- Preprocessing data
- Loading data
- Transform data
- Split data
- Building model
- Initialize weights & biases
- Activation function
- Loss function
- Feed forward
- Backpropagation
- Update weights
- Training
-
- Execute (train, validate, test).
-
- Evaluating
- Accuracy: approx 80 - 83%
Clone the repo from Github and pull the project.
git clone https://github.com/hanahh080601/Basic-Deep-Learning-Exercise.git
git checkout hanlhn/multi-layers-nn
git pull
cd hanlhn/hanlhn
poetry install
poetry config virtualenvs.in-project true
poetry update
.
├── hanlhn
│ ├── .venv
│ ├── poetry.lock
│ ├── pyproject.toml
│ ├── README.rst
│ └── hanlhn
│ ├── pycache
│ ├── data
│ │ ├── dataset
│ │ │ ├── test_record.csv
│ │ │ └── train_record.csv
│ │ └── datapipeline.py
│ ├── models
│ │ ├── TwoLayersNN.py
│ │ ├── FCL.py
│ │ └── MultiLayersNN.py
│ ├── tests
│ │ ├── init.py
│ │ └── test_hanlhn.py
│ ├── init.py
│ ├── config.py
│ └── main.py
├── .gitignore
└── README.md
cd hanlhn/hanlhn
python main.py
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Please make sure to update tests as appropriate.
Lê Hoàng Ngọc Hân - Đại học Bách Khoa - Đại học Đà Nẵng (DUT)