Randomly crop the images to target height and width
layer_random_crop(object, height, width, seed = NULL, ...)
What to compose the new Layer
instance with. Typically a
Sequential model or a Tensor (e.g., as returned by layer_input()
).
The return value depends on object
. If object
is:
missing or NULL
, the Layer
instance is returned.
a Sequential
model, the model with an additional layer is returned.
a Tensor, the output tensor from layer_instance(object)
is returned.
Integer, the height of the output shape.
Integer, the width of the output shape.
Integer. Used to create a random seed.
standard layer arguments.
This layer will crop all the images in the same batch to the same cropping
location.
By default, random cropping is only applied during training. At inference
time, the images will be first rescaled to preserve the shorter side, and
center cropped. If you need to apply random cropping at inference time,
set training
to TRUE
when calling the layer.
Input shape:
3D (unbatched) or 4D (batched) tensor with shape:
(..., height, width, channels)
, in "channels_last"
format.
Output shape:
3D (unbatched) or 4D (batched) tensor with shape:
(..., target_height, target_width, channels)
.
https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomCrop
https://keras.io/api/layers/preprocessing_layers/image_augmentation/random_crop
Other image augmentation layers:
layer_random_brightness()
,
layer_random_contrast()
,
layer_random_flip()
,
layer_random_height()
,
layer_random_rotation()
,
layer_random_translation()
,
layer_random_width()
,
layer_random_zoom()
Other preprocessing layers:
layer_category_encoding()
,
layer_center_crop()
,
layer_discretization()
,
layer_hashing()
,
layer_integer_lookup()
,
layer_normalization()
,
layer_random_brightness()
,
layer_random_contrast()
,
layer_random_flip()
,
layer_random_height()
,
layer_random_rotation()
,
layer_random_translation()
,
layer_random_width()
,
layer_random_zoom()
,
layer_rescaling()
,
layer_resizing()
,
layer_string_lookup()
,
layer_text_vectorization()