Spaces:
Sleeping
Sleeping
| title: Galaxy Segmentor | |
| emoji: ⚡ | |
| colorFrom: indigo | |
| colorTo: gray | |
| sdk: gradio | |
| sdk_version: 6.5.1 | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| short_description: Automatically segment galaxies into spiral and bar masks | |
| arxiv: "2309.02380" | |
| ### Galaxy Segmentor | |
| A minimalist `gradio` interface for a UNet model trained to segment galaxy images into probability masks highlighting spiral arms and galaxy bars. | |
| This is the same model used in [my paper](https://arxiv.org/abs/2309.02380) "A morphological segmentation approach to determining bar lengths", albeit converted from the original TensorFlow to ONNX. | |
| The model was trained using data from the citizen science project [Galaxy Zoo 3D](https://www.zooniverse.org/projects/klmasters/galaxy-zoo-3d/about/results). |