OASIS brain data set using VQVAE - Daniel Miller 45810536 #458
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…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.
…enting VQVAE structure.
…owever, quantised layer function still needs to be implemented and is currently preventing the code to run.
…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.
…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
|
This is an initial inspection, no action is required at this point
|
Good Practice (Design/Commenting, TF/Torch Usage)Adequate use and implementation (missing pixel CNN) -2 Recognition ProblemSolves problem (no generations) -2 Commit LogMeaningful commit messages DocumentationReadMe OK, model info and background missing -2 Pull RequestSuccessful Pull Request (Working Algorithm Delivered on Time in Correct Branch) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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