Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,32 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- mnist
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
pipeline_tag: image-classification
|
8 |
---
|
9 |
+
|
10 |
+
# CNN Model for MNIST Digit Classification
|
11 |
+
|
12 |
+
This repository contains a Convolutional Neural Network (CNN) model trained on the MNIST dataset for digit classification. The model has achieved an accuracy of 99% on the test dataset and is available for use as a TensorFlow model.
|
13 |
+
|
14 |
+
## Model Details
|
15 |
+
- **Architecture**: Convolutional Neural Network (CNN)
|
16 |
+
- **Input Size**: 28x28 pixels with 1 channel (grayscale)
|
17 |
+
- **Data Preprocessing**: The model has been trained on normalized data.
|
18 |
+
- **Accuracy**: 99%
|
19 |
+
|
20 |
+
## Usage
|
21 |
+
You can use this model for digit classification tasks. Below are some code snippets to help you get started:
|
22 |
+
|
23 |
+
```python
|
24 |
+
# Load the model and perform inference
|
25 |
+
import tensorflow as tf
|
26 |
+
model = tf.keras.models.load_model('model.h5')
|
27 |
+
|
28 |
+
# Perform inference
|
29 |
+
predictions = model.predict(image)
|
30 |
+
|
31 |
+
# Get the predicted digit
|
32 |
+
predicted_digit = np.argmax(predictions)
|