[source]

decode_predictions function¶

larq_zoo.decode_predictions(preds, top=5, **kwargs)

Decodes the prediction of an ImageNet model.

Argument

Arguments¶

preds: Numpy tensor encoding a batch of predictions. top: Integer, how many top-guesses to return.

Return

Returns¶

A list of lists of top class prediction tuples (class_name, class_description, score). One list of tuples per sample in batch input.

Raise

Raises¶

ValueError: In case of invalid shape of the pred array (must be 2D).

[source]

preprocess_input function¶

larq_zoo.preprocess_input(image)

Preprocesses a Tensor or Numpy array encoding a image.

Argument

Arguments¶

image: Numpy array or symbolic Tensor, 3D.

Return

Returns¶

Preprocessed Tensor or Numpy array.