tflite_support.task.vision.ImageEmbedder

Class that performs dense feature vector extraction on images.

tflite_support.task.vision.ImageEmbedder(
    options: tflite_support.task.vision.ImageEmbedderOptions,
    cpp_embedder: _CppImageEmbedder
) -> None

number_of_output_layers Gets the number of output layers of the model.
options

Methods

cosine_similarity

View source

cosine_similarity(
    u: tflite_support.task.processor.FeatureVector,
    v: tflite_support.task.processor.FeatureVector
) -> float

Computes cosine similarity [1] between two feature vectors.

create_from_file

View source

@classmethod
create_from_file(
    file_path: str
) -> 'ImageEmbedder'

Creates the ImageEmbedder object from a TensorFlow Lite model.

Args
file_path Path to the model.

Returns
ImageEmbedder object that's created from the model file.

Raises
ValueError If failed to create ImageEmbedder 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.ImageEmbedderOptions
) -> 'ImageEmbedder'

Creates the ImageEmbedder object from image embedder options.

Args
options Options for the image embedder task.

Returns
ImageEmbedder object that's created from options.

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

embed

View source

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

Performs actual feature vector extraction on the provided TensorImage.

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
The embedding result.

Raises
ValueError If any of the input arguments is invalid.
RuntimeError If failed to calculate the embedding vector.

get_embedding_by_index

View source

get_embedding_by_index(
    result: tflite_support.task.processor.EmbeddingResult,
    output_index: int
) -> tflite_support.task.processor.Embedding

Gets the embedding in the embedding result by output_index.

Args
result embedding result.
output_index output index of the output layer.

Returns
The Embedding output by the output_index'th layer. In (the most common) case where a single embedding is produced, you can just call get_feature_vector_by_index(result, 0).

Raises
ValueError if the output index is out of bound.

get_embedding_dimension

View source

get_embedding_dimension(
    output_index: int
) -> int

Gets the dimensionality of the embedding output.

Args
output_index The output index of output layer.

Returns
Dimensionality of the embedding output by the output_index'th output layer. Returns -1 if output_index is out of bounds.