This is a configurable neural network from scratch. Configurable parameters include the activation layers, number of layers, neurons per layer, type of gradient descent, type of learning rate, number of iterations and loss function.
=> Note : This project was done using python3 in a python venv environment. The OS used was WSL2.
1. Run
pip install -r requirements.txt
to install. Note you must be in the root directory.
1. Navigate to the src directory
cd src/
2. Run the main.py file by typing following command
python3 main.py
3. Fill in your parameter as instructed and press enter. The neural net you created will train using the wisconsin breast cancer dataset.
4. Results will be printed on screen and saved in the /Results
directory in a numpy file format.