Spaces:
Sleeping
Sleeping
title: TerraNomaly | |
emoji: π | |
colorFrom: gray | |
colorTo: indigo | |
sdk: gradio | |
sdk_version: 5.9.1 | |
app_file: app.py | |
pinned: false | |
# TerraNomaly | |
This project aims to identify visually interesting satellite images from the EarthView dataset. | |
## How to Use | |
1. **Labeling Tab:** | |
* View satellite images. | |
* Click "Cool" or "Not Cool" to label the image. | |
* Your labeled data will be saved in `labeled_data.json`. | |
2. **Display Tab:** | |
* View new, unlabeled images. | |
* Compare them to a selection of your previously labeled "cool" images. | |
* Click "Refresh" to see a new set of images. | |
## Development | |
This is a basic demo. Future development could include: | |
* Training a machine learning model on the labeled data. | |
* Using the model to predict the "coolness" of new images. | |
* Expanding to other subsets of the EarthView dataset. | |