Data

Tools

Indexes

Applications

Experiments

Open Source Science

logicseg

(ICCV23 Oral) LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning

https://github.com/lingorx/logicseg

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.6%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

(ICCV23 Oral) LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning

Basic Info
  • Host: GitHub
  • Owner: lingorX
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 2.9 MB
Statistics
  • Stars: 22
  • Watchers: 1
  • Forks: 1
  • Open Issues: 3
  • Releases: 0
Created over 2 years ago · Last pushed about 2 years ago
Metadata Files
Readme Contributing License Code of conduct Citation

README.md

LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning

This repo contains the pytorch version code and configuration files to reproduce logicSeg. It is based on mmsegmentaion.

Usage

Installation

Please refer to get_started.md for installation and dataset preparation.

Requirement

Pytorch >= 1.8.0 & torchvision >= 0.9.0

Inference

```

single-gpu testing

python tools/test.py --eval mIoU

multi-gpu testing

tools/disttest.sh <CONFIGFILE> --eval mIoU

multi-gpu, multi-scale testing

tools/disttest.sh <CONFIGFILE> --aug-test --eval mIoU ```

Training

To train with pre-trained models, run: ```

single-gpu training

python tools/train.py --options model.pretrained= [model.backbone.use_checkpoint=True] [other optional arguments]

multi-gpu training

tools/disttrain.sh <CONFIGFILE> --options model.pretrained= [model.backbone.usecheckpoint=True] [other optional arguments] For example, to train on Mapillary Vistas 2.0 with a `ResNet-101` backbone and 4 gpus, run: tools/disttrain.sh localconfigs/deeplabv3plus/deeplabv3plusr101-d8512x512160kmapillaryv2_hiera.py 4 ```

Citing LogicSeg

BibTeX @inproceedings{li2023logicseg, title={Logicseg: Parsing visual semantics with neural logic learning and reasoning}, author={Li, Liulei and Wang, Wenguan and Yang, Yi}, booktitle=ICCV, year={2023} }

Any comments, please email: liulei.li@student.uts.edu.au.

Owner

  • Name: lingor
  • Login: lingorX
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - name: "MMSegmentation Contributors"
title: "OpenMMLab Semantic Segmentation Toolbox and Benchmark"
date-released: 2020-07-10
url: "https://github.com/open-mmlab/mmsegmentation"
license: Apache-2.0

GitHub Events

Total
  • Watch event: 2
Last Year
  • Watch event: 2