project/
│
├── src/ # Source files
│ ├── models/ # each one's folder
│
├── data/ # CSV files
│
├── notebooks/ # Jupyter notebooks
|
├── tensorboard/ # TensorBoard
|
├── checkpoints/ # Checkpoints
│
├── .gitignore # Specifies intentionally untracked files to ignore
│
├── README.md # Project overview and setup instructions
│
└── requirements.txt # The dependencies file
- Put the csv files under the "data" folder.
- In the training data, we use the first 80% as the training set, and last 20% as the validation set.
pip install -r requirements.txtUncomment or add train_pipeline in train.py, then
cd ./src
python train.pyModels will be saved in the "checkpoints" folder.
cd ./src
python bagging.pyAn "output.csv" will be generated under the "data" folder.