tflite_support.task.vision.ImageSearcher

Class to performs image search.

tflite_support.task.vision.ImageSearcher(
    options: tflite_support.task.vision.ImageSearcherOptions,
    cpp_searcher: _CppImageSearcher
) -> None

It works by performing embedding extraction on images, followed by nearest-neighbor search in an index of embeddings through ScaNN.

options

Methods

create_from_file

View source

@classmethod
create_from_file(
    model_file_path: str, index_file_path: Optional[str] = None
) -> 'ImageSearcher'

Creates the ImageSearcher object from a TensorFlow Lite model.

Args
model_file_path Path to the model.
index_file_path Path to the index. Only required if the index is not attached to the output tensor metadata as an AssociatedFile with type SCANN_INDEX_FILE.

Returns
ImageSearcher object that's created from options.

Raises
ValueError If failed to create ImageSearcher object from the provided file such as invalid file.
RuntimeError If other types of error occurred.

create_from_options

View source

@classmethod
create_from_options(
    options: tflite_support.task.vision.ImageSearcherOptions
) -> 'ImageSearcher'

Creates the ImageSearcher object from image searcher options.

Args
options Options for the image searcher task.

Returns
ImageSearcher object that's created from options.

Raises
ValueError If failed to create ImageSearcher object from ImageSearcherOptions such as missing the model.
RuntimeError If other types of error occurred.

get_user_info

View source

get_user_info() -> str

Gets the user info stored in the index file.

Returns
Opaque user info stored in the index file (if any), in raw binary form. Returns an empty string if the index doesn't contain user info.

View source

search(
    image: tflite_support.task.vision.TensorImage,
    bounding_box: Optional[tflite_support.task.processor.BoundingBox] = None
) -> tflite_support.task.processor.SearchResult

Search for image with similar semantic meaning.

This method performs actual feature extraction on the provided image input, followed by nearest-neighbor search in the index.

Args
image Tensor image, used to extract the feature vectors.
bounding_box Bounding box, optional. If set, performed feature vector extraction only on the provided region of interest. Note that the region of interest is not clamped, so this method will fail if the region is out of bounds of the input image.

Returns
Search result.

Raises
ValueError If any of the input arguments is invalid.
RuntimeError If failed to perform nearest-neighbor search.