Improved UNet segmentaion on ISIC 2017 data set by msmith-aus · Pull Request #431 · shakes76/PatternFlow

msmith-aus · 2022-10-21T07:48:30Z

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 :)

… 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.

…me to train and make some nice plots

…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

…d all files

SiyuLiu0329 · 2022-11-14T03:36:52Z

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 · 2022-11-17T13:54:31Z

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

msmith-aus · 2022-10-21T07:48:30Z

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 :)

… 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.

…me to train and make some nice plots

…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

…d all files

SiyuLiu0329 · 2022-11-14T03:36:52Z

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 · 2022-11-17T13:54:31Z

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

msmith-aus · 2022-10-21T07:48:30Z

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 :)

… 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.

…me to train and make some nice plots

…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

…d all files

SiyuLiu0329 · 2022-11-14T03:36:52Z

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 · 2022-11-17T13:54:31Z

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

msmith-aus · 2022-10-21T07:48:30Z

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 :)

… 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.

…me to train and make some nice plots

…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

…d all files

SiyuLiu0329 · 2022-11-14T03:36:52Z

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 · 2022-11-17T13:54:31Z

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

msmith-aus · 2022-10-21T07:48:30Z

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 :)

… 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.

…me to train and make some nice plots

…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

…d all files

SiyuLiu0329 · 2022-11-14T03:36:52Z

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 · 2022-11-17T13:54:31Z

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

msmith-aus · 2022-10-21T07:48:30Z

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 :)

… 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.

…me to train and make some nice plots

…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

…d all files

SiyuLiu0329 · 2022-11-14T03:36:52Z

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 · 2022-11-17T13:54:31Z

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

msmith-aus · 2022-10-21T07:48:30Z

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 :)

… 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.

…me to train and make some nice plots

…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

…d all files

SiyuLiu0329 · 2022-11-14T03:36:52Z

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 · 2022-11-17T13:54:31Z

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

msmith-aus · 2022-10-21T07:48:30Z

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 :)

… 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.

…me to train and make some nice plots

…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

…d all files

SiyuLiu0329 · 2022-11-14T03:36:52Z

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 · 2022-11-17T13:54:31Z

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

msmith-ausand others added 10 commits October 20, 2022 20:05

Folder structure + model built in modules.py, need to test the model,…
a61c452
… 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

Finished off Model, did preprocessing function, nextdevelop a functio…
b15fb93
…n for disc parameter and then start training.

Added notebook to train on google colab. laptop too slow :(
1c19304

Dice coeff function added. Still need to train the model...
1113063

Added dice coefficient loss function and documented utils.py, fixed s…
0be9893
…ome bugs in modules.py, still working through errors in modules.py.

Finished Improved Unet model and now compiles width model.compile(...)
634073f

First training run!!!, fixed errors in utils.py and module.py, now ti…
bf10d55
…me to train and make some nice plots

Model has trained through once with appropiate disc scores :). Finish…
2fd511b
…ed train.py functionality. Need to do predict.py and make plots+images

train.py runs the model and saves to local directory, adding plotting…
17a5b24
… functions in util.py to plot accuracy and loss. Last thing for funcionality is predict.py

Final commit, produced training graphs, finished read.me and commente…
05be933
…d all files

gayanku added the Improved UNet label Nov 5, 2022

shakes76 added the Unmergeable Cant be merged for history or other reason label Nov 17, 2022