Detecting Skin Lesions with YOLOv11 - 47450253

[LonelyNo]

Author: Samuel Bond-Murphy
Student ID: 47450253

Using YOLOv11 to detect skin lesions in the ISIC 2018 dataset.

This pull request implements a solution to problem 3: "Detect lesions within the ISIC 2017/8 data set with YOLOv7 or newer".
This implementation makes use of a pretrained YOLOv11 model, due to its significant improvements in small and obscured object detection to achieve a Precision of 0.965 and Recall of 0.939 on the test dataset with an IOU threshold of 0.8 through further training and tweaks to hyperparameters.

Information on how to import the dataset and run the model can be found in the README.md, in addition to information regarding the model architecture, training and predictions.

Dependencies

• PyTorch 2.5.1+cu124
• Torchvision 0.20.1+cu124
• Ultralytics 8.3.24
• opencv-python 4.10.0.84

[shaivikaaaa]

This is an initial inspection

Difficulty : Normal
Task : 3

1. Recognition Problem:

• code structure is ok
• missing train.py missing
• minimal comments

2. Commit Log:

• Commit message are ok
• Commits are not progressive and done in 2 days

3. Documentation:
   README looks good but

• do not have a section of "Reproducibility" stating how can someone else can reproduce the results and run the model to achieve same results

4. Pull Request

• PR can be better

Feedback:

• PR can be better and more detailed then what you have now
• add a section of "Reproducibility" stating how can someone else can reproduce the results and run the model to achieve same results

[aniketgupta17]

Observational Feedback

Pull Request:
Correctly created the Pull request from Topic Recognition Branch .
The pull request should include a clear description about the file structure .
No previous feedback incorporated .

File Organizing: Well-organized files.

Commit Log:
Commit messages are progressive for the Recognition Problem solved using 4 files .
Commits are not regularly made showing no logical development and completed within 2 days

Documentation:

Code comments and docstrings are included.
Proper GitHub markdown formatting is used, with organized headings, lists, and code blocks.
Should add about Conclusion and future improvements in the ReadMe.

[LonelyNo]

I have implemented the feedback regarding changes to the README,. For changes to the PR itself should I just directly edit the pull request, or should I do it in some other way so there is still evidence of the original PR?

Thanks.

[gayanku]

Marking

Good/OK/Fair Practice (Design/Commenting, TF/Torch Usage)
	Good design and implementation.
	Spacing and comments.
	No Header blocks.	-1
Recognition Problem
	Good solution to problem.
	Driver Script NOT present. No train.py	-1
	File structure present.
	Good Usage & Demo & Visualisation & Data usage.
	Module present.
	Commenting missing. Minimal.	-1
	No Data leakage found. Has Data splits.
	Difficulty : Normal. YOLO (Normal Difficulty)	-5
Commit Log
	Good Meaningful commit messages.
	Some/Adequate Progressive commits. Over 2 days only.	-1
Documentation
	Readme :Acceptable.	-1
	Model/technical explanation :Good.
	Description and Comments :Good.
	Markdown used and PDF submitted. PDF Checked.
Pull Request
	Pull Request has problems: Late submission.	-2
	No Feedback required.
	Request Description is adequate.	-1
TOTAL		-13

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

[LonelyNo]

Marking

Good/OK/Fair Practice (Design/Commenting, TF/Torch Usage)
Good design and implementation.
Spacing and comments.
No Header blocks. -1
Recognition Problem
Good solution to problem.
Driver Script NOT present. No train.py -1
File structure present.
Good Usage & Demo & Visualisation & Data usage.
Module present.
Commenting missing. Minimal. -1
No Data leakage found. Has Data splits.
Difficulty : Normal. YOLO (Normal Difficulty) -5
Commit Log
Good Meaningful commit messages.
Some/Adequate Progressive commits. Over 2 days only. -1
Documentation
Readme :Acceptable. -1
Model/technical explanation :Good.
Description and Comments :Good.
Markdown used and PDF submitted. PDF Checked.
Pull Request
Pull Request has problems: Late submission. -2
No Feedback required.
Request Description is adequate. -1
TOTAL -13
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

Could I please have an explanation about "Driver Script NOT present. No train.py"? train.py exists in the repository.
Also late submission of the pull request was due to an approved extension, was that just a comment or am I being marked down for this?

The changes after were the feedback implementation, I thought that was how that was meant to be done? We have received basically no explanation on how we are meant to do this with several posts on ed regarding this topic with no response.

[shakes76]

Approved extension +2