-
Notifications
You must be signed in to change notification settings - Fork 41
Image Model #143
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Image Model #143
Conversation
Model file for Image Processing
🔒 Security Scan Results✅ No critical security issues detected. The code has passed all critical security checks. |
🔒 Security Scan Results✅ No critical security issues detected. The code has passed all critical security checks. |
🔒 Security Scan Results✅ No critical security issues detected. The code has passed all critical security checks. |
…imer's Disease Prediction Using A.pdf
🔒 Security Scan Results✅ No critical security issues detected. The code has passed all critical security checks. |
🔒 Security Scan Results✅ No critical security issues detected. The code has passed all critical security checks. |
🔒 Security Scan Results✅ No critical security issues detected. The code has passed all critical security checks. |
🔒 Security Scan Results✅ No critical security issues detected. The code has passed all critical security checks. |
🔒 Security Scan Results✅ No critical security issues detected. The code has passed all critical security checks. |
🔒 Security Scan Results✅ No critical security issues detected. The code has passed all critical security checks. |
🔒 Security Scan Results✅ No critical security issues detected. The code has passed all critical security checks. |
🔒 Security Scan Results✅ No critical security issues detected. The code has passed all critical security checks. |
What are the changes?
This pull request implements a complete deep learning pipeline for classifying Alzheimer's disease stages using MRI images. The core contribution is the development of a Convolutional Neural Network (CNN) model, supported by preprocessing, oversampling, and evaluation logic.
The entire codebase — including model architecture, data processing, visualization, training, and performance analysis — has been written and structured by Om, with Aryan contributing to dataset preparation and reviewing intermediate results.
Who worked on the changes?
Om: Implemented the entire CNN model, image preprocessing, training logic, validation setup, and evaluation (classification report, confusion matrix, and visualizations).
Aryan: Assisted with verifying dataset loading and providing peer review during model testing.
New Components/Features
Full CNN architecture with multiple convolutional layers and dropout for regularization.
SMOTE integration for oversampling to address class imbalance.
Classification report and confusion matrix generation for evaluation.
Model training visualization (loss and accuracy curves).
Grid display of random sample predictions and class counts.
Enhanced Components/Features
Structured image loading and DataFrame creation from folder-based dataset.
Preprocessing pipeline to resize, normalize, and prepare input images.
Stratified train/validation/test split to ensure balanced evaluation.
Early stopping and model checkpointing for robust training.
Other Changes/Fixes
Refactored image sampling code to produce cleaner visual output.
Improved inline documentation and markdown structure across all notebook cells.
Ensured compatibility with Kaggle's file system and directory structure.
Additional Notes
The current version focuses on baseline CNN performance; potential enhancements include experimenting with pre-trained architectures like VGG16 or EfficientNet.
All code components are modular and can be reused across future deep learning experiments or health-related imaging projects.