rotorliu

mmdetection

OpenMMLab Detection Toolbox and Benchmark

apollo

An open autonomous driving platform

CenterNet

Codes for our paper "CenterNet: Keypoint Triplets for Object Detection" .

deep-residual-networks

Deep Residual Learning for Image Recognition

DeRPN

Dimension decomposition region proposal network -- a novel region proposal method for more general object detection.

Detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

displaz

A las viewer for geospatial lidar

LAStools

efficient tools for LiDAR processing

mmclassification

OpenMMLab Image Classification Toolbox and Benchmark

netscope

Neural network visualizer

rotorliu/mmclassification

OpenMMLab Image Classification Toolbox and Benchmark

rotorliu/darknet

Windows version of Yolo Convolutional Neural Networks

rotorliu/DeepStream-Yolo

NVIDIA DeepStream SDK 5 configuration for YoloV4 and YoloV3 model

rotorliu/EfficientPS

PyTorch code for training EfficientPS for Panoptic Segmentation https://rl.uni-freiburg.de/research/panoptic

rotorliu/Image-Processing-Techniques

Implementations of Fourier Transform, Laplacian Pyramids, Edge Detection

rotorliu/involution

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

rotorliu/Long-Tailed-Recognition.pytorch

[NeurIPS 2020] This project provides a strong single-stage baseline for Long-Tailed Classification, Detection, and Instance Segmentation (LVIS). It is also a PyTorch implementation of the NeurIPS 2020 paper 'Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect'.

rotorliu/mapextrackt

Pytorch Feature Map Extractor

rotorliu/mmdetection

OpenMMLab Detection Toolbox and Benchmark

rotorliu/mmsegmentation

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

rotorliu/MobileNets-SSD

MobileNet-SSD, MobileNetV2-SSD/SSDLite on VOC, BDD100K Datasets.

rotorliu/nanodet

⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

rotorliu/only_train_once

[ICLR 2023] OTOv2: Automatic, Generic, User-Friendly; [NeurIPS 2021] Only Train Once: A One-Shot Neural Network Training And Pruning Framework

rotorliu/ORB_SLAM3

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

rotorliu/PaDiM-Anomaly-Detection-Localization-master

This is an unofficial implementation of the paper “PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization”.

rotorliu/ParNet

Custom Implementation of Non-Deep Networks

rotorliu/PointTrack

PointTrack (ECCV2020 ORAL): Segment as Points for Efficient Online Multi-Object Tracking and Segmentation

rotorliu/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers

aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

rotorliu/RecoNet

Tensor Low-rank Reconstruction for Semantic Segmentation

rotorliu/rknn-toolkit

rotorliu/sc_depth_pl

Pytorch Lightning Implementation of SC-Depth (V1, V2...) for Unsupervised Monocular Depth Estimation.

rotorliu/SpatialEmbeddings

Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth

rotorliu/TensorRT

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

rotorliu/tkDNN

Deep neural network library and toolkit to do high performace inference on NVIDIA jetson platforms

rotorliu/triton-inference-server

The Triton Inference Server provides a cloud inferencing solution optimized for NVIDIA GPUs.

rotorliu/vcuda-controller

rotorliu/yolact_edge

The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.

rotorliu/Yolo-FastestV2

:zap: Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

rotorliu/Yolo_mark

GUI for marking bounded boxes of objects in images for training neural network Yolo v3 and v2

rotorliu/YOLOP

You Only Look Once for Panopitic Driving Perception.（https://arxiv.org/abs/2108.11250）