tf.keras.layers.RandomCrop

A preprocessing layer which randomly crops images during training.

Inherits From: Layer, Module

tf.keras.layers.RandomCrop(
    height, width, seed=None, **kwargs
)

During training, this layer will randomly choose a location to crop images down to a target size. The layer will crop all the images in the same batch to the same cropping location.

At inference time, and during training if an input image is smaller than the target size, the input will be resized and cropped so as to return the largest possible window in the image that matches the target aspect ratio. If you need to apply random cropping at inference time, set training to True when calling the layer.

Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats.

For an overview and full list of preprocessing layers, see the preprocessing guide.

3D unbatched) or 4D (batched) tensor with shape

(..., height, width, channels), in "channels_last" format.

3D unbatched) or 4D (batched) tensor with shape

(..., target_height, target_width, channels).

height Integer, the height of the output shape.
width Integer, the width of the output shape.
seed Integer. Used to create a random seed.

auto_vectorize Control whether automatic vectorization occurs.

By default the call() method leverages the tf.vectorized_map() function. Auto-vectorization can be disabled by setting self.auto_vectorize = False in your __init__() method. When disabled, call() instead relies on tf.map_fn(). For example:

class SubclassLayer(BaseImageAugmentationLayer):
  def __init__(self):
    super().__init__()
    self.auto_vectorize = False