Metadata-Version: 2.2
Name: image-grouping-tool
Version: 0.1.4
Summary: Python library for analisys and clustering of images
Project-URL: Homepage, https://github.com/mathbarc/image-grouping-tools
Keywords: image,clustering,image analysis
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: numpy>=1.26.4
Requires-Dist: torch>=2.2.2
Requires-Dist: torchvision>=0.17.2
Requires-Dist: scikit-learn>=1.6.1
Requires-Dist: plotly
Requires-Dist: click
Requires-Dist: tqdm
Provides-Extra: dev
Requires-Dist: pylint>=2.10; extra == "dev"
Requires-Dist: black>=23.3.0; extra == "dev"
Provides-Extra: tests
Requires-Dist: pytest>=7.3.1; extra == "tests"
Requires-Dist: pytest-cov>=4.0.0; extra == "tests"
Provides-Extra: docs
Requires-Dist: sphinx>=5.0.1; extra == "docs"
Requires-Dist: sphinx-markdown-builder; extra == "docs"
Requires-Dist: sphinx_rtd_theme>=1.0.0; extra == "docs"

# Image Grouping Tool

The current package contains tools for analysing big sets of images by leveraging CNN models as images descriptors. Currently the package contains a cli tool with the following commands:

```bash
image_grouping compute_features <path_to_image_folders>
```

The command above scans the appointed folder for PNG and JPEG images and generates a .pt file containing the features and image paths.

```bash
image_grouping apply_pca <path_to_features_file>
```

Applies the PCA algorithm for dimension reduction and stores it to a second file.

```bash
image_grouping cluster <path_to_features_file>
```

Clusterizes data and plots results.

for a more detailed list of params it is possible to use the *--help* command with each of these options.
