tflite_support.task.vision.TensorImage

Wrapper class for the Image object.

tflite_support.task.vision.TensorImage(
    image_data: image_utils.ImageData, is_from_numpy_array: bool = True
) -> None

image_data image_utils.ImageData, contains raw image data, width, height and channels info.
is_from_numpy_array boolean, whether image_data is loaded from numpy array. if False, it means that image_data is loaded from stbi_load** function in C++ and need to free the storage of ImageData in the destructor.

buffer Gets the numpy array that represents self.image_data.
color_space_type Gets the color space type of the image.
height Gets the height of the image.
width Gets the width of the image.

Methods

create_from_array

View source

@classmethod
create_from_array(
    array: np.ndarray
) -> 'TensorImage'

Creates TensorImage object from the numpy array.

Args
array numpy array with dtype=uint8. Its shape should be either (h, w, 3) or (1, h, w, 3) for RGB images, either (h, w) or (1, h, w) for GRAYSCALE images and either (h, w, 4) or (1, h, w, 4) for RGBA images.

Returns
TensorImage object.

Raises
ValueError if the dytype of the numpy array is not uint8 or the dimention is not the valid dimention.

create_from_buffer

View source

@classmethod
create_from_buffer(
    buffer: str
) -> 'TensorImage'

Creates TensorImage object from the binary buffer.

Args
buffer Binary memory buffer.

Returns
TensorImage object.

Raises
RuntimeError if the binary buffer can't be decoded into TensorImage object.

create_from_file

View source

@classmethod
create_from_file(
    file_name: str
) -> 'TensorImage'

Creates TensorImage object from the image file.

Args
file_name Image file name.

Returns
TensorImage object.

Raises
RuntimeError if the image file can't be decoded.