layer_random_width: Randomly vary the width of a batch of images during training

View source: R/layers-preprocessing.R

layer_random_widthR Documentation

Randomly vary the width of a batch of images during training

Description

Randomly vary the width of a batch of images during training

Usage

layer_random_width(
  object,
  factor,
  interpolation = "bilinear",
  seed = NULL,
  ...
)

Arguments

object

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.

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, factor = c(0.2, 0.3) results in an output with width changed by a random amount in the range ⁠[20%, 30%]⁠. ⁠factor=(-0.2, 0.3)⁠ results in an output with width changed by a random amount in the range ⁠[-20%, +30%]⁠. factor = 0.2 results in an output with width changed by a random amount in the range ⁠[-20%, +20%]⁠.

interpolation

String, the interpolation method. Defaults to bilinear. Supports "bilinear", "nearest", "bicubic", "area", "lanczos3", "lanczos5", "gaussian", "mitchellcubic".

seed

Integer. Used to create a random seed.

...

standard layer arguments.

Details

Adjusts the width 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_height(), layer_random_rotation(), layer_random_translation(), 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_height(), layer_random_rotation(), layer_random_translation(), layer_random_zoom(), layer_rescaling(), layer_resizing(), layer_string_lookup(), layer_text_vectorization()


keras documentation built on May 29, 2024, 3:20 a.m.