THINGSvision Versions Save

Python package for extracting representations from state-of-the-art computer vision models

v2.6.0

3 weeks ago
  • added support for torch>=2.0.0 and torchvision=0.15.* (fixes issue #165)
  • implemented CKA in both NumPy and PyTorch (PyTorch runs 2x faster than NumPy)
  • added CUDA support for CKA in PyTorch (100x faster than CKA in NumPy)
  • added new function called get_cka where the user can set the backend (torch or numpy); function returns the CKA object
  • added an unbiased CKA variant (from here) in addition to vanilla CKA

v2.5.3

1 month ago
  • improved the efficiency of batch-wise feature extraction (with custom data pipeline)
  • added pretrained MAEs to the thingsvision model collection

v2.5.2

1 month ago
  • efficient batch-wise feature extraction (using a with statement for PyTorch models) for custom data pipeline

v2.5.1

1 month ago
  • added a public batch-wise extraction method to the feature extractor (for custom dataset and data loader classes)
  • updated README and docs with explanations about how and when to use the mini-batch extraction method
  • small bug fixes and refactorings

v2.5.0

1 month ago
  • added method to extractor class for aligning representations using gLocal
  • small bug fixes and refactoring

v2.4.2

1 month ago
  • new DreamSim models
  • support for CLS token extraction for supervised ViTs

v2.4.1

9 months ago
  • fixed import issues with DINO models
  • improved unittests
  • enhanced modularity of codebase

v2.3.18

9 months ago
  • integrated DreamSim models into thingsvision
  • small changes to the codebase (more modularity)
  • minor refactors

v2.3.17

10 months ago
  • memory fixes

v2.3.14

1 year ago
  • adapted Command Line Interface (CLI) to the most recent changes in the library (see v2.3)
  • added automatic device checks