|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- mnist |
|
metrics: |
|
- accuracy |
|
pipeline_tag: image-classification |
|
--- |
|
|
|
# CNN Model for MNIST Digit Classification |
|
|
|
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. |
|
|
|
## Model Details |
|
- **Architecture**: Convolutional Neural Network (CNN) |
|
- **Input Size**: 28x28 pixels with 1 channel (grayscale) |
|
- **Data Preprocessing**: The model has been trained on normalized data. |
|
- **Accuracy**: 99% |
|
|
|
## Usage |
|
You can use this model for digit classification tasks. Below are some code snippets to help you get started: |
|
|
|
```python |
|
# Load the model and perform inference |
|
import tensorflow as tf |
|
model = tf.keras.models.load_model('model.h5') |
|
|
|
# Perform inference |
|
predictions = model.predict(image) |
|
|
|
# Get the predicted digit |
|
predicted_digit = np.argmax(predictions) |
|
|
