Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
title: FashionMNISTClassification
|
| 3 |
-
emoji:
|
| 4 |
colorFrom: red
|
| 5 |
colorTo: red
|
| 6 |
sdk: docker
|
|
@@ -12,9 +12,27 @@ short_description: CNN image classifier for Fashion-MNIST, 10 classes
|
|
| 12 |
license: mit
|
| 13 |
---
|
| 14 |
|
| 15 |
-
#
|
| 16 |
|
| 17 |
-
|
|
|
|
| 18 |
|
| 19 |
-
|
| 20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: FashionMNISTClassification
|
| 3 |
+
emoji: 🧥
|
| 4 |
colorFrom: red
|
| 5 |
colorTo: red
|
| 6 |
sdk: docker
|
|
|
|
| 12 |
license: mit
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# 🧥 Fashion-MNIST CNN Classifier (Streamlit)
|
| 16 |
|
| 17 |
+
This Space demonstrates a Convolutional Neural Network (CNN) trained on the **Fashion-MNIST** dataset.
|
| 18 |
+
The model classifies grayscale clothing images into **10 classes** (e.g., T-shirt, Trouser, Sneaker, Bag).
|
| 19 |
|
| 20 |
+
## Model Performance
|
| 21 |
+
- Test Accuracy: **~92%**
|
| 22 |
+
|
| 23 |
+
## How it works
|
| 24 |
+
1. Upload an image (PNG/JPG).
|
| 25 |
+
2. The app converts it to **28×28 grayscale** and normalizes pixel values to **[0, 1]**.
|
| 26 |
+
3. The CNN predicts the class and shows probabilities.
|
| 27 |
+
|
| 28 |
+
> Note: The model was trained on Fashion-MNIST images (small grayscale). Real photos may reduce accuracy.
|
| 29 |
+
|
| 30 |
+
## Files
|
| 31 |
+
- `app.py` → Streamlit application
|
| 32 |
+
- `fashion_mnist_cnn.keras` → trained CNN model (must be in repo root)
|
| 33 |
+
- `requirements.txt` → dependencies
|
| 34 |
+
|
| 35 |
+
## Run locally
|
| 36 |
+
```bash
|
| 37 |
+
pip install -r requirements.txt
|
| 38 |
+
streamlit run app.py
|