Skip to content

The project focuses on classifying brain tumors using the Multi-Modal Squeeze and Excitation Network.

Notifications You must be signed in to change notification settings

Afrid1045/Brain-Tumor-Severity-Prediction-using-Multi-Modal-Squeeze-and-Excitation-Network

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 

Repository files navigation

Brain-Tumor-Severity-Prediction-using-Multi-Modal-Squeeze-and-Excitation-Network

Project Overview: The project focuses on classifying brain tumors using the Multi-Modal Squeeze and Excitation Network.

Modalities and Pretrained Models: Two modalities are employed, utilizing pre-trained models: InceptionV2 and Xception net.

Hardware Requirements: The project requires GPU acceleration, and the Kaggle accelerator was utilized for its computational capabilities.

Dataset Source: The dataset is sourced from the public repository Figshare dataset.

Execution Environment: To run the code effectively, it's recommended to use the Kaggle platform, particularly with GPU support, as the model size exceeds the capacity of local CPUs.

Accessing the Dataset: The dataset is available on Kaggle, allowing users to easily access and run the code directly on the Kaggle platform.