Skip to content

v0.5.0
Compare
Choose a tag to compare
@nmichlo nmichlo released this 01 Apr 01:00
· 45 commits to main since this release
v0.5.0
2540a5e

This release marks the end of my MSc. and splitting the research out into its own repository!

  • The repo was previously setup such that development took place on an xdev branch. An automated script was then used to clean this branch of research code and commit the changes to the dev branch, which was then published.
  • This has now been disabled in favour of standard dev practice. I no longer need to maintain the old research code and can incorporate this functionality directly into disent.

MSc. Additions

  • disent.dataset.data - Various new datasets!

    • XYObjectData and XYObjectShadedData equivalent datasets with different representations of their ground-truth factors. Disentanglement performance is affected by the choice of ground-truth factors even if the data is exactly the same!
    • XYSquaresData is an adversarial dataset for VAEs that use pixel-wise reconstruction losses. VAEs usually perform terribly on this dataset in terms of disentanglement performance. This dataset contains three squares that can move across a non-overlapping grid.
    • XYSingleSquareData is like XYSquaresData but only has a single square that can move across the image.
    • XColumnsData is a simplistic version of XYSquaresData that is still adversarial, but only moves columns left and right instead of an object across a grid.

  • disent.frameworks.vae

    • AdaNegTripletVae aka. "ada_tvae": Supervised disentanglement framework that uses our proposed Adaptive Triplet Loss to disentangle representations and introduce axis-alignment. Triplets are constructed using the L1 distance between ground-truth factors.
    • DataOverlapTripletVae aka. "ada_tvae_d": Unsupervised version of the AdaNegTripletVae that order triplets using the distances between datapoints in terms of the reconstruction loss. Distances within disentanglement datasets often correspond to the distances between ground-truth factors, suggesting disentanglement is accidental!

  • disent.frameworks.ae

    • AdaNegTripletAe aka. "ada_tae" - The AE version of AdaNegTripletVae
    • DataOverlapTripletAe aka. "ada_tae_d" - The AE version of DataOverlapTripletVae
    • AdaAe - The AE version of the AdaVae

  • disent.metrics

    • flatness_components consists of three separate metrics
      • distances: measure the rank correlation between ground-truth distances and latent distances
      • linearity: measure how well factor traversal embeddings lie on an arbitrarily rotated n-dimensional line
      • axis-alignment: measure how well factor traversal embeddings correspond to a single latent variable (ie. an n-dimensional line that is axis-aligned).
    • flatness an older metric that measures the path length of factor traversal embeddings over the max distance between points.

  • experiment/configs updated to included configs for all the added classes, frameworks, datasets, metrics and features!

    • new schedules schedule/adanegtvae_*.yaml that should be used with the Adaptive Triplet frameworks. Otherwise these frameworks do not learn.

MSc. Removals

  • All the remaining research code contained in research/* has been deleted

Add Examples

  • Added an example docs/examples/extend_experiment of how to override or extend the disent experiment conifigs! This is useful for creating your own research!
  • Added an example of plotting various aspects of disent docs/examples/plotting_examples.

Fixes

  • Fixed tests for new locations
  • Added appropriate entries to the registry
Assets 2
Loading