synthval.features_extraction.DinoV2FeatureExtractor
===================================================

.. py:class:: synthval.features_extraction.DinoV2FeatureExtractor(model_id)

   Bases: :py:obj:`FeatureExtractor`


   Feature extractor using models from the HuggingFace DinoV2 family
   (https://huggingface.co/collections/facebook/dinov2-6526c98554b3d2576e071ce3).

   Note: As of December 16, 2024, Dino models utilize the operator `aten::upsample_bicubic2d.out`,
   which is not currently supported on the MPS backend. To use these models as feature extractors
   on MPS, users must set the environment variable `PYTORCH_ENABLE_MPS_FALLBACK` to `1`.


   .. py:method:: batch_feature_extraction(images)

      Extract features from a batch of images using the HuggingFace DinoV2 model.

      :param images: List of PIL images to extract features from.
      :type images: List[PIL.Image.Image]

      :returns: A NumPy array where each row corresponds to the feature vector of an image.
      :rtype: numpy.ndarray