Science Score: 26.0%

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

  • 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 (6.4%) to scientific vocabulary
Last synced: 11 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: murtazaa-hussainn
  • License: agpl-3.0
  • Language: Python
  • Default Branch: main
  • Size: 587 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 2 years ago · Last pushed over 2 years ago
Metadata Files
Readme Contributing License Citation

README.md

Steps to perform to run this repo: 1. Data is stored in data folder (images and labels) 2. Run the command pip install -r requirements.txt to install all the required libraries 3. Run the python file: data/data-matching.py to check if all the labels are available against all the images 4. Once the above is completed, run the python file: data/label-annotation.py to convert the labels in pascal VOC format 5. Once the above completes its run, run the python file: data-preparation.py, it will divide the dataset into training and testing data 6. Once the above one is completed, the data is now in order and you can customise the config.json file and run train.py to train the model 7. Once the model is trained used the best.pt weights to test the data using val.py script 8. You can also detect the object using images and videos as source using detect.py file

Owner

  • Login: murtazaa-hussainn
  • Kind: user

GitHub Events

Total
Last Year