This repository contains code and files related to a machine learning model for image classification using the MobileNet architecture. The model is trained on a dataset consisting of five classes: Mass, Nodule, Normal, Pneumonia, and Tuberculosis.
The dataset used for training and testing the model should be organized in the following directory structure:
This is a dataset containing images with a resolution of 224x224 pixels, consisting of 5 different classes. This dataset is used to train and test convolutional neural network models.
The following dependencies are required to run the code:
- TensorFlow
- Keras
- scikit-learn
- seaborn
- numpy
- matplotlib
The repository includes the following files:
Mount Drive and Check GPU: Use the notebook Mount Drive dan Cek GPU Colab.ipynb to mount Google Drive and check if a GPU is available on Google Colab.
Count Files: Use the notebook Hitung File yang Digunakan.ipynb to calculate the number of files in each category within the dataset.
Preprocessing and Setting Layer: Use the notebook Preprocessing dan Setting Layer.ipynb to perform data preprocessing and set up the layers of the MobileNet model.
Train Model: Use the notebook Train Model.ipynb to train the MobileNet model on the dataset. The trained model will be saved as MobileNet_Adam_CLAHE.h5.
Test and Graphs: Use the notebook Test dan Grafik.ipynb to evaluate the trained model on a test dataset and generate classification reports, confusion matrices, and graphs.
Note: Make sure to adjust the file paths in the code according to the location of your dataset.
main