deploy: 95c183f

.buildinfo

@@ -0,0 +1,4 @@
+# Sphinx build info version 1
+# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
+config: adac4c8459f20da2a85f5ca9f7ac218e
+tags: 645f666f9bcd5a90fca523b33c5a78b7

_sources/docs_readme.md.txt

@@ -0,0 +1,160 @@
+# Minerva
+
+![GitHub release (latest by date)](https://img.shields.io/github/v/release/Pale-Blue-Dot-97/Minerva?)
+![GitHub](https://img.shields.io/github/license/Pale-Blue-Dot-97/Minerva?)
+![PyPI - Python Version](https://img.shields.io/pypi/pyversions/minerva)
+![GitHub contributors](https://img.shields.io/github/contributors/Pale-Blue-Dot-97/Minerva?)
+[![CodeFactor](https://www.codefactor.io/repository/github/pale-blue-dot-97/minerva/badge)](https://www.codefactor.io/repository/github/pale-blue-dot-97/minerva)
+![tests](https://github.com/Pale-Blue-Dot-97/Minerva/actions/workflows/tests.yml/badge.svg)
+[![Read the Docs](https://img.shields.io/readthedocs/smp?)](https://pale-blue-dot-97.github.io/Minerva/)
+[![Qodana](https://github.com/Pale-Blue-Dot-97/Minerva/actions/workflows/code_quality.yml/badge.svg)](https://github.com/Pale-Blue-Dot-97/Minerva/actions/workflows/code_quality.yml)
+[![CircleCI](https://dl.circleci.com/status-badge/img/gh/Pale-Blue-Dot-97/Minerva/tree/main.svg?style=svg&circle-token=7c738d256a0d8df674b2682daeb2f4b52381ced4)](https://dl.circleci.com/status-badge/redirect/gh/Pale-Blue-Dot-97/Minerva/tree/main)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Coverage Status](https://coveralls.io/repos/github/Pale-Blue-Dot-97/Minerva/badge.svg?t=ZycdOW)](https://coveralls.io/github/Pale-Blue-Dot-97/Minerva)
+[![security: bandit](https://img.shields.io/badge/security-bandit-yellow.svg)](https://github.com/PyCQA/bandit)
+[![pre-commit.ci status](https://results.pre-commit.ci/badge/github/Pale-Blue-Dot-97/Minerva/main.svg)](https://results.pre-commit.ci/latest/github/Pale-Blue-Dot-97/Minerva/main)
+
+<!-- PROJECT LOGO -->
+<br />
+<div align="center">
+  <a href="https://github.com/Pale-Blue-Dot-97/Minerva">
+    <img src="docs/images/Minerva_logo.png" alt="Logo" width="" height="400">
+  </a>
+  <p align="center">
+    <b style="font-size:26px;"> v0.25</b>
+    <br />
+    <a href="https://pale-blue-dot-97.github.io/Minerva/"><strong>Explore the docs »</strong></a>
+    <br />
+    <br />
+    <a href="https://github.com/Pale-Blue-Dot-97/Minerva/issues">Report Bug</a>
+    ·
+    <a href="https://github.com/Pale-Blue-Dot-97/Minerva/issues">Request Feature</a>
+  </p>
+</div>
+
+## About 🔎
+
+Minerva is a package to aid in the building, fitting and testing of neural network models on multi-spectral geo-spatial data.
+
+## Getting Started ▶
+
+If one wishes to use [torchgeo](https://pypi.org/project/torchgeo/), installation on Linux is recommended to handle the
+compilation of the required C-based libraries.
+
+### Installation ⬇
+
+`minerva` is currently not included in any distribution. The recommended install is therefore to install the latest version from `GitHub`.
+
+```shell
+pip install git+https://github.com/Pale-Blue-Dot-97/Minerva.git
+```
+
+<p align="right">(<a href="#top">back to top</a>)</p>
+
+### Requirements 📌
+
+`minerva` now supports the use of [torchgeo](https://torchgeo.readthedocs.io/en/latest/)
+datasets with upcoming support for [torchvision](https://pytorch.org/vision/stable/index.html) datasets.
+
+Required Python modules for `minerva` are stated in the `setup.cfg`.
+
+`minerva` currently only supports `python` 3.8 -- 3.11.
+
+<p align="right">(<a href="#top">back to top</a>)</p>
+
+## Usage 🖥
+
+The core functionality of `minerva` provides the modules to define `models` to fit and test, `loaders` to pre-process,
+load and parse data, and a `Trainer` to handle all aspects of a model fitting. Below is a MWE of creating datasets,
+initialising a Trainer and model, and fitting and testing that model then outputting the results:
+
+### MWE Driver Script 📄
+
+```python
+from minerva.utils import CONFIG  # Module containing various utility functions.
+from minerva.trainer import Trainer  # Class designed to handle fitting of model.
+
+
+# Initialise a Trainer. Also creates the model.
+trainer = Trainer(**CONFIG)
+
+# Run the fitting (train and validation epochs).
+trainer.fit()
+
+# Run the testing epoch and output results.
+trainer.test()
+```
+
+See `scripts\MinervaExp.py` as an example script implementing `minerva`.
+
+### Config Structure ⚙
+
+See `minerva\inbuilt_cfgs\example_config.yml` as an example config file.
+
+### Creating a Manifest for your Dataset 📑
+
+Use `scripts\ManifestMake.py` to construct a manifest to act as a look-up table for a dataset.
+
+<p align="right">(<a href="#top">back to top</a>)</p>
+
+<!-- CONTRIBUTING -->
+## Contributing 🤝
+
+Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are **greatly appreciated**.
+
+If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement".
+Don't forget to give the project a star! Thanks again!
+
+1. Fork the Project
+2. Create your Feature Branch (`git checkout -b feature/AmazingFeature`)
+3. Commit your Changes (`git commit -m 'Add some AmazingFeature'`)
+4. Push to the Branch (`git push origin feature/AmazingFeature`)
+5. Open a Pull Request
+
+<p align="right">(<a href="#top">back to top</a>)</p>
+
+## License 🔏
+
+Minerva is distributed under a [MIT License](https://choosealicense.com/licenses/mit/).
+
+<p align="right">(<a href="#top">back to top</a>)</p>
+
+## Authors ✒
+
+Created by Harry Baker as part of a project towards for a PhD in Computer Science from the
+University of Southampton. Funded by the Ordnance Survey Ltd.
+
+Contributions also provided by:
+
+- [Jo Walsh](https://github.com/metazool)
+- [Navid Rahimi](https://github.com/NavidCOMSC)
+- [Isabel Sargent](https://github.com/PenguinJunk)
+- [Steve Coupland](https://github.com/scoupland-os)
+- [Joe Guyatt](https://github.com/joeguyatt97)
+- [Ben Dickens](https://github.com/BenDickens)
+- [Kitty Varghese](https://github.com/kittyvarghese)
+
+## Acknowledgments 📢
+
+I'd like to acknowledge the invaluable supervision and contributions of [Prof Jonathon Hare](https://github.com/jonhare) and
+[Dr Isabel Sargent](https://github.com/PenguinJunk) towards this work.
+
+The following modules are adapted from open source third-parites:
+| Module | Original Author | License | Link |
+|:-------|:----------------|:--------|:-----|
+| `pytorchtools` | [Noah Golmant](https://github.com/noahgolmant) | MIT | https://github.com/noahgolmant/pytorch-lars/blob/master/lars.py |
+| `optimisers` | [Bjarte Mehus Sunde](https://github.com/Bjarten) | MIT | https://github.com/Bjarten/early-stopping-pytorch |
+
+This repositry also contains two small ``.tiff`` exercpts from the [ChesapeakeCVPR](https://lila.science/datasets/chesapeakelandcover) dataset used for unit testing purposes. Credit for this data goes to:
+
+> Robinson C, Hou L, Malkin K, Soobitsky R, Czawlytko J, Dilkina B, Jojic N.
+Large Scale High-Resolution Land Cover Mapping with Multi-Resolution Data.
+Proceedings of the 2019 Conference on Computer Vision and Pattern Recognition (CVPR 2019)
+
+<p align="right">(<a href="#top">back to top</a>)</p>
+
+## Project Status 🔴🟡🟢
+
+This project is now in release *beta* state. Still expect some bugs and there may be breaking changes in future versions.
+
+<p align="right">(<a href="#top">back to top</a>)</p>

_sources/index.rst.txt

@@ -0,0 +1,39 @@
+.. Minerva documentation master file, created by
+   sphinx-quickstart on Tue Mar 29 18:44:06 2022.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root ``toctree`` directive.
+
+.. include:: readme_link.rst
+
+.. toctree::
+   :maxdepth: 2
+   :hidden:
+   :caption: Source Documentation 📙:
+
+   source/minerva/datasets
+   source/minerva/logger
+   source/minerva/metrics
+   source/minerva/modelio
+   source/minerva/optimisers
+   source/minerva/pytorchtools
+   source/minerva/samplers
+   source/minerva/trainer
+   source/minerva/transforms
+   source/minerva/models/index
+   source/minerva/utils/index
+
+
+.. toctree::
+   :maxdepth: 2
+   :hidden:
+   :caption: Guides and Information 📗:
+
+   source/guides/index
+   source/glossary
+
+Indices and tables 📚
+=====================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

_sources/readme_link.rst.txt

@@ -0,0 +1,2 @@
+.. include:: docs_readme.md
+   :parser: myst_parser.sphinx_

_sources/source/glossary.rst.txt

@@ -0,0 +1,29 @@
+Glossary
+========
+
+.. note::
+    This glossary is very much WIP and incomplete!
+
+.. glossary::
+
+    patch
+    patches
+        A section of land, cut from a larger :term:`tile`.
+
+    tile
+        A large section of planetary surface, often defining a basic unit of a geo-referencing system.
+
+    collapse level
+        A metric of how close outputs from a Siamese model are to collapsing to a trivial solution.
+
+    euclidean distance
+        The Euclidean distance between two vectors.
+
+    MIoU
+        Mean Intersection over Union. Measure of the colloration between predicted and ground truth labels
+        in segmentation masks.
+
+    OHE
+        One-hot-encoding. A method of encoding information in vectors of length ``N`` where ``N`` is the number
+        of possible classes. A label for class ``n`` is represented by a ``1`` placed in the ``n-th`` dimension
+        of the vector, with all other dimensions being ``0``.