https://github.com/sam783/lenet-mnist
Implementation of LeNet-5 CNN for MNIST Handwritten Digit Recognition
https://github.com/sam783/lenet-mnist
deep-learning handwritten-digit-recognition keras-tensorflow lenet-5 lenet-mnist machine-learning mnist neural-networks python3
Last synced: about 1 month ago
JSON representation
Implementation of LeNet-5 CNN for MNIST Handwritten Digit Recognition
- Host: GitHub
- URL: https://github.com/sam783/lenet-mnist
- Owner: Sam783
- Created: 2025-02-01T15:47:34.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-01T17:20:50.000Z (over 1 year ago)
- Last Synced: 2025-02-01T17:28:11.017Z (over 1 year ago)
- Topics: deep-learning, handwritten-digit-recognition, keras-tensorflow, lenet-5, lenet-mnist, machine-learning, mnist, neural-networks, python3
- Language: Jupyter Notebook
- Homepage:
- Size: 2.09 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Dataset
The MNIST dataset consists of 60,000 training images and 10,000 test images of handwritten digits (0-9). Each image is 28x28 pixels in grayscale.
# Model Architecture (LeNet-5)
- **Input Layer**: 28×28 grayscale images
- **Conv Layer 1**: 32 filters (5×5), ReLU activation
- **MaxPooling Layer 1**: 2×2 pooling
- **Conv Layer 2**: 64 filters (5×5), ReLU activation
- **MaxPooling Layer 2**: 2×2 pooling
- **Flatten Layer**
- **Fully Connected Layer 1**: 120 neurons, ReLU activation
- **Fully Connected Layer 2**: 84 neurons, ReLU activation
- **Output Layer**: 10 neurons (Softmax for classification)
# Features
- Implemented LeNet-5 architecture using TensorFlow/Keras
- Trained on the MNIST dataset (28×28 grayscale images)
- Utilizes CNNs for feature extraction and classification
- Evaluates model performance using accuracy metrics
- Developed a user-friendly interface using Streamlit for real-time digit recognition
# Getting Started
1. Clone the repository:
```bash
https://github.com/Sam783/LeNet-MNIST.git
2. Navigate to the project directory:
```bash
cd LeNet-MNIST
3. Install the required dependencies:
```bash
pip install -r requirements.txt
4. Run the Streamlit app:
```bash
streamlit run app.py