Skip to content
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

Improved UNet segmentaion on ISIC 2017 data set #431

Open
wants to merge 10 commits into
base: topic-recognition
Choose a base branch
from

Conversation

msmith-aus
Copy link

@msmith-aus msmith-aus commented Oct 21, 2022

This is my solution to task 1.
The model takes in rgb images of skin moles and segments out the mole using the Improved UNet. When train.py is provided the data locations in the correct format as specified in train.py. Training metrics will be plotted against the training and validation test sets.
I believe there will be a chance to receive feedback which I will gladly accept and act upon.

Michael :)

msmith-aus and others added 10 commits October 20, 2022 20:05
… next thing to do is develop functions to process the data to feed to the model (should have started this assignment a bit earlier hey
…n for disc parameter and then start training.
…ome bugs in modules.py, still working through errors in modules.py.
…ed train.py functionality. Need to do predict.py and make plots+images
… functions in util.py to plot accuracy and loss. Last thing for funcionality is predict.py
@SiyuLiu0329
Copy link
Collaborator

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

  • Code: OK with no obvious error
  • Results: missing test results, results and loss dont look quite right (flat curves). need test results to verify
  • Readme: images are broken on GitHub web
  • Commit Messages: OK but mostly pushed in 2 days
  • Other comments: please do not commit empty files

@shakes76
Copy link
Owner

shakes76 commented Nov 17, 2022

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

Adequate use and implementation (no prediction) -2
Good spacing and comments
Header blocks missing -1

Recognition Problem

Solves problem (no outputs, can't verify working) -3
Driver Script present
File structure present
Shows Usage & Demo & Visualisation & Data usage (no outputs) -2
Module present
Commenting
No Data leakage (no test set) -2
Difficulty: Easy -10

Commit Log

Meaningful commit messages
Progressive commits used (could be spread out more, use more commits) -1

Documentation

ReadMe minimal, broken links, could be more informative -2
Good Description and Comments
Markdown used PDF submitted

Pull Request

Successful Pull Request (Working Algorithm Delivered on Time in Correct Branch)
No Feedback required, not mergeable because not verified as working.
Request Description OK, could be more informative -1

@shakes76 shakes76 added the Unmergeable Cant be merged for history or other reason label Nov 17, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Improved UNet Unmergeable Cant be merged for history or other reason
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants