This is a PyTorch implementation of semantic segmentation models on MIT ADE20K scene parsing dataset. This module differs from the built-in PyTorch BatchNorm as the mean and standard-deviation are reduced across all devices during training. The importance of synchronized batch normalization in object detection has been recently proved with a an extensive analysis in the paper MegDet: A Large Mini-Batch Object Detector, and we empirically find that it is also important for segmentation.
pytorch semantic-segmentation scene-recognition ade20kGluonCV provides implementations of the state-of-the-art (SOTA) deep learning models in computer vision.
deep-learning computer-vision neural-network gluon mxnet machine-learning image-classification object-detection semantic-segmentationLabelme is a graphical image annotation tool inspired by http://labelme.csail.mit.edu. It is written in Python and uses Qt for its graphical interface. Fig 2. VOC dataset example of instance segmentation.
image-annotation computer-vision annotations deep-learning semantic-segmentation instance-segmentation video-annotation classificationA web based labeling tool for creating AI training data sets (2D and 3D). The tool has been developed in the context of autonomous driving research. It supports images (.jpg or .png) and point clouds (.pcd). It is a Meteor app developed with React, Paper.js and three.js. (Optional) You can modify settings.json to customize classes data.
machine-learning semantic-segmentation manual-annotations pointcloud pcd image-labeling labeling-tool image-labeling-tool labeling ai machine_learningMMSegmentation is an open source semantic segmentation toolbox based on PyTorch. It is a part of the OpenMMLab project. The master branch works with PyTorch 1.3+.
pytorch semantic-segmentation pspnet deeplabv3This code has been tested with Python 3.5, Tensorflow 1.11, CUDA 9.0 and cuDNN 7.4.1 on Ubuntu 16.04. Update 03/21/2020, pre-trained models and results are available now. You can download the pre-trained models and results here. Note that, please specify the model path in the main function (e.g., main_S3DIS.py) if you want to use the pre-trained model and have a quick try of our RandLA-Net.
computer-vision semantic-segmentation 3d-vision s3dis semantickitti semantic3d🔥Deep Learning for 3D Point Clouds (IEEE TPAMI, 2020)
semantic-segmentation pointclouds 3d-segmentation instance-segmentation 3d-deep-learning 3d-detection 3d-classification 3d-trackingTry it out at udt.dev, download the desktop app or run on-premise. The Universal Data Tool is a web/desktop app for editing and annotating images, text, audio, documents and to view and edit any data defined in the extensible .udt.json and .udt.csv standard.
machine-learning csv computer-vision deep-learning image-annotation desktop dataset named-entity-recognition classification labeling image-segmentation hacktoberfest semantic-segmentation annotation-tool text-annotation labeling-tool entity-recognition annotate-images image-labeling-tool text-labelingWelcome to PaddleSeg! PaddleSeg is an end-to-end image segmentation development kit developed based on PaddlePaddle, which covers a large number of high-quality segmentation models in different directions such as high-performance and lightweight. With the help of modular design, we provide two application methods: Configuration Drive and API Calling. So one can conveniently complete the entire image segmentation application from training to deployment through configuration calls or API calls. High Performance Model: Based on the high-performance backbone trained by Baidu's self-developed semi-supervised label knowledge distillation scheme (SSLD), combined with the state of the art segmentation technology, we provides 50+ high-quality pre-training models, which are better than other open source implementations.
image-segmentation unet semantic-segmentation pspnet icnet deeplabv3 hrnetby Panqu Wang, Pengfei Chen, Ye Yuan, Ding Liu, Zehua Huang, Xiaodi Hou, and Garrison Cottrell. This repository is for Understanding Convolution for Semantic Segmentation (WACV 2018), which achieved state-of-the-art result on the CityScapes, PASCAL VOC 2012, and Kitti Road benchmark.
semantic-segmentation deep-neural-networks mxnet cityscapes convolution deep-learningPyTorch implementation of Fully Convolutional Networks. See VOC example.
pytorch computer-vision deep-learning semantic-segmentation convolutional-networks fcn fcn8sPoint Cloud Oversegmentation with Graph-Structured Deep Metric Learning https://arxiv.org/pdf/1904.02113. To switch to the stable branch with only SPG, switch to release.
semantic clustering point-cloud pytorch lidar segmentation partition semantic-segmentation large-scale ply-files superpoint-graphsThis project aims at providing an easy-to-use, modifiable reference implementation for real-time semantic segmentation models using PyTorch. PyTorch and Torchvision needs to be installed before running the scripts, PyTorch v1.1 or later is supported.
computer-vision pytorch neural-networks segmentation image-segmentation semantic-segmentation cityscapes scene-understanding semantic-segmentation-models camvid real-time-semantic-segmentation efficient-segmentation-networks lightweight-semantic-segmentation driving-scene-understandingFigure 1: Performance of SegFormer-B0 to SegFormer-B5. SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, and Ping Luo. Technical Report 2021.
transformer semantic-segmentation cityscapes ade20kThis repository contains Keras/Tensorflow code for the "CRF-RNN" semantic image segmentation method, published in the ICCV 2015 paper Conditional Random Fields as Recurrent Neural Networks. This paper was initially described in an arXiv tech report. The online demo of this project won the Best Demo Prize at ICCV 2015. Original Caffe-based code of this project can be found here. Results produced with this Keras/Tensorflow code are almost identical to that with the Caffe-based version. The root directory of the clone will be referred to as crfasrnn_keras hereafter.
image-segmentation semantic-segmentation crf-as-rnn tensorflow keras crfasrnn crfasrnn-keras crfasrnn-tensorflow crf-rnn-tensorflow crf-rnn-kerasInstall ROS by following our reference, or the official ROS website. First, install Kimera-Semantics, see instructions above.
real-time cpu robotics mapping reconstruction voxels depth-image semantic-segmentation rviz 3d-reconstruction rosbag volumetric-reconstruction disparity-imageSemantic SLAM can generate a 3D voxel based semantic map using only a hand held RGB-D camera (e.g. Asus xtion) in real time. We use ORB_SLAM2 as SLAM backend, a CNN (PSPNet) to produce semantic prediction and fuse semantic information into a octomap. Note that our system can also be configured to generate rgb octomap without semantic information. This project is released under a GPLv3 license.
ros slam semantic-segmentation 3d-reconstruction octomap semantic-slamThis project contains the code (Note: The code is test in the environment with python=3.6, cuda=9.0, PyTorch-0.4.1, also support Pytorch-0.4.1+) for: LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation by Yu Wang. Clone this repository.
real-time computer-vision pytorch semantic-segmentation cityscape-dataset lednetThis repo has been deprecated currently and I will not maintain it. Meanwhile, I strongly recommend you can refer to my new repo: TorchSeg, which offers fast, modular reference implementation and easy training of semantic segmentation algorithms in PyTorch. A repository contains some exiting networks and some experimental networks for semantic segmentation.
deep-learning pytorch semantic-segmentation
We have large collection of open source products. Follow the tags from
Tag Cloud >>
Open source products are scattered around the web. Please provide information
about the open source projects you own / you use.
Add Projects.