This project creates a Deep Neural Network with 4 hidden layers (1500 nodes each) to train and test against the MNIST Handwritten Digit dataset. The project also uses Convolution Neural Networks with 2 hidden layers against the MNIST dataset Lastly, this project uses Recurrent Neural Networks approach on the same MNIST data
This project uses the Tensorflow Library in Python and uses Deep Neural Networks and Convolution Neural Networks
- Tensorflow 1.0
- Python 2.7
- NVIDIA CUDA GPU (Optional)
To install Tensorflow
pip install tensorflow
To run the code
python deep-net.py
python cnn.py
python rnn.py
- Tensorflow - The Deep Learning Library
- Jahin Majumdar - (https://github.com/jahin07)