Spaces:
Sleeping
Sleeping
docs: update reademe
Browse files
README.md
CHANGED
|
@@ -1 +1,54 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: Mineral Identifier
|
| 3 |
+
emoji: 🪨
|
| 4 |
+
colorFrom: indigo
|
| 5 |
+
colorTo: purple
|
| 6 |
+
sdk: gradio
|
| 7 |
+
sdk_version: 5.29.1
|
| 8 |
+
python_version: 3.11
|
| 9 |
+
app_file: app.py
|
| 10 |
+
fullWidth: true
|
| 11 |
+
header: default
|
| 12 |
+
short_description: Upload a rock image to identify its mineral composition using a trained model.
|
| 13 |
+
tags:
|
| 14 |
+
- geology
|
| 15 |
+
- mineralogy
|
| 16 |
+
- image-classification
|
| 17 |
+
- gradio
|
| 18 |
+
- computer-vision
|
| 19 |
+
datasets:
|
| 20 |
+
- Nech-C/mineralimage5K-98
|
| 21 |
+
pinned: true
|
| 22 |
+
---
|
| 23 |
+
|
| 24 |
+
# 🪨 Mineral Identifier
|
| 25 |
+
|
| 26 |
+
Welcome to the **Mineral Identifier** app! This tool uses a deep learning model to identify the **type of mineral** in a rock image you upload.
|
| 27 |
+
|
| 28 |
+
## 🚀 Features
|
| 29 |
+
|
| 30 |
+
- 🔍 **Image classification** powered by a trained neural network
|
| 31 |
+
- 📸 Upload an image of a mineral sample
|
| 32 |
+
- 💡 Get a **prediction** along with confidence levels
|
| 33 |
+
- 🌐 Built with [Gradio](https://gradio.app/) for fast, accessible user interaction
|
| 34 |
+
|
| 35 |
+
## 🧠 Behind the Model
|
| 36 |
+
|
| 37 |
+
The app is powered by a convolutional neural network trained on a curated dataset of mineral images including:
|
| 38 |
+
- Quartz
|
| 39 |
+
- Calcite
|
| 40 |
+
- Feldspar
|
| 41 |
+
- Mica
|
| 42 |
+
- And more!
|
| 43 |
+
|
| 44 |
+
If you’d like to explore the dataset used:
|
| 45 |
+
- [Dataset on Hugging Face Hub](https://huggingface.co/datasets/Nech-C/mineralimage5K-98)
|
| 46 |
+
|
| 47 |
+
## 🛠️ How to Use
|
| 48 |
+
|
| 49 |
+
1. Choose a photo of your rock/mineral sample.
|
| 50 |
+
2. The app will process the image and output the **predicted mineral type**.
|
| 51 |
+
|
| 52 |
+
## 💬 Feedback
|
| 53 |
+
|
| 54 |
+
If you encounter any issues or have suggestions for improvements, feel free to open an [issue on GitHub](https://github.com/Nech-C/rockognize/issues) or reach out on the [Hugging Face community](https://huggingface.co/spaces/Nech-C/Rock-Identifier).
|