iamZe

MetaPruning

MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning. In ICCV 2019.

WDNet

automatic-watermark-detection

Project for Digital Image Processing

SmallObjectAugmentation

Simple implementation of augmentation for small object detection

copy-paste-aug

Copy-paste augmentation for segmentation and detection tasks

MobileNet-v2-pruning

Try out different pruning-approaches on lightweight Backbones.

Neural-IMage-Assessment

A PyTorch Implementation of Neural IMage Assessment

MixMatch-pytorch

Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"

prepare_detection_dataset

convert dataset to coco/voc format

centerX

This repo is implemented based on detectron2 and centernet

Knowledge-Distillation-Zoo

Pytorch implementation of various Knowledge Distillation (KD) methods.

MEAL-V2

MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.

logohunter

Deep learning tool to find brand logos in everyday pictures

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Yolo-Fastest

:zap: Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+

CenterNet2

Two-stage CenterNet

CenterNet

Object detection, 3D detection, and pose estimation using center point detection:

darknet

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

VLAD

Python implementation of VLAD descriptors

pytorch-mobilenet-v2

A PyTorch implementation of MobileNet V2 architecture and pretrained model.

PyRetri

Open source deep learning based unsupervised image retrieval toolbox built on PyTorch🔥

deep-image-retrieval

End-to-end learning of deep visual representations for image retrieval

Efficient-AI-Backbones

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

Fast-AutoAug-Torch

ISDA-for-Deep-Networks

An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.

SupContrast

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

CTracker

tensorRTIntegrate

TensorRT ONNX Plugin、Inference、Compile

GNMOT

Graph Networks for Multiple Object Tracking

TubeTK

Official implementation of paper: TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model (CVPR 2020 oral)