Topic recognition

[GuanhuaMa]

No description provided.

[wangzhaomxy]

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

File Organizing: Well-organized files.

Problem Solving:

• The algorithm mostly solve the problem. However, a improved Unet 2D is expected in task 3, the model in the code is a simple Unet 2D.
• Accuracy in testing dataset (Dice): 0.85. However, there’s no test evidence provided, and the reported Dice score is very close to the training result.

Model and functions:

• The model is a simple Unet 2D instead of a improved Unet.
• NO data augmentation.
• The train/test split is used correctly. However, a validation set is expected as part of the model selection process to choose the best-performing model on unseen data.

Code design: Good.

Code comment and docstring:

• Good code comments
• Good function docstrings
• Good header block

Difficulty: Normal.

Additional Comments:

• Good commits
• Good ReadMe design and report content. However, as a report, However, as a report, discussion and conclusion section is expected to properly summarize your project.
• The inference results are not reasonable, as both the ground truth and the predicted masks appear blank. You need to carefully select a clearer example to demonstrate your results.

[gayanku]

Marking

Good/OK/Fair Practice (Design/Commenting, TF/Torch Usage)
	Adequate design and implementation.	-1
	Spacing and comments.
	Header blocks. train.py	-0.5
Recognition Problem
	OK solution to problem.	-2
	Driver Script present.
	File structure present.
	Good Usage & Demo & Visualisation & Data usage.
	Module present.
	Commenting missing.	-1
	No Data leakage found.
	Difficulty : Easy. Easy. Unet2D [ model in the code is a simple Unet 2D.]	-10
Commit Log
	Some/Adequate Meaningful commit messages. Some	-1
	Some/Adequate Progressive commits. Majotity on 3 days	-1
Documentation
	Readme :Acceptable. Limited. No test evidance.	-3
	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).
	No Feedback required.
	Request Description is missing.	-2
TOTAL		-23.5

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