starred repositories

YOLOX

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

Language:PythonLicense:Apache-2.0Stargazers:8946Issues:76Issues:1461

lite.ai.toolkit

🛠 A lite C++ toolkit of awesome AI models, support ONNXRuntime, MNN. Contains YOLOv5, YOLOv6, YOLOX, YOLOR, FaceDet, HeadSeg, HeadPose, Matting etc. Engine: ONNXRuntime, MNN.

Language:C++License:GPL-3.0Stargazers:3406Issues:71Issues:249

PINTO_model_zoo

A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.

Language:PythonLicense:MITStargazers:3224Issues:114Issues:319

Awesome-Deblurring

A curated list of resources for Image and Video Deblurring

aimet

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

Language:PythonLicense:NOASSERTIONStargazers:1853Issues:43Issues:1231

MobileNet-Yolo

MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:

Language:CLicense:NOASSERTIONStargazers:1676Issues:35Issues:34

involution

[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

Language:PythonLicense:MITStargazers:1304Issues:15Issues:57

Transformer-in-Vision

Recent Transformer-based CV and related works.

BSRGAN

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021) (PyTorch) - We released the training code!

Language:PythonLicense:Apache-2.0Stargazers:1106Issues:38Issues:43

CoordAttention

Code for our CVPR2021 paper coordinate attention

Language:PythonLicense:MITStargazers:932Issues:9Issues:49

d2go

D2Go is a toolkit for efficient deep learning

Language:PythonLicense:Apache-2.0Stargazers:821Issues:45Issues:144

Adlik

Adlik: Toolkit for Accelerating Deep Learning Inference

Language:C++License:Apache-2.0Stargazers:789Issues:29Issues:180

DenseCL

Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021 Oral.

Language:PythonLicense:GPL-3.0Stargazers:538Issues:7Issues:35

pnnx

PyTorch Neural Network eXchange

Low-Level-Vision-Paper-Record

记录近期的 1) 图像/视频的超分增强等low level vision任务; 2) 图像生成 等任务相关论文, 主要为18年以后的DL based方法.

DASR

[CVPR 2021] Unsupervised Degradation Representation Learning for Blind Super-Resolution

Language:PythonLicense:MITStargazers:376Issues:9Issues:96

ClassSR

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

ECBSR

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

Language:PythonLicense:Apache-2.0Stargazers:317Issues:17Issues:37

DiverseBranchBlock

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

Language:PythonLicense:Apache-2.0Stargazers:307Issues:9Issues:34

RepMLP

RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality (CVPR 2022)

Language:PythonLicense:MITStargazers:291Issues:11Issues:13

Neighbor2Neighbor

Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images

Language:PythonLicense:BSD-3-ClauseStargazers:229Issues:8Issues:19

ddfnet

The official implementation of the CVPR2021 paper: Decoupled Dynamic Filter Networks

Language:PythonLicense:MITStargazers:209Issues:8Issues:35

halonet-pytorch

Implementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones

Language:PythonLicense:MITStargazers:201Issues:7Issues:5

HCFlow

Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)

Language:PythonLicense:Apache-2.0Stargazers:184Issues:11Issues:14

BossNAS

(ICCV 2021) BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search

dcd

official code for dynamic convolution decomposition

Language:PythonLicense:NOASSERTIONStargazers:127Issues:5Issues:9

HDRTVNet

ICCV2021 - A New Journey from SDRTV to HDRTV.

Language:PythonLicense:MITStargazers:117Issues:5Issues:22
Language:PythonLicense:MITStargazers:27Issues:1Issues:3