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
Repository
Urban Computing Project
Basic Info
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
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
- Repositories: 2
- Profile: https://github.com/Atzetra
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
- tensorflow/tensorflow 2.3.0 build
- Sphinx *
- black *
- jupyter *
- markdown *
- mkdocs *
- mkdocs-material *
- pygments *
- pymdown-extensions *
- keras-nlp >=0.4.0
- keras-tuner >=1.1.0
- packaging *
- pandas *
- tensorflow >=2.8.0