Instructions to use kolkela/simple-cnn-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use kolkela/simple-cnn-classifier with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://kolkela/simple-cnn-classifier") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language: en
|
| 3 |
+
tags:
|
| 4 |
+
- keras
|
| 5 |
+
- computer-vision
|
| 6 |
+
- image-classification
|
| 7 |
+
- cnn
|
| 8 |
license: mit
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
# Simple CNN Classifier
|
| 12 |
+
|
| 13 |
+
## Model Architecture
|
| 14 |
+
- **Data Augmentation:** Random Flip, Rotation, Zoom, Contrast
|
| 15 |
+
- **Conv Blocks:** 32 -> 64 -> 128 filters + MaxPool
|
| 16 |
+
- **Regularization:** Dropout
|
| 17 |
+
- **Head:** GlobalAveragePooling2D -> Dense Layer
|
| 18 |
+
|
| 19 |
+
## How to Load & Use
|
| 20 |
+
```python
|
| 21 |
+
import keras
|
| 22 |
+
|
| 23 |
+
model = keras.saving.load_model("hf://kolkela/simple-cnn-classifier")
|