v2.4.1

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

v2.3.18

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

v2.3.17

• memory fixes

v2.3.14

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

v2.3

• added possibility to easily extract features from harmonized models from the Harmonization repo
• added various DINO models to the available ssl models
• fixed dependency issues for custom models

v2.2.24

• added tests for custom model extractor and refactored torch and tensorflow extractor classes

v2.2.23

• added various DINO SSL models to thingsvision (weights retrieved from torch.hub)

v2.2.22

• added output_type option for choosing between torch.Tensor and np.ndarray for type of returned features in extractor.extract_features(...) for substantial speed-ups during the extraction process (moving tensors to CPU is costly which is why we want to avoid it wherever possible)
• note that the above is only possible for backend="pt" (not for backend="tf")

v2.2.21

• added output_type option for choosing between torch.Tensor and np.ndarray for type of returned features in extractor.extract_features(...) for substantial speed-ups during the extraction process (moving tensors to CPU is costly which is why we want to avoid it wherever possible)
• note that the above is only possible for backend="pt"

v2.2.18

• memory issue fixes
• abstract base class
• removed mixin classes