layer_random_height {keras} | R Documentation |
Randomly vary the height of a batch of images during training
Description
Randomly vary the height of a batch of images during training
Usage
layer_random_height(
object,
factor,
interpolation = "bilinear",
seed = NULL,
...
)
Arguments
object |
What to compose the new
|
factor |
A positive float (fraction of original height), or a list of size 2
representing lower and upper bound for resizing vertically. When
represented as a single float, this value is used for both the upper and
lower bound. For instance, |
interpolation |
String, the interpolation method. Defaults to |
seed |
Integer. Used to create a random seed. |
... |
standard layer arguments. |
Details
Adjusts the height of a batch of images by a random factor. The input
should be a 3D (unbatched) or 4D (batched) tensor in the "channels_last"
image data format.
By default, this layer is inactive during inference.
See Also
Other image augmentation layers:
layer_random_brightness()
,
layer_random_contrast()
,
layer_random_crop()
,
layer_random_flip()
,
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_crop()
,
layer_random_flip()
,
layer_random_rotation()
,
layer_random_translation()
,
layer_random_width()
,
layer_random_zoom()
,
layer_rescaling()
,
layer_resizing()
,
layer_string_lookup()
,
layer_text_vectorization()