guanghan Goto Github PK

3dod_thesis

3D Object Detection for Autonomous Driving in PyTorch, trained on the KITTI dataset.

action-recognition-visual-attention

Action recognition using soft attention based deep recurrent neural networks

algorithms

automl

Enter the AutoML

caffe

Caffe: a fast framework for deep learning. For the most recent version checkout the dev branch. For the latest stable release checkout the master branch.

caldistsoftware

This is the built software of the calibration tool and the distance measurement tool

calibrationtool

This is the Calibration part of the distance measurement tool.

centerhmr

CenterHMR: a bottom-up single-shot method for multi-person 3D mesh recovery from a single image

centermulti

基于CenterNet训练的目标检测&人脸对齐&姿态估计模型

centernet-better

An easy to understand and better performance version of CenterNet

centernet_pro_max

Experiments based on CenterNet (more backbones, TensorRT deployment and mask head)

cpunet

YOLO running on CPU with optimization

danr

Data Augmentation for Object Detection via Differentiable Neural Rendering

darknet

Convolutional Neural Networks

deeplearntoolbox

Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to get you started.

distmeasuretool

This is for the measurement of distances in the wild. Calibration is needed before the measurement.

easypython

Basic re-usable scripts for python

fairmot

A simple baseline for one-shot multi-object tracking

fastext

Efficient Unconstrained Scene Text Detector

gnet-caffe

Caffe for Knowledge-guided Deep Fractal Neural Networks for Human Pose Estimation

gnet-pose

Source code release of the paper: Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation.

hello-world

It is a test for GitHub

hilight

keras-centernet

A Keras implementation of CenterNet with pre-trained model (unofficial)

lighttrack

LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking

loco

This repository contains the source code for the paper Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation

markdown-resume-js

Turn a simple markdown document into a resume in HTML and PDF

mxnet-centernet

Gluon implementation of "Objects as Points", aka "CenterNet"

mydocs

ngp_jax

Implementation of "instant neural graphics primitives (instant ngp)" with JAX