seglight

Super fast and real-time semantic segmentation (cpu only) can be use for 1 core cpu

https://github.com/mahdizynali/seglight

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
  • Committers with academic emails
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (10.4%) to scientific vocabulary

Keywords

ai deep-learning image keras-tensorflow machine-learning neural-network object-detection robot robotics segment-anything semantic semantic-segmentation soccer-robots tensorflow
Last synced: 6 months ago · JSON representation ·

Repository

Super fast and real-time semantic segmentation (cpu only) can be use for 1 core cpu

Basic Info
  • Host: GitHub
  • Owner: mahdizynali
  • License: mit
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 305 KB
Statistics
  • Stars: 12
  • Watchers: 1
  • Forks: 2
  • Open Issues: 3
  • Releases: 0
Topics
ai deep-learning image keras-tensorflow machine-learning neural-network object-detection robot robotics segment-anything semantic semantic-segmentation soccer-robots tensorflow
Created almost 2 years ago · Last pushed 6 months ago
Metadata Files
Readme License Citation

README.md

Light Semantic Segmentation

Approch of this project is implementing light weight semantic segmentation model which has the least inference time as possible on cpu that we use on humanoid soccer robots. Also network architecture has been inspired from our last team project.

How to use

first of all you have to prepare suitable semantic dataset as images and labels files in dataset directory like bellow : datase/ |_ seri1: |_ /images/ |_ /labels/ |_ seri2: |_ /images/ |_ /labels/ ... alt text alt text \ Then you have to set your configuration in config file and intiate your semantic color-map.

Notice : if you don't have reach dataset, you would use repeat option in augmentation data_provider file :

train_dataset = train_dataset.repeat(60) repeat dataset 60 times !!

Save Model Hint !

in tensorflow version 2.16.0 and above, keras kernel updates into version 3 and it limit us to save models only in .h5 or .keras format; so as i wanna inference on cpp and cppflow, i need to save as tf format .pb as keras v2 in order to load in cppflow inferencer.\ try to install also keras v2 : pip install tf-keras~=2.16 then in directory of your project set env : export TF_USE_LEGACY_KERAS=1 in main code you would change formats as you wish : model.save("save/path", save_format='tf') # for keras v2 model.save("model.h5") # or may .keras for keras v3 Finally try to run main.py as trainer file to store trained model into that specific folder which you set in main.py.


Star History

Star History Chart


Citation

@software{Mahdi_SegLight_Light_Semantic, author = {Mahdi, Zeinali},{Erfan, Ramezani}, title = {{SegLight (Light Semantic Segmentation For Humanoid Soccer Robots)}}, url = {https://github.com/mahdizynali/SegLight}, version = {1.0} }

Owner

  • Name: Mahdi Zeinali
  • Login: mahdizynali
  • Kind: user
  • Location: Tehran-Qazvin
  • Company: Data2Learn

I'm Nothing right now !!

Citation (CITATION.cff)

cff-version: 1.2.0
message: "I will be glad if you cite this project as below."
authors:
- family-names: "Mahdi"
  given-names: "Zeinali"
- family-names: "Erfan"
  given-names: "Ramezani"
title: "SegLight (Light Semantic Segmentation For Humanoid Soccer Robots)"
version: 1.0
date-released: 04/15/2024
url: "https://github.com/mahdizynali/SegLight"

GitHub Events

Total
  • Issues event: 2
  • Watch event: 3
  • Push event: 7
  • Pull request event: 3
  • Create event: 2
Last Year
  • Issues event: 2
  • Watch event: 3
  • Push event: 7
  • Pull request event: 3
  • Create event: 2

Committers

Last synced: 8 months ago

All Time
  • Total Commits: 73
  • Total Committers: 2
  • Avg Commits per committer: 36.5
  • Development Distribution Score (DDS): 0.068
Past Year
  • Commits: 3
  • Committers: 1
  • Avg Commits per committer: 3.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Mahdi z****y@g****m 68
Erfan Ramezani E****5@g****m 5

Issues and Pull Requests

Last synced: 8 months ago

All Time
  • Total issues: 1
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 1
  • Total pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • Erfan-ram (1)
  • mahdizynali (1)
Pull Request Authors
  • Copilot (2)
Top Labels
Issue Labels
documentation (2) enhancement (1)
Pull Request Labels