uc-project

Urban Computing Project

https://github.com/atzetra/uc-project

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 (9.3%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Urban Computing Project

Basic Info
  • Host: GitHub
  • Owner: Atzetra
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 1.25 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 2 years ago · Last pushed about 2 years ago
Metadata Files
Readme License Citation

README.md

logo

Implementing Image Segmentation into AutoKeras


Installation

To install the dependencies, run shell conda create --file autokeras.yml pip install -e .

This repo has been developed in a WSL/Ubuntu environment using this dockerimage for cuda compute compatabilities.

Structure

All the files needed for dataset generation of the water dataset are located in ./helpers/datagen.py. This file assumes that you have the Sentinel 2 dataset downloaded and preprocessed.

Use the ./datasets/dataset_processing.ipynb notebook for this. Here we detailed how to download and generate the files needed.

To run the sementation, run ./segmentation.py. I (@Atzetra) got to the point we had to define output shapes and had to choose our own segmentation blocks/architecture to incorporate as detailed in our report. A stacktrace when running /segmentation.py should show you what we mean.

Running ./segmentation.py should be enough to run if all the paths are correct. This script generates the tfds pipeline and preprocesses all data if the steps above for generating the sentinel-2 dataset are followed.

Acknowledgements

I would like to thank the Urban Computing team for offering a very interesting course to be able to follow. As someone of the master's Bio-Pharmaceutical Sciences, it was fun, albeit very challanging, to learn.

  • Enzo

Owner

  • Name: Enzo Sastrokarijo
  • Login: Atzetra
  • Kind: user
  • Company: AEGEE-Leiden

Citation (CITATION.cff)

---
authors:
  - family-names: Sastrokarijo
    given-names: Enzo
    orcid: https://orcid.org/0009-0006-2345-5958
cff-version: 1.2.0
date-released: 2017-12-18T00:00:00.000Z
message: If you use this software, please cite it as below.
title: AutoKeras with Image Segmentation
url: https://github.com/Atzetra/UC-Project
version: 0.9.0

GitHub Events

Total
Last Year

Dependencies

docker/Dockerfile docker
  • tensorflow/tensorflow 2.3.0 build
docs/requirements.txt pypi
  • Sphinx *
  • black *
  • jupyter *
  • markdown *
  • mkdocs *
  • mkdocs-material *
  • pygments *
  • pymdown-extensions *
pyproject.toml pypi
setup.py pypi
  • keras-nlp >=0.4.0
  • keras-tuner >=1.1.0
  • packaging *
  • pandas *
  • tensorflow >=2.8.0