I aim to build a simple Neural Network from scratch based on PyTorch. The sole objective is to understand the fundamentals of deep learning and to understand the backend implementation of the code.
You need to install a few libraries to execute these codes. The dependencies are mentioned in requirements.txt and environment.yml. Please take a look!
pip install knets
- Clone the repository
git clone https://github.com/khushi-411/knets.git cd knets
- Create a virtual Conda environment:
conda env create -f environment.yml
- Install dependencies:
pip install -r requirements.txt
- Build project:
python -m build --sdist --wheel .
- Install:
pip install .
- Wikipedia’s article on Neural Network.
- The code heavily rely on PyTorch.
- To plot the graph’s I referred Matplotlib.
- The code is highly inspired by Morvan Zhou’s work on simple neural network.
- Good Read: d2l.ai.
- CSV Dataset is taken from MNIST datset.