lipeng-gu Goto Github PK

3d-detection-tracking-viewer

3D detection and tracking viewer (visualization) for kitti & waymo dataset

adabound

An optimizer that trains as fast as Adam and as good as SGD.

attention-augmented-conv2d

Implementing Attention Augmented Convolutional Networks using Pytorch

centernet

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

centernet-deep-sort

realtime multiple people tracking (centerNet based person detector + deep sort algorithm with pytorch)

centernet3d

CenterNet3D An Anchor free Object Detector for Autonomous Driving

centernet3d-pytorch

Unofficial PyTorch implementation of the paper: "CenterNet3D: An Anchor free Object Detector for Autonomous Driving"

centertrack

Simultaneous object detection and tracking using center points.

csp

High-level Semantic Feature Detection: A New Perspective for Pedestrian Detection, CVPR, 2019

deep-high-resolution-net.pytorch

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

deep_sort

Simple Online Realtime Tracking with a Deep Association Metric

deepmot

Official implementation of DeepMOT: A Differentiable Framework for Training Multiple Object Trackers.

efficientnet-pytorch

A PyTorch implementation of EfficientNet

fairmot

A simple baseline for one-shot multi-object tracking

fcos_plus

Some improvements (center sample) about FCOS (FCOS: Fully Convolutional One-Stage Object Detection).

hrnet-semantic-segmentation

High-resolution representation learning (HRNets) for Semantic Segmentation

lanedetection_end2end

End-to-end Lane Detection for Self-Driving Cars (ICCV 2019 Workshop)

lipeng-gu.github.io

lookahead.pytorch

lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch

lstr

This is an official repository of End-to-end Lane Shape Prediction with Transformers.

masktrackrcnn

MaskTrackRCNN for video instance segmentation based on mmdetection

mmmot

[ICCV2019] Robust Multi-Modality Multi-Object Tracking

multitarget-tracker

Multiple Object Tracker, Based on Hungarian algorithm + Kalman filter.

octaveconv_pytorch

Pytorch implementation of newly added convolution

octconv

A PyTorch Implementation for Octave Convolution in Drop an Octave

open-reid-tracking

open-reid with PCB, IDE, triplet, ZJU; MOT/MTMCT feature extraction support included

pointenet

pointsee

polylanenet

Repository for the paper entitled "PolyLaneNet: Lane Estimation via Deep Polynomial Regression" (ICPR 2020)

py-motmetrics

:bar_chart: Benchmark multiple object trackers (MOT) in Python