Image resizing layer

layer_resizing(
  object,
  height,
  width,
  interpolation = "bilinear",
  crop_to_aspect_ratio = FALSE,
  ...
)

Arguments

object

What to call the new Layer instance with. Typically a keras Model, another Layer, or a tf.Tensor/KerasTensor. If object is missing, the Layer instance is returned, otherwise, layer(object) is returned.

height

Integer, the height of the output shape.

width

Integer, the width of the output shape.

interpolation

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

crop_to_aspect_ratio

If TRUE, resize the images without aspect ratio distortion. When the original aspect ratio differs from the target aspect ratio, the output image will be cropped so as to return the largest possible window in the image (of size (height, width)) that matches the target aspect ratio. By default (crop_to_aspect_ratio = FALSE), aspect ratio may not be preserved.

...

standard layer arguments.

Details

Resize the batched image input to target height and width. The input should be a 4D (batched) or 3D (unbatched) tensor in "channels_last" format.

See also