larsoncs

106-landmarks-dataset

A dataset for 106 facial landmarks

2D-

Avatars for Zoom, Skype and other video-conferencing apps.

ACE

[ACL-IJCNLP 2021] Automated Concatenation of Embeddings for Structured Prediction

Alibaba-MIT-Speech

Alibaba speech technology

alpr-unconstrained

best car recognition

AR.js

Image tracking, Location Based AR, Marker tracking. All on the Web.

automl

Google Brain AutoML

compressed-model-diff

模型压缩后效果对比工具

dnn-movie-posters

A simple demo / tutorial / experiment / portfolio project for me to better understand the concepts of Machine Learning

xrslam-VR

OpenXRLab Visual-inertial SLAM Toolbox and Benchmark

larsoncs/106-landmarks-dataset

A dataset for 106 facial landmarks

larsoncs/alpr-unconstrained

best car recognition

larsoncs/bigmm2018-code

Code of Paper (No.174): "Real-time Vehicle Detection from UAV Imagery"

larsoncs/caffe-int8-convert-tools

This convert tools is base on TensorRT 2.0 Int8 calibration tools,which use the KL algorithm to find the suitable threshold to quantize the activions from Float32 to Int8(-128 - 127).

larsoncs/DaSiamRPN

Distractor-aware Siamese Networks for Visual Object Tracking (ECCV2018)

larsoncs/Deep-Association-Learning

Code on Paper [BMVC2018]Deep Association Learning for Unsupervised Video Person Re-identification

larsoncs/deep_motion_mag

Tensorflow implementation of Learning-based Video Motion Magnification

larsoncs/Detectron-Cascade-RCNN

Cascade R-CNN in Detectron

larsoncs/Detectron-DA-Faster-RCNN

Domain Adaptive Faster R-CNN in Detectron

larsoncs/Detectron4Competition

Detectron for Detection and Instance Segmentation Competition

larsoncs/EANet-reid

EANet: Enhancing Alignment for Cross-Domain Person Re-identification

larsoncs/Face-Track-Detect-Extract

💎 Detect , track and extract the optimal face in multi-target faces (exclude side face and select the optimal face).

larsoncs/FCHD-Fully-Convolutional-Head-Detector

Code for FCHD - A fast and accurate head detector

larsoncs/Gemfield

Gemfield homework or libgemfield.so

larsoncs/HyperLandmark

基于深度学习人脸标定算法 Open Source Face Landmark

larsoncs/inaSpeechSegmenter

CNN-based audio segmentation toolkit. Allows to detect speech, music and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.

larsoncs/LAB

[CVPR 2018] Look at Boundary: A Boundary-Aware Face Alignment Algorithm

larsoncs/Learning2Ask_TypedDecoder

larsoncs/mobilefacenet-V2

improve the accuracy of mobilefacenet(insight face)

larsoncs/ncnn

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

larsoncs/pascal2coco

This script is used to transform pascal voc format(.xml) to COCO format(.json)

larsoncs/RefineDet

Single-Shot Refinement Neural Network for Object Detection, CVPR, 2018

larsoncs/semantic-segmentation-pytorch

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

larsoncs/Semantic-Segmentation-Suite

Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!

larsoncs/simpledet

A Simple and Versatile Framework for Object Detection and Instance Recognition

larsoncs/SSD-Tensorflow

Single Shot MultiBox Detector in TensorFlow

larsoncs/supervision-by-registration

Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors

larsoncs/VGG_mscocoModel_convertto_pascalvolModel

VGG_mscocoModel_convertto_pascalvolModel

larsoncs/xDeepFM

larsoncs/ZQCNN

一款比mini-caffe更快的Forward库，觉得好用请点星啊，400星公布快速人脸检测模型，500星公布106点landmark，600星公布人头检测模型，700星公布人脸检测套餐（六种pnet,两种rnet随意混合使用满足各种速度/精度要求）