Skip to content

Conversation

@justintengg
Copy link

checking out the topic-recognition branch within your fork

checking out the topic-recognition branch within your fork
added different .py files according to the task sheet and added a README.md file
renamed the folder from GAN_model_47508042 to GANmodel_47508042
added imports and a rough outline for the encoder and decoder class to modules.py
created a rough readme template to be used at a later time
created a rough template for a vector quantizer.
created a rough template for the VQVAE class
updated the readme from the previous format as i realised i wont have too much considering i only have a couple files, hence i removed the contents part and author since i am the only one doing this project
added classes to dataset.py and train.py (code unfinished)
added on to the dataset and train files. added a utils file to have some helper functions as well
added 2 functions to predict.py
fixed some bugs that was found in the train.py file and module.py file preventing me from training the model
fixed some issues with the utils, modules, dataset and predict.py files. got the code working which is good
commented each file and finished up the readme. double checked the code whether it works and it does so this should be the final edit.
@justintengg
Copy link
Author

should be the final edit

@justintengg justintengg changed the title initial justin teng (47508042) Oct 28, 2025
updated my readme file to meet the marking criterias.
@justintengg
Copy link
Author

updated the readme and should be finalised now

@shaivikaaaa
Copy link
Collaborator

shaivikaaaa commented Nov 23, 2025

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

VQVAE → Hard Difficulty

Category Marks Comments
Algorithm solves the problem 5 1 no early stop, no plots/graph, no image for original Vs reconstructed images, no train/test, validation split mentioned
Implementation functions as intended 3 2 no data augmentation
Good design 1 1
Commenting 1 0.5 minimal commenting
Algorithm above Normal Difficulty 5 5
Algorithm is Hard difficulty 5 5 Hard Difficulty
Section IV : Max mark from 20 14.5

@gayanku
Copy link
Collaborator

gayanku commented Nov 24, 2025

Marking

Good/OK/Fair Practice (Design/Commenting, TF/Torch Usage)
Adequate design and implementation. -1
Spacing and comments.
Header blocks.
Recognition Problem
OK solution to problem. -1
Driver Script present.
File structure present.
Good Usage & Demo & Visualisation & Data usage.
Module present.
Commenting missing. -1
No Data leakage found.
Difficulty : Hard. Hard Difficulty : VQVAE
Commit Log
Good Meaningful commit messages.
Good Progressive commits.
Documentation
Readme :Acceptable. -2
Model/technical explanation :Acceptable. -2
Description and Comments :Good.
Markdown used and PDF submitted.
Pull Request
Successful Pull Request (Working Algorithm Delivered on Time in Correct Branch).
Feedback action require: Feedback marks possible +2 if the requested changes are made. Fix structure, remove cache files, for merge.-2
Request Description is missing. -2
TOTAL-11

Marked as per the due date and changes after which aren't necessarily allowed to contribute to grade for fairness.
Subject to approval from Shakes

olivermccarthy-uq added a commit to olivermccarthy-uq/PatternAnalysis-2025 that referenced this pull request Nov 29, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants