zensvi.cv.Embeddings
====================

.. py:class:: zensvi.cv.Embeddings(model_name: str = 'resnet-18', cuda: bool = False, tensor: bool = True, verbosity: int = 1)

   A class for extracting image embeddings using pre-trained models.


   .. py:method:: load_image(image_path)

      Load and preprocess an image from a file path.

      :param image_path: Path to the image file.

      :returns: Loaded and resized image.
      :rtype: PIL.Image



   .. py:method:: get_model_and_layer()

      Get the pre-trained model and extraction layer.

      :returns:

                Contains:
                    - torch.nn.Module: The pre-trained model
                    - torch.nn.Module: The extraction layer
      :rtype: tuple



   .. py:method:: get_image_embedding(image_path: Union[List[str], str], tensor: bool = None, cuda: bool = None)

      Extract embedding for a single image.

      :param image_path: Path to the image file.
      :param tensor: Whether to return the embedding as a PyTorch tensor.
                     If None, uses the instance default.
      :param cuda: Whether to use CUDA for computation.
                   If None, uses the instance default.

      :returns: The image embedding.
      :rtype: Union[torch.Tensor, numpy.ndarray]



   .. py:method:: generate_embedding(images_path: Union[List[str], str], dir_embeddings_output: str, batch_size: int = 100, maxWorkers: int = 8, verbosity: int = None)

      Generate and save embeddings for multiple images.

      :param images_path: Either a directory path containing images or a list of image paths.
      :param dir_embeddings_output: Directory where embeddings will be saved as parquet files.
      :param batch_size: Number of images to process in each batch. Default is 100.
      :param maxWorkers: Maximum number of worker threads for image processing. Default is 8.
      :param verbosity: Level of verbosity for progress bars.
                        0 = no progress bars, 1 = outer loops only, 2 = all loops.
                        If None, uses the instance's verbosity level.

      :returns: True if embeddings were successfully generated and saved.
      :rtype: bool



   .. py:method:: search_similar_images(image_key: str, embeddings_dir: str, number_of_items: int = 10)

      Search for similar images using embeddings.

      :param image_key: Key of the query image.
      :param embeddings_dir: Directory containing the embeddings parquet file.
      :param number_of_items: Number of similar images to return. Default is 10.

      :returns: List of tuples containing (similarity_score, image_key, image_filename).
      :rtype: list



   .. py:method:: get_all_models()

      Get all the available models.

      :returns: Dictionary of available models with their configurations.
      :rtype: dict