This project focuses on Alzheimer detection using deep learning techniques. The provided CLI (Command-Line Interface) allows you to train, test, and perform model testing with ease.
python main.py train --train_data_path <train_data_path> --Epochs <num_epochs> --model <model_name> --test_data_path <test_data_path> [--val_exp] [--val_data_path <val_data_path>] [--biased]
--train_data_path
: Path to the training data.--Epochs
: Number of training epochs.--model
: Specify the model architecture.--test_data_path
: Path to the test data.
- Ensure that the provided data paths exist.
- Use
--val_exp
to indicate the use of explicit validation data. - If
--val_exp
is provided, include--val_data_path
with the validation data path.
- Include
--biased
if the data is imbalanced.
python main.py train --train_data_path data/train_data --Epochs 50 --model CNN_model --test_data_path data/test_data --val_exp --val_data_path data/val_data --biased
python main.py test --model <model_name> --test_data_path <test_data_path> --model_path <model_path>
--model
: Specify the model architecture.--test_data_path
: Path to the test data.--model_path
: Path to the saved model.
python main.py test --model CNN_model --test_data_path data/test_data --model_path saved_models/CNN_model_epoch_50.h5
python main.py model_testing --model <model_name> --test_data_path <test_data_path> --model_path <model_path>
--model
: Specify the model architecture.--test_data_path
: Path to the test data.--model_path
: Path to the saved model.
python main.py model_testing --model CNN_model --test_data_path data/test_data --model_path saved_models/CNN_model_epoch_50.h5