Data

Tools

Indexes

Applications

Experiments

Open Source Science

segmentation-with-upsamplers

https://github.com/tiny-smart/segmentation-with-upsamplers

Science Score: 44.0%

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
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (3.5%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: tiny-smart
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 3.73 MB
Statistics
  • Stars: 3
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 3
Created over 2 years ago · Last pushed about 2 years ago
Metadata Files
Readme License Citation

README.md

Semantic segmentation with dynamic upsamplers, based on mmsegmentation

For example, to train UPerNet-R50 with CARAFE in FPN:

shell bash dist_train.sh configs/dynamic_upsampling/upernet_r50_4xb4_carafe-80k_ade20k-512x512.py 4 We find that the performance on ADE20K is unstable and may fluctuate about (-0.5, +0.5) mIoU.

The code of upsampler application on SegFormer (Semantic Segmentation) and DepthFormer (Monocular Depth Estimation) can be found here.

Owner

  • Name: tiny-smart
  • Login: tiny-smart
  • Kind: organization

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: 1
Last Year
  • Watch event: 1