Topic recognition

[sv-Tjipto]

A Siamese Networking model to classify Alzheimer's disease using ADNI brain data.

Using the train.py to run the program

[nathasha-naranpanawa]

This is an initial inspection, no action is required at this point

Difficulty: Hard

Readme: OK

• sufficient information on algorithm and usage
• no information on data splits, or augmentations
• a loss plot is shown (assuming it's for the training data)
• no discussion on the results

Commit messages: OK

Code:

• good design
• sufficiently commented

Functionality/Performance:

• only performing similarity detection between pairs of images, no classification
• seem to achieve OK accuracy for similarity detection with the siamese

General comments:

• algorithm solves the respective problem only half-way
• you need to have added a classifier that can classify an individual image as AD or NC with their features extracted by the trained siamese network

[shakes76]

Marking

Good Practice (Design/Commenting, TF/Torch Usage)

Adequate design and implementation
Good spacing and comments
Header blocks

Recognition Problem

Solves problem, no single image classifier -3
Driver Script present
File structure present
Shows Usage & Demo & Visualisation & Data usage
Module present
Commenting
No Data leakage, splits unknown -1
Difficulty: Hard

Commit Log

Meaningful commit messages sometimes -1
Progressive commits used

Documentation

ReadMe acceptable, could have more info like discussion -1
Model/technical explanation minimal -1
Good Description and Comments
Markdown used and PDF submitted

Pull Request

Successful Pull Request (Working Algorithm Delivered on Time in Correct Branch)
Feedback required, remove pyc files before I can merge -2
Request Description minimal -1

[shakes76]

Feedback marks possible +2 if the requested changes are made (see above).

[wangzhaomxy]

No feedback attempt and no feedback marks granted.