OASIS brain data set using VQVAE - Daniel Miller 45810536 by dapmiller · Pull Request #458 · shakes76/PatternFlow

dapmiller · 2022-10-21T13:16:02Z

A VQVAE in tensorflow has been implemented to generate reconstructed images from OASIS brain dataset. When reconstructing images from VQVAE, a SSIM of 0.734 was achieved. A readme file explains the process and gives a brief rundown of how it works.

Files included:
modules.py: VQVAE model
dataset.py: data loader
train.py: training functions
predict.py: predicts results using model
readme_images: summary

…ataset and the other loads the training images into a numpy array

….py file for normalising and preprocessing training data

…th one hot encoding. Train.py now calls this for training data.

…et.py

…enting VQVAE structure.

…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

…mary in train.py

… train.py

…tion from dataset.py. Reformatted the functions in modules.py -> encoder and decoder are now in terms of modules instead of sequenitial and the vq layer and overall model builder are in classes to allow other atrributes to be assessed of the model functionality. train.py has reduced in code whereas data is no longer being batched before training (now batched in model.fit). Read.me file has notes being written

… currently does not work however. Training for data is also working, however there is a high loss.

… modules.py

…menting results for post model training

… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

… calculated incorrectly. Wrote draft read.me file

… calculated incorrectly.

…ernFlow into topic-recognition

… calculated incorrectly.

…lcnn stuff as ran out of time to finish it

SiyuLiu0329 · 2022-11-09T03:47:58Z

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

Reconstruction: OK
Generative part: pixel-cnn part seems to be missing
Readme seems incomplete with placeholder(s)

shakes76 · 2022-11-18T04:34:55Z

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

Adequate use and implementation (missing pixel CNN) -2
Good spacing and comments
Header blocks

Recognition Problem

Solves problem (no generations) -2
Driver Script present
File structure present
Shows Usage & Demo & Visualisation & Data usage (no plots) -1
Module present
Commenting
No Data leakage
Difficulty: Hard

Commit Log

Meaningful commit messages
Progressive commits used

Documentation

ReadMe OK, model info and background missing -2
Good Description and Comments
Markdown used PDF submitted

Pull Request

Successful Pull Request (Working Algorithm Delivered on Time in Correct Branch)
Feedback required, remove duplicate Readmes -2
Request Description OK, more info would be good -1

dapmiller · 2022-10-21T13:16:02Z

A VQVAE in tensorflow has been implemented to generate reconstructed images from OASIS brain dataset. When reconstructing images from VQVAE, a SSIM of 0.734 was achieved. A readme file explains the process and gives a brief rundown of how it works.

Files included:
modules.py: VQVAE model
dataset.py: data loader
train.py: training functions
predict.py: predicts results using model
readme_images: summary

…ataset and the other loads the training images into a numpy array

….py file for normalising and preprocessing training data

…th one hot encoding. Train.py now calls this for training data.

…et.py

…enting VQVAE structure.

…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

…mary in train.py

… train.py

…tion from dataset.py. Reformatted the functions in modules.py -> encoder and decoder are now in terms of modules instead of sequenitial and the vq layer and overall model builder are in classes to allow other atrributes to be assessed of the model functionality. train.py has reduced in code whereas data is no longer being batched before training (now batched in model.fit). Read.me file has notes being written

… currently does not work however. Training for data is also working, however there is a high loss.

… modules.py

…menting results for post model training

… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

… calculated incorrectly. Wrote draft read.me file

… calculated incorrectly.

…ernFlow into topic-recognition

… calculated incorrectly.

…lcnn stuff as ran out of time to finish it

SiyuLiu0329 · 2022-11-09T03:47:58Z

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

Reconstruction: OK
Generative part: pixel-cnn part seems to be missing
Readme seems incomplete with placeholder(s)

shakes76 · 2022-11-18T04:34:55Z

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

Adequate use and implementation (missing pixel CNN) -2
Good spacing and comments
Header blocks

Recognition Problem

Solves problem (no generations) -2
Driver Script present
File structure present
Shows Usage & Demo & Visualisation & Data usage (no plots) -1
Module present
Commenting
No Data leakage
Difficulty: Hard

Commit Log

Meaningful commit messages
Progressive commits used

Documentation

ReadMe OK, model info and background missing -2
Good Description and Comments
Markdown used PDF submitted

Pull Request

Successful Pull Request (Working Algorithm Delivered on Time in Correct Branch)
Feedback required, remove duplicate Readmes -2
Request Description OK, more info would be good -1

dapmiller · 2022-10-21T13:16:02Z

A VQVAE in tensorflow has been implemented to generate reconstructed images from OASIS brain dataset. When reconstructing images from VQVAE, a SSIM of 0.734 was achieved. A readme file explains the process and gives a brief rundown of how it works.

Files included:
modules.py: VQVAE model
dataset.py: data loader
train.py: training functions
predict.py: predicts results using model
readme_images: summary

…ataset and the other loads the training images into a numpy array

….py file for normalising and preprocessing training data

…th one hot encoding. Train.py now calls this for training data.

…et.py

…enting VQVAE structure.

…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

…mary in train.py

… train.py

…tion from dataset.py. Reformatted the functions in modules.py -> encoder and decoder are now in terms of modules instead of sequenitial and the vq layer and overall model builder are in classes to allow other atrributes to be assessed of the model functionality. train.py has reduced in code whereas data is no longer being batched before training (now batched in model.fit). Read.me file has notes being written

… currently does not work however. Training for data is also working, however there is a high loss.

… modules.py

…menting results for post model training

… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

… calculated incorrectly. Wrote draft read.me file

… calculated incorrectly.

…ernFlow into topic-recognition

… calculated incorrectly.

…lcnn stuff as ran out of time to finish it

SiyuLiu0329 · 2022-11-09T03:47:58Z

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

Reconstruction: OK
Generative part: pixel-cnn part seems to be missing
Readme seems incomplete with placeholder(s)

shakes76 · 2022-11-18T04:34:55Z

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

Adequate use and implementation (missing pixel CNN) -2
Good spacing and comments
Header blocks

Recognition Problem

Solves problem (no generations) -2
Driver Script present
File structure present
Shows Usage & Demo & Visualisation & Data usage (no plots) -1
Module present
Commenting
No Data leakage
Difficulty: Hard

Commit Log

Meaningful commit messages
Progressive commits used

Documentation

ReadMe OK, model info and background missing -2
Good Description and Comments
Markdown used PDF submitted

Pull Request

Successful Pull Request (Working Algorithm Delivered on Time in Correct Branch)
Feedback required, remove duplicate Readmes -2
Request Description OK, more info would be good -1

dapmiller · 2022-10-21T13:16:02Z

A VQVAE in tensorflow has been implemented to generate reconstructed images from OASIS brain dataset. When reconstructing images from VQVAE, a SSIM of 0.734 was achieved. A readme file explains the process and gives a brief rundown of how it works.

Files included:
modules.py: VQVAE model
dataset.py: data loader
train.py: training functions
predict.py: predicts results using model
readme_images: summary

…ataset and the other loads the training images into a numpy array

….py file for normalising and preprocessing training data

…th one hot encoding. Train.py now calls this for training data.

…et.py

…enting VQVAE structure.

…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

…mary in train.py

… train.py

…tion from dataset.py. Reformatted the functions in modules.py -> encoder and decoder are now in terms of modules instead of sequenitial and the vq layer and overall model builder are in classes to allow other atrributes to be assessed of the model functionality. train.py has reduced in code whereas data is no longer being batched before training (now batched in model.fit). Read.me file has notes being written

… currently does not work however. Training for data is also working, however there is a high loss.

… modules.py

…menting results for post model training

… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

… calculated incorrectly. Wrote draft read.me file

… calculated incorrectly.

…ernFlow into topic-recognition

… calculated incorrectly.

…lcnn stuff as ran out of time to finish it

SiyuLiu0329 · 2022-11-09T03:47:58Z

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

Reconstruction: OK
Generative part: pixel-cnn part seems to be missing
Readme seems incomplete with placeholder(s)

shakes76 · 2022-11-18T04:34:55Z

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

Adequate use and implementation (missing pixel CNN) -2
Good spacing and comments
Header blocks

Recognition Problem

Solves problem (no generations) -2
Driver Script present
File structure present
Shows Usage & Demo & Visualisation & Data usage (no plots) -1
Module present
Commenting
No Data leakage
Difficulty: Hard

Commit Log

Meaningful commit messages
Progressive commits used

Documentation

ReadMe OK, model info and background missing -2
Good Description and Comments
Markdown used PDF submitted

Pull Request

Successful Pull Request (Working Algorithm Delivered on Time in Correct Branch)
Feedback required, remove duplicate Readmes -2
Request Description OK, more info would be good -1

dapmiller · 2022-10-21T13:16:02Z

A VQVAE in tensorflow has been implemented to generate reconstructed images from OASIS brain dataset. When reconstructing images from VQVAE, a SSIM of 0.734 was achieved. A readme file explains the process and gives a brief rundown of how it works.

Files included:
modules.py: VQVAE model
dataset.py: data loader
train.py: training functions
predict.py: predicts results using model
readme_images: summary

…ataset and the other loads the training images into a numpy array

….py file for normalising and preprocessing training data

…th one hot encoding. Train.py now calls this for training data.

…et.py

…enting VQVAE structure.

…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

…mary in train.py

… train.py

…tion from dataset.py. Reformatted the functions in modules.py -> encoder and decoder are now in terms of modules instead of sequenitial and the vq layer and overall model builder are in classes to allow other atrributes to be assessed of the model functionality. train.py has reduced in code whereas data is no longer being batched before training (now batched in model.fit). Read.me file has notes being written

… currently does not work however. Training for data is also working, however there is a high loss.

… modules.py

…menting results for post model training

… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

… calculated incorrectly. Wrote draft read.me file

… calculated incorrectly.

…ernFlow into topic-recognition

… calculated incorrectly.

…lcnn stuff as ran out of time to finish it

SiyuLiu0329 · 2022-11-09T03:47:58Z

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

Reconstruction: OK
Generative part: pixel-cnn part seems to be missing
Readme seems incomplete with placeholder(s)

shakes76 · 2022-11-18T04:34:55Z

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

Adequate use and implementation (missing pixel CNN) -2
Good spacing and comments
Header blocks

Recognition Problem

Solves problem (no generations) -2
Driver Script present
File structure present
Shows Usage & Demo & Visualisation & Data usage (no plots) -1
Module present
Commenting
No Data leakage
Difficulty: Hard

Commit Log

Meaningful commit messages
Progressive commits used

Documentation

ReadMe OK, model info and background missing -2
Good Description and Comments
Markdown used PDF submitted

Pull Request

Successful Pull Request (Working Algorithm Delivered on Time in Correct Branch)
Feedback required, remove duplicate Readmes -2
Request Description OK, more info would be good -1

dapmiller · 2022-10-21T13:16:02Z

A VQVAE in tensorflow has been implemented to generate reconstructed images from OASIS brain dataset. When reconstructing images from VQVAE, a SSIM of 0.734 was achieved. A readme file explains the process and gives a brief rundown of how it works.

Files included:
modules.py: VQVAE model
dataset.py: data loader
train.py: training functions
predict.py: predicts results using model
readme_images: summary

…ataset and the other loads the training images into a numpy array

….py file for normalising and preprocessing training data

…th one hot encoding. Train.py now calls this for training data.

…et.py

…enting VQVAE structure.

…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

…mary in train.py

… train.py

…tion from dataset.py. Reformatted the functions in modules.py -> encoder and decoder are now in terms of modules instead of sequenitial and the vq layer and overall model builder are in classes to allow other atrributes to be assessed of the model functionality. train.py has reduced in code whereas data is no longer being batched before training (now batched in model.fit). Read.me file has notes being written

… currently does not work however. Training for data is also working, however there is a high loss.

… modules.py

…menting results for post model training

… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

… calculated incorrectly. Wrote draft read.me file

… calculated incorrectly.

…ernFlow into topic-recognition

… calculated incorrectly.

…lcnn stuff as ran out of time to finish it

SiyuLiu0329 · 2022-11-09T03:47:58Z

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

Reconstruction: OK
Generative part: pixel-cnn part seems to be missing
Readme seems incomplete with placeholder(s)

shakes76 · 2022-11-18T04:34:55Z

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

Adequate use and implementation (missing pixel CNN) -2
Good spacing and comments
Header blocks

Recognition Problem

Solves problem (no generations) -2
Driver Script present
File structure present
Shows Usage & Demo & Visualisation & Data usage (no plots) -1
Module present
Commenting
No Data leakage
Difficulty: Hard

Commit Log

Meaningful commit messages
Progressive commits used

Documentation

ReadMe OK, model info and background missing -2
Good Description and Comments
Markdown used PDF submitted

Pull Request

Successful Pull Request (Working Algorithm Delivered on Time in Correct Branch)
Feedback required, remove duplicate Readmes -2
Request Description OK, more info would be good -1

dapmiller · 2022-10-21T13:16:02Z

A VQVAE in tensorflow has been implemented to generate reconstructed images from OASIS brain dataset. When reconstructing images from VQVAE, a SSIM of 0.734 was achieved. A readme file explains the process and gives a brief rundown of how it works.

Files included:
modules.py: VQVAE model
dataset.py: data loader
train.py: training functions
predict.py: predicts results using model
readme_images: summary

…ataset and the other loads the training images into a numpy array

….py file for normalising and preprocessing training data

…th one hot encoding. Train.py now calls this for training data.

…et.py

…enting VQVAE structure.

…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

…mary in train.py

… train.py

…tion from dataset.py. Reformatted the functions in modules.py -> encoder and decoder are now in terms of modules instead of sequenitial and the vq layer and overall model builder are in classes to allow other atrributes to be assessed of the model functionality. train.py has reduced in code whereas data is no longer being batched before training (now batched in model.fit). Read.me file has notes being written

… currently does not work however. Training for data is also working, however there is a high loss.

… modules.py

…menting results for post model training

… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

… calculated incorrectly. Wrote draft read.me file

… calculated incorrectly.

…ernFlow into topic-recognition

… calculated incorrectly.

…lcnn stuff as ran out of time to finish it

SiyuLiu0329 · 2022-11-09T03:47:58Z

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

Reconstruction: OK
Generative part: pixel-cnn part seems to be missing
Readme seems incomplete with placeholder(s)

shakes76 · 2022-11-18T04:34:55Z

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

Adequate use and implementation (missing pixel CNN) -2
Good spacing and comments
Header blocks

Recognition Problem

Solves problem (no generations) -2
Driver Script present
File structure present
Shows Usage & Demo & Visualisation & Data usage (no plots) -1
Module present
Commenting
No Data leakage
Difficulty: Hard

Commit Log

Meaningful commit messages
Progressive commits used

Documentation

ReadMe OK, model info and background missing -2
Good Description and Comments
Markdown used PDF submitted

Pull Request

Successful Pull Request (Working Algorithm Delivered on Time in Correct Branch)
Feedback required, remove duplicate Readmes -2
Request Description OK, more info would be good -1

dapmiller · 2022-10-21T13:16:02Z

A VQVAE in tensorflow has been implemented to generate reconstructed images from OASIS brain dataset. When reconstructing images from VQVAE, a SSIM of 0.734 was achieved. A readme file explains the process and gives a brief rundown of how it works.

Files included:
modules.py: VQVAE model
dataset.py: data loader
train.py: training functions
predict.py: predicts results using model
readme_images: summary

…ataset and the other loads the training images into a numpy array

….py file for normalising and preprocessing training data

…th one hot encoding. Train.py now calls this for training data.

…et.py

…enting VQVAE structure.

…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

…mary in train.py

… train.py

…tion from dataset.py. Reformatted the functions in modules.py -> encoder and decoder are now in terms of modules instead of sequenitial and the vq layer and overall model builder are in classes to allow other atrributes to be assessed of the model functionality. train.py has reduced in code whereas data is no longer being batched before training (now batched in model.fit). Read.me file has notes being written

… currently does not work however. Training for data is also working, however there is a high loss.

… modules.py

…menting results for post model training

… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

… calculated incorrectly. Wrote draft read.me file

… calculated incorrectly.

…ernFlow into topic-recognition

… calculated incorrectly.

…lcnn stuff as ran out of time to finish it

SiyuLiu0329 · 2022-11-09T03:47:58Z

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

Reconstruction: OK
Generative part: pixel-cnn part seems to be missing
Readme seems incomplete with placeholder(s)

shakes76 · 2022-11-18T04:34:55Z

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

Adequate use and implementation (missing pixel CNN) -2
Good spacing and comments
Header blocks

Recognition Problem

Solves problem (no generations) -2
Driver Script present
File structure present
Shows Usage & Demo & Visualisation & Data usage (no plots) -1
Module present
Commenting
No Data leakage
Difficulty: Hard

Commit Log

Meaningful commit messages
Progressive commits used

Documentation

ReadMe OK, model info and background missing -2
Good Description and Comments
Markdown used PDF submitted

Pull Request

Successful Pull Request (Working Algorithm Delivered on Time in Correct Branch)
Feedback required, remove duplicate Readmes -2
Request Description OK, more info would be good -1

Daniel Millerand others added 30 commits October 11, 2022 16:16

Trying something meaningful
c2702e2

Created required files
15ca543

Provided brief description for each file of what is to be included
032ac04

Added 2 new functions into datasey.py which one downloads the oasis d…
446c8ba
…ataset and the other loads the training images into a numpy array

Add comments to function for explanation and understanding in dataset…
13144c6
….py file for normalising and preprocessing training data

Added functions to dataset.py to load labels and also process them wi…
6e334b3
…th one hot encoding. Train.py now calls this for training data.

Added calls to load validation and test labels in train.py from datas…
4c758ce
…et.py

Added brief summary to Read.me file about model
38430c7

Safety commit of working loading and processing of data before implem…
d4f1ec4
…enting VQVAE structure.

Created encoder, decoder and overall vq-vae functions in modules.py h…
b1bb74b
…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

Finished building model in modules.py. It compiles and prints out sum…
fa73b09
…mary in train.py

Finished building model in modules.py and it successfully compiles in…
b2c7b49
… train.py

Testing commit
df70801

Commited the module.py file and removed unnecessary code
dee848c

created a function to batch data before training in dataset.py
9ee75d3

Created functions in train.py that compute structural similiarity. It…
1e99576
… currently does not work however. Training for data is also working, however there is a high loss.

Edited the ssim in train.py. Also added references to dataset.py anhd…
d361777
… modules.py

Fixed bug that was stopping loss reduce in model.fit. Currently imple…
235585b
…menting results for post model training

Create Images
b0d498b

Delete Images
9b90b9f

Edited train.py bug in training. It now runs and the losses appear to…
f396991
… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

Fixed Bug in model.fit that caused loss. It was due to variance being…
3aeadda
… calculated incorrectly. Wrote draft read.me file

Fixed Bug in model.fit that caused loss. It was due to variance being…
a8f82d0
… calculated incorrectly.

Merge branch 'topic-recognition' ofhttps://github.com/dapmiller/Patt…
92073ce
…ernFlow into topic-recognition

Fixed Bug in model.fit that caused loss. It was due to variance being…
ab702fe
… calculated incorrectly.

Trying to add images
6899684

Added Graph
63a9a18

Cleaned up Files and finsihed off REadme file. Commented out the pixe…
f5db768
…lcnn stuff as ran out of time to finish it

Fixed ssim to read 0.74 not 74
09450f8

LinfengLiu98 added the VQVAE label Nov 5, 2022

shakes76 added the Feedback_Needed label Nov 18, 2022

Daniel Millerand others added 30 commits October 11, 2022 16:16

Trying something meaningful
c2702e2

Created required files
15ca543

Provided brief description for each file of what is to be included
032ac04

Added 2 new functions into datasey.py which one downloads the oasis d…
446c8ba
…ataset and the other loads the training images into a numpy array

Add comments to function for explanation and understanding in dataset…
13144c6
….py file for normalising and preprocessing training data

Added functions to dataset.py to load labels and also process them wi…
6e334b3
…th one hot encoding. Train.py now calls this for training data.

Added calls to load validation and test labels in train.py from datas…
4c758ce
…et.py

Added brief summary to Read.me file about model
38430c7

Safety commit of working loading and processing of data before implem…
d4f1ec4
…enting VQVAE structure.

Created encoder, decoder and overall vq-vae functions in modules.py h…
b1bb74b
…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

Finished building model in modules.py. It compiles and prints out sum…
fa73b09
…mary in train.py

Finished building model in modules.py and it successfully compiles in…
b2c7b49
… train.py

Testing commit
df70801

Commited the module.py file and removed unnecessary code
dee848c

created a function to batch data before training in dataset.py
9ee75d3

Created functions in train.py that compute structural similiarity. It…
1e99576
… currently does not work however. Training for data is also working, however there is a high loss.

Edited the ssim in train.py. Also added references to dataset.py anhd…
d361777
… modules.py

Fixed bug that was stopping loss reduce in model.fit. Currently imple…
235585b
…menting results for post model training

Create Images
b0d498b

Delete Images
9b90b9f

Edited train.py bug in training. It now runs and the losses appear to…
f396991
… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

Fixed Bug in model.fit that caused loss. It was due to variance being…
3aeadda
… calculated incorrectly. Wrote draft read.me file

Fixed Bug in model.fit that caused loss. It was due to variance being…
a8f82d0
… calculated incorrectly.

Merge branch 'topic-recognition' ofhttps://github.com/dapmiller/Patt…
92073ce
…ernFlow into topic-recognition

Fixed Bug in model.fit that caused loss. It was due to variance being…
ab702fe
… calculated incorrectly.

Trying to add images
6899684

Added Graph
63a9a18

Cleaned up Files and finsihed off REadme file. Commented out the pixe…
f5db768
…lcnn stuff as ran out of time to finish it

Fixed ssim to read 0.74 not 74
09450f8

LinfengLiu98 added the VQVAE label Nov 5, 2022

shakes76 added the Feedback_Needed label Nov 18, 2022

Daniel Millerand others added 30 commits October 11, 2022 16:16

Trying something meaningful
c2702e2

Created required files
15ca543

Provided brief description for each file of what is to be included
032ac04

Added 2 new functions into datasey.py which one downloads the oasis d…
446c8ba
…ataset and the other loads the training images into a numpy array

Add comments to function for explanation and understanding in dataset…
13144c6
….py file for normalising and preprocessing training data

Added functions to dataset.py to load labels and also process them wi…
6e334b3
…th one hot encoding. Train.py now calls this for training data.

Added calls to load validation and test labels in train.py from datas…
4c758ce
…et.py

Added brief summary to Read.me file about model
38430c7

Safety commit of working loading and processing of data before implem…
d4f1ec4
…enting VQVAE structure.

Created encoder, decoder and overall vq-vae functions in modules.py h…
b1bb74b
…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

Finished building model in modules.py. It compiles and prints out sum…
fa73b09
…mary in train.py

Finished building model in modules.py and it successfully compiles in…
b2c7b49
… train.py

Testing commit
df70801

Commited the module.py file and removed unnecessary code
dee848c

created a function to batch data before training in dataset.py
9ee75d3

Created functions in train.py that compute structural similiarity. It…
1e99576
… currently does not work however. Training for data is also working, however there is a high loss.

Edited the ssim in train.py. Also added references to dataset.py anhd…
d361777
… modules.py

Fixed bug that was stopping loss reduce in model.fit. Currently imple…
235585b
…menting results for post model training

Create Images
b0d498b

Delete Images
9b90b9f

Edited train.py bug in training. It now runs and the losses appear to…
f396991
… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

Fixed Bug in model.fit that caused loss. It was due to variance being…
3aeadda
… calculated incorrectly. Wrote draft read.me file

Fixed Bug in model.fit that caused loss. It was due to variance being…
a8f82d0
… calculated incorrectly.

Merge branch 'topic-recognition' ofhttps://github.com/dapmiller/Patt…
92073ce
…ernFlow into topic-recognition

Fixed Bug in model.fit that caused loss. It was due to variance being…
ab702fe
… calculated incorrectly.

Trying to add images
6899684

Added Graph
63a9a18

Cleaned up Files and finsihed off REadme file. Commented out the pixe…
f5db768
…lcnn stuff as ran out of time to finish it

Fixed ssim to read 0.74 not 74
09450f8

LinfengLiu98 added the VQVAE label Nov 5, 2022

shakes76 added the Feedback_Needed label Nov 18, 2022

Daniel Millerand others added 30 commits October 11, 2022 16:16

Trying something meaningful
c2702e2

Created required files
15ca543

Provided brief description for each file of what is to be included
032ac04

Added 2 new functions into datasey.py which one downloads the oasis d…
446c8ba
…ataset and the other loads the training images into a numpy array

Add comments to function for explanation and understanding in dataset…
13144c6
….py file for normalising and preprocessing training data

Added functions to dataset.py to load labels and also process them wi…
6e334b3
…th one hot encoding. Train.py now calls this for training data.

Added calls to load validation and test labels in train.py from datas…
4c758ce
…et.py

Added brief summary to Read.me file about model
38430c7

Safety commit of working loading and processing of data before implem…
d4f1ec4
…enting VQVAE structure.

Created encoder, decoder and overall vq-vae functions in modules.py h…
b1bb74b
…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

Finished building model in modules.py. It compiles and prints out sum…
fa73b09
…mary in train.py

Finished building model in modules.py and it successfully compiles in…
b2c7b49
… train.py

Testing commit
df70801

Commited the module.py file and removed unnecessary code
dee848c

created a function to batch data before training in dataset.py
9ee75d3

Created functions in train.py that compute structural similiarity. It…
1e99576
… currently does not work however. Training for data is also working, however there is a high loss.

Edited the ssim in train.py. Also added references to dataset.py anhd…
d361777
… modules.py

Fixed bug that was stopping loss reduce in model.fit. Currently imple…
235585b
…menting results for post model training

Create Images
b0d498b

Delete Images
9b90b9f

Edited train.py bug in training. It now runs and the losses appear to…
f396991
… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

Fixed Bug in model.fit that caused loss. It was due to variance being…
3aeadda
… calculated incorrectly. Wrote draft read.me file

Fixed Bug in model.fit that caused loss. It was due to variance being…
a8f82d0
… calculated incorrectly.

Merge branch 'topic-recognition' ofhttps://github.com/dapmiller/Patt…
92073ce
…ernFlow into topic-recognition

Fixed Bug in model.fit that caused loss. It was due to variance being…
ab702fe
… calculated incorrectly.

Trying to add images
6899684

Added Graph
63a9a18

Cleaned up Files and finsihed off REadme file. Commented out the pixe…
f5db768
…lcnn stuff as ran out of time to finish it

Fixed ssim to read 0.74 not 74
09450f8

LinfengLiu98 added the VQVAE label Nov 5, 2022

shakes76 added the Feedback_Needed label Nov 18, 2022

Daniel Millerand others added 30 commits October 11, 2022 16:16

Trying something meaningful
c2702e2

Created required files
15ca543

Provided brief description for each file of what is to be included
032ac04

Added 2 new functions into datasey.py which one downloads the oasis d…
446c8ba
…ataset and the other loads the training images into a numpy array

Add comments to function for explanation and understanding in dataset…
13144c6
….py file for normalising and preprocessing training data

Added functions to dataset.py to load labels and also process them wi…
6e334b3
…th one hot encoding. Train.py now calls this for training data.

Added calls to load validation and test labels in train.py from datas…
4c758ce
…et.py

Added brief summary to Read.me file about model
38430c7

Safety commit of working loading and processing of data before implem…
d4f1ec4
…enting VQVAE structure.

Created encoder, decoder and overall vq-vae functions in modules.py h…
b1bb74b
…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

Finished building model in modules.py. It compiles and prints out sum…
fa73b09
…mary in train.py

Finished building model in modules.py and it successfully compiles in…
b2c7b49
… train.py

Testing commit
df70801

Commited the module.py file and removed unnecessary code
dee848c

created a function to batch data before training in dataset.py
9ee75d3

Created functions in train.py that compute structural similiarity. It…
1e99576
… currently does not work however. Training for data is also working, however there is a high loss.

Edited the ssim in train.py. Also added references to dataset.py anhd…
d361777
… modules.py

Fixed bug that was stopping loss reduce in model.fit. Currently imple…
235585b
…menting results for post model training

Create Images
b0d498b

Delete Images
9b90b9f

Edited train.py bug in training. It now runs and the losses appear to…
f396991
… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

Fixed Bug in model.fit that caused loss. It was due to variance being…
3aeadda
… calculated incorrectly. Wrote draft read.me file

Fixed Bug in model.fit that caused loss. It was due to variance being…
a8f82d0
… calculated incorrectly.

Merge branch 'topic-recognition' ofhttps://github.com/dapmiller/Patt…
92073ce
…ernFlow into topic-recognition

Fixed Bug in model.fit that caused loss. It was due to variance being…
ab702fe
… calculated incorrectly.

Trying to add images
6899684

Added Graph
63a9a18

Cleaned up Files and finsihed off REadme file. Commented out the pixe…
f5db768
…lcnn stuff as ran out of time to finish it

Fixed ssim to read 0.74 not 74
09450f8

LinfengLiu98 added the VQVAE label Nov 5, 2022

shakes76 added the Feedback_Needed label Nov 18, 2022

Daniel Millerand others added 30 commits October 11, 2022 16:16

Trying something meaningful
c2702e2

Created required files
15ca543

Provided brief description for each file of what is to be included
032ac04

Added 2 new functions into datasey.py which one downloads the oasis d…
446c8ba
…ataset and the other loads the training images into a numpy array

Add comments to function for explanation and understanding in dataset…
13144c6
….py file for normalising and preprocessing training data

Added functions to dataset.py to load labels and also process them wi…
6e334b3
…th one hot encoding. Train.py now calls this for training data.

Added calls to load validation and test labels in train.py from datas…
4c758ce
…et.py

Added brief summary to Read.me file about model
38430c7

Safety commit of working loading and processing of data before implem…
d4f1ec4
…enting VQVAE structure.

Created encoder, decoder and overall vq-vae functions in modules.py h…
b1bb74b
…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

Finished building model in modules.py. It compiles and prints out sum…
fa73b09
…mary in train.py

Finished building model in modules.py and it successfully compiles in…
b2c7b49
… train.py

Testing commit
df70801

Commited the module.py file and removed unnecessary code
dee848c

created a function to batch data before training in dataset.py
9ee75d3

Created functions in train.py that compute structural similiarity. It…
1e99576
… currently does not work however. Training for data is also working, however there is a high loss.

Edited the ssim in train.py. Also added references to dataset.py anhd…
d361777
… modules.py

Fixed bug that was stopping loss reduce in model.fit. Currently imple…
235585b
…menting results for post model training

Create Images
b0d498b

Delete Images
9b90b9f

Edited train.py bug in training. It now runs and the losses appear to…
f396991
… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

Fixed Bug in model.fit that caused loss. It was due to variance being…
3aeadda
… calculated incorrectly. Wrote draft read.me file

Fixed Bug in model.fit that caused loss. It was due to variance being…
a8f82d0
… calculated incorrectly.

Merge branch 'topic-recognition' ofhttps://github.com/dapmiller/Patt…
92073ce
…ernFlow into topic-recognition

Fixed Bug in model.fit that caused loss. It was due to variance being…
ab702fe
… calculated incorrectly.

Trying to add images
6899684

Added Graph
63a9a18

Cleaned up Files and finsihed off REadme file. Commented out the pixe…
f5db768
…lcnn stuff as ran out of time to finish it

Fixed ssim to read 0.74 not 74
09450f8

LinfengLiu98 added the VQVAE label Nov 5, 2022

shakes76 added the Feedback_Needed label Nov 18, 2022

Daniel Millerand others added 30 commits October 11, 2022 16:16

Trying something meaningful
c2702e2

Created required files
15ca543

Provided brief description for each file of what is to be included
032ac04

Added 2 new functions into datasey.py which one downloads the oasis d…
446c8ba
…ataset and the other loads the training images into a numpy array

Add comments to function for explanation and understanding in dataset…
13144c6
….py file for normalising and preprocessing training data

Added functions to dataset.py to load labels and also process them wi…
6e334b3
…th one hot encoding. Train.py now calls this for training data.

Added calls to load validation and test labels in train.py from datas…
4c758ce
…et.py

Added brief summary to Read.me file about model
38430c7

Safety commit of working loading and processing of data before implem…
d4f1ec4
…enting VQVAE structure.

Created encoder, decoder and overall vq-vae functions in modules.py h…
b1bb74b
…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

Finished building model in modules.py. It compiles and prints out sum…
fa73b09
…mary in train.py

Finished building model in modules.py and it successfully compiles in…
b2c7b49
… train.py

Testing commit
df70801

Commited the module.py file and removed unnecessary code
dee848c

created a function to batch data before training in dataset.py
9ee75d3

Created functions in train.py that compute structural similiarity. It…
1e99576
… currently does not work however. Training for data is also working, however there is a high loss.

Edited the ssim in train.py. Also added references to dataset.py anhd…
d361777
… modules.py

Fixed bug that was stopping loss reduce in model.fit. Currently imple…
235585b
…menting results for post model training

Create Images
b0d498b

Delete Images
9b90b9f

Edited train.py bug in training. It now runs and the losses appear to…
f396991
… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

Fixed Bug in model.fit that caused loss. It was due to variance being…
3aeadda
… calculated incorrectly. Wrote draft read.me file

Fixed Bug in model.fit that caused loss. It was due to variance being…
a8f82d0
… calculated incorrectly.

Merge branch 'topic-recognition' ofhttps://github.com/dapmiller/Patt…
92073ce
…ernFlow into topic-recognition

Fixed Bug in model.fit that caused loss. It was due to variance being…
ab702fe
… calculated incorrectly.

Trying to add images
6899684

Added Graph
63a9a18

Cleaned up Files and finsihed off REadme file. Commented out the pixe…
f5db768
…lcnn stuff as ran out of time to finish it

Fixed ssim to read 0.74 not 74
09450f8

LinfengLiu98 added the VQVAE label Nov 5, 2022

shakes76 added the Feedback_Needed label Nov 18, 2022

Daniel Millerand others added 30 commits October 11, 2022 16:16

Trying something meaningful
c2702e2

Created required files
15ca543

Provided brief description for each file of what is to be included
032ac04

Added 2 new functions into datasey.py which one downloads the oasis d…
446c8ba
…ataset and the other loads the training images into a numpy array

Add comments to function for explanation and understanding in dataset…
13144c6
….py file for normalising and preprocessing training data

Added functions to dataset.py to load labels and also process them wi…
6e334b3
…th one hot encoding. Train.py now calls this for training data.

Added calls to load validation and test labels in train.py from datas…
4c758ce
…et.py

Added brief summary to Read.me file about model
38430c7

Safety commit of working loading and processing of data before implem…
d4f1ec4
…enting VQVAE structure.

Created encoder, decoder and overall vq-vae functions in modules.py h…
b1bb74b
…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.

Finished building model in modules.py. It compiles and prints out sum…
fa73b09
…mary in train.py

Finished building model in modules.py and it successfully compiles in…
b2c7b49
… train.py

Testing commit
df70801

Commited the module.py file and removed unnecessary code
dee848c

created a function to batch data before training in dataset.py
9ee75d3

Created functions in train.py that compute structural similiarity. It…
1e99576
… currently does not work however. Training for data is also working, however there is a high loss.

Edited the ssim in train.py. Also added references to dataset.py anhd…
d361777
… modules.py

Fixed bug that was stopping loss reduce in model.fit. Currently imple…
235585b
…menting results for post model training

Create Images
b0d498b

Delete Images
9b90b9f

Edited train.py bug in training. It now runs and the losses appear to…
f396991
… decrease realistically. The bug occurred due to the value of the variance variable being feed into model.fit.

Fixed Bug in model.fit that caused loss. It was due to variance being…
3aeadda
… calculated incorrectly. Wrote draft read.me file

Fixed Bug in model.fit that caused loss. It was due to variance being…
a8f82d0
… calculated incorrectly.

Merge branch 'topic-recognition' ofhttps://github.com/dapmiller/Patt…
92073ce
…ernFlow into topic-recognition

Fixed Bug in model.fit that caused loss. It was due to variance being…
ab702fe
… calculated incorrectly.

Trying to add images
6899684

Added Graph
63a9a18

Cleaned up Files and finsihed off REadme file. Commented out the pixe…
f5db768
…lcnn stuff as ran out of time to finish it

Fixed ssim to read 0.74 not 74
09450f8

LinfengLiu98 added the VQVAE label Nov 5, 2022

shakes76 added the Feedback_Needed label Nov 18, 2022

Conversation

dapmiller commented Oct 21, 2022

Uh oh!

SiyuLiu0329 commented Nov 9, 2022

Uh oh!

shakes76 commented Nov 18, 2022

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

Recognition Problem

Commit Log

Documentation

Pull Request

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Conversation

dapmiller commented Oct 21, 2022

Uh oh!

SiyuLiu0329 commented Nov 9, 2022

Uh oh!

shakes76 commented Nov 18, 2022

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

Recognition Problem

Commit Log

Documentation

Pull Request

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Conversation

dapmiller commented Oct 21, 2022

Uh oh!

SiyuLiu0329 commented Nov 9, 2022

Uh oh!

shakes76 commented Nov 18, 2022

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

Recognition Problem

Commit Log

Documentation

Pull Request

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Conversation

dapmiller commented Oct 21, 2022

Uh oh!

SiyuLiu0329 commented Nov 9, 2022

Uh oh!

shakes76 commented Nov 18, 2022

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

Recognition Problem

Commit Log

Documentation

Pull Request

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants