synthval.features_extraction.MambaFeatureExtractor

class synthval.features_extraction.MambaFeatureExtractor(model_id)

Bases: FeatureExtractor

Feature extractor using models from the HuggingFace MambaVision family (https://huggingface.co/collections/nvidia/mambavision-66943871a6b36c9e78b327d3).

Note: MambaVision models require a CUDA-enabled environment and the installation of specific packages. To use these models as feature extractors, users must have CUDA installed and install the necessary packages by running pip install mambavision.

Parameters:

model_id (str)

batch_feature_extraction(images)

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

Parameters:

images (List[PIL.Image.Image]) – List of PIL images to extract features from.

Returns:

A NumPy array where each row corresponds to the feature vector of an image.

Return type:

numpy.ndarray