Skip to content

Navigation Menu

Appearance settings

View all features
- BY COMPANY SIZE
  Enterprises
  Small and medium teams
  Startups
  Nonprofits
- BY USE CASE
  App Modernization
  DevSecOps
  DevOps
  CI/CD
  View all use cases
- BY INDUSTRY
  Healthcare
  Financial services
  Manufacturing
  Government
  View all industries
View all solutions
- EXPLORE BY TOPIC
  AI
  Software Development
  DevOps
  Security
  View all topics
- EXPLORE BY TYPE
  Customer stories
  Events & webinars
  Ebooks & reports
  Business insights
  GitHub Skills
- SUPPORT & SERVICES
  Documentation
  Customer support
  Community forum
  Trust center
  Partners
- COMMUNITY
  GitHub SponsorsFund open source developers
- PROGRAMS
  Security Lab
  Maintainer Community
  Accelerator
  Archive Program
- REPOSITORIES
  Topics
  Trending
  Collections
- ENTERPRISE SOLUTIONS
  Enterprise platformAI-powered developer platform
- AVAILABLE ADD-ONS
  GitHub Advanced SecurityEnterprise-grade security features
  Copilot for BusinessEnterprise-grade AI features
  Premium SupportEnterprise-grade 24/7 support
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

Appearance settings

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

shakes76 / PatternFlow Public

Notifications You must be signed in to change notification settings
Fork 391
Star 42

Code
Issues
Pull requests 110
Actions
Projects
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Actions
Projects
Security
Insights

Topic recognition#469

Open

4lon wants to merge 63 commits intoshakes76:topic-recognitionshakes76/PatternFlow:topic-recognitionfrom

4lon:topic-recognition4lon/PatternFlow:topic-recognitionCopy head branch name to clipboard

Conversation Commits63 (63)Checks Files changed

Open

Topic recognition#469
4lon wants to merge 63 commits intoshakes76:topic-recognitionfrom
4lon:topic-recognition

Commits

Commits on Oct 11, 2022

Initial commit and filling out basic project structure.
4lon
committed
Added basic dataset class that loads all images in directory and return samples for learning.
4lon
committed
Added template for VAE
4lon
committed
Corrected error in dataset class location, moved from train to dataset.
4lon
committed

Commits on Oct 14, 2022

Added Vector Quantizer
4lon
committed
Updated encoder and decoders
4lon
committed
Fixed wrong layer errors and added vqvae model, likely need to fix padding issue.
4lon
committed

Commits on Oct 20, 2022

Updated to use pytorch embeddings and fleshed out vector quantizer.
4lon
committed
Cleanup
4lon
committed
Cleanup and redid vq_vae class to add more individual functions. This should be useful later for implementation and prediction.
4lon
committed
Updated to make dataloaders in dataset.py
4lon
committed
Basis of training script setting up
4lon
committed
Built out saving model and modularised functions
4lon
committed
Fixed up incorrect dataset formatting and loading of imgs
4lon
committed
Fleshed out training function
4lon
committed
Fleshed out testing function
4lon
committed
Added image generation and saving to tensorboard for visual analysis
4lon
committed
Refactored modules to include original functions file and updated dataset location.
4lon
committed

Commits on Nov 7, 2022

Increase HPC utilisation
4lon
committed
add checks
4lon
committed
Increased Epochs
4lon
committed
Original pytorch attempt was not working, start of tensorflow attempt, reimplemented the dataset, however this current implementation is loading every image into an array, that's far from ideal so …
4lon
committed
Old train model, not relevant anymore but good for looking back and not ready to remove
4lon
committed
Redesigned VQVAE modules for tensorflow. This is a simpler design overall however time is limited. If I have time I intend to work back to this and improve the model
4lon
committed
Reimplemented basic training method, but this one does not evaluate against other data partitions or save sample outputs.
4lon
committed
Fixed some errors encountered when trying to train because of tracker dictionary, and updated directory to dataset.
4lon
committed
Added plotting of results including losses and reconstruction post learning
4lon
committed
Updated directory
4lon
committed
Fixed missing param
4lon
committed
Train on more images
4lon
committed
Updated optional param
4lon
committed
Imporved plotting
4lon
committed
Removed print statement
4lon
committed
Fixed image formatting
4lon
committed
New dataset dtype to remove reconstruction issues.
4lon
committed
Reduced batch size because of memory running out in new datatype (going from 16bits to 32 bits must mean smaller batch size required.)
4lon
committed
Reduced batch size again.
4lon
committed
Changed data type because space requirement was unachievable
4lon
committed
Built basic masked convolution layer and limited dataset size (memory issues)
4lon
committed
Implemented residual block for pixelcnn
4lon
committed
Implemented basic pixel cnn architecture but not sure it works.
4lon
committed
Added pixelcnn training to learn codebook production
4lon
committed
Updated plotting to also save pixel cnn performance
4lon
committed
Updated training with ssim metrics
4lon
committed
reduced dataset size
4lon
committed
reduced dataset size
4lon
committed
reduced dataset size
4lon
committed
reduced dataset size
4lon
committed
Added sample model outputs
4lon
committed
Added better sample model outputs
4lon
committed
Refactored training to seperate pixel cnn and vqvae in case of seperate training (this helps quite a bit with the memory problems of the dataset implementation.
4lon
committed
Fleshing out report
4lon
committed
Fleshing out report
4lon
committed
Add brain generating function but doesn't really work.
4lon
committed
Removed old attempt in pytorch and added snapshots of inference.
4lon
committed
Fixed up incorrect function call from refactor and add SSIM evaulation and recontruction to predict.py
4lon
committed
Finalising report
4lon
committed
Fixed reconstruction a bit
4lon
committed

Commits on Nov 24, 2022

Merge branch 'topic-recognition' into topic-recognition
4lon
authored
Delete recognition/44801582_OASIS_VAE/samples/pixelcnn_model directory
4lon
authored
Delete recognition/44801582_OASIS_VAE/samples/vqvae_model directory
4lon
authored
Delete pixelcnn_model_weights.h5
4lon
authored
Delete vqvae_model_weights.h5
4lon
authored

Footer

© 2026 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Community
Docs
Contact

You can’t perform that action at this time.