synthval.features_extraction.InceptionExtractor#

class synthval.features_extraction.InceptionExtractor(model_id, get_probabilities=False)#

Bases: FeatureExtractor

Feature extractor using traditional Inception models from the timm library (https://huggingface.co/docs/timm/index). Supports batch processing and provides options to extract feature embeddings or class probabilities.

Parameters:

  • model_id (str)

  • get_probabilities (bool)

batch_feature_extraction(images)#

Extract features (or probabilities) from a batch of images using the Inception 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 (or probability vector) of an image.

Return type:

numpy.ndarray