A preprocessing layer which randomly zooms images during training.

This layer will randomly zoom in or out on each axis of an image independently, filling empty space according to fill_mode.

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

Usage

layer_random_zoom(
  object,
  height_factor,
  width_factor = NULL,
  fill_mode = "reflect",
  interpolation = "bilinear",
  seed = NULL,
  fill_value = 0,
  data_format = NULL,
  ...
)

Arguments

object

Object to compose the layer with. A tensor, array, or sequential model.

height_factor

a float represented as fraction of value, or a list of size 2 representing lower and upper bound for zooming vertically. When represented as a single float, this value is used for both the upper and lower bound. A positive value means zooming out, while a negative value means zooming in. For instance, height_factor=c(0.2, 0.3) result in an output zoomed out by a random amount in the range [+20%, +30%]. height_factor=c(-0.3, -0.2) result in an output zoomed in by a random amount in the range [+20%, +30%].

width_factor

a float represented as fraction of value, or a list of size 2 representing lower and upper bound for zooming horizontally. When represented as a single float, this value is used for both the upper and lower bound. For instance, width_factor=c(0.2, 0.3) result in an output zooming out between 20% to 30%. width_factor=c(-0.3, -0.2) result in an output zooming in between 20% to 30%. NULL means i.e., zooming vertical and horizontal directions by preserving the aspect ratio. Defaults to NULL.

fill_mode

Points outside the boundaries of the input are filled according to the given mode. Available methods are "constant", "nearest", "wrap" and "reflect". Defaults to "constant".

"reflect": (d c b a | a b c d | d c b a) The input is extended by reflecting about the edge of the last pixel.
"constant": (k k k k | a b c d | k k k k) The input is extended by filling all values beyond the edge with the same constant value k specified by fill_value.
"wrap": (a b c d | a b c d | a b c d) The input is extended by wrapping around to the opposite edge.
"nearest": (a a a a | a b c d | d d d d) The input is extended by the nearest pixel. Note that when using torch backend, "reflect" is redirected to "mirror" (c d c b | a b c d | c b a b) because torch does not support "reflect". Note that torch backend does not support "wrap".

interpolation

Interpolation mode. Supported values: "nearest", "bilinear".

seed

Integer. Used to create a random seed.

fill_value

a float that represents the value to be filled outside the boundaries when fill_mode="constant".

data_format

string, either "channels_last" or "channels_first". The ordering of the dimensions in the inputs. "channels_last" corresponds to inputs with shape (batch, height, width, channels) while "channels_first" corresponds to inputs with shape (batch, channels, height, width). It defaults to the image_data_format value found in your Keras config file at ~/.keras/keras.json. If you never set it, then it will be "channels_last".

...

Base layer keyword arguments, such as name and dtype.

Value

The return value depends on the value provided for the first argument. If object is:

a keras_model_sequential(), then the layer is added to the sequential model (which is modified in place). To enable piping, the sequential model is also returned, invisibly.
a keras_input(), then the output tensor from calling layer(input) is returned.
NULL or missing, then a Layer instance is returned.

Input Shape

3D (unbatched) or 4D (batched) tensor with shape: (..., height, width, channels), in "channels_last" format, or (..., channels, height, width), in "channels_first" format.

Output Shape

3D (unbatched) or 4D (batched) tensor with shape: (..., target_height, target_width, channels), or (..., channels, target_height, target_width), in "channels_first" format.

Note: This layer is safe to use inside a tf.data pipeline (independently of which backend you're using).

Examples

input_img <- random_uniform(c(32, 224, 224, 3))
layer <- layer_random_zoom(height_factor = .5, width_factor = .2)
out_img <- layer(input_img)

Other preprocessing layers:
layer_category_encoding()
layer_center_crop()
layer_discretization()
layer_feature_space()
layer_hashed_crossing()
layer_hashing()
layer_integer_lookup()
layer_mel_spectrogram()
layer_normalization()
layer_random_brightness()
layer_random_contrast()
layer_random_crop()
layer_random_flip()
layer_random_rotation()
layer_random_translation()
layer_rescaling()
layer_resizing()
layer_string_lookup()
layer_text_vectorization()

Other layers:
Layer()
layer_activation()
layer_activation_elu()
layer_activation_leaky_relu()
layer_activation_parametric_relu()
layer_activation_relu()
layer_activation_softmax()
layer_activity_regularization()
layer_add()
layer_additive_attention()
layer_alpha_dropout()
layer_attention()
layer_average()
layer_average_pooling_1d()
layer_average_pooling_2d()
layer_average_pooling_3d()
layer_batch_normalization()
layer_bidirectional()
layer_category_encoding()
layer_center_crop()
layer_concatenate()
layer_conv_1d()
layer_conv_1d_transpose()
layer_conv_2d()
layer_conv_2d_transpose()
layer_conv_3d()
layer_conv_3d_transpose()
layer_conv_lstm_1d()
layer_conv_lstm_2d()
layer_conv_lstm_3d()
layer_cropping_1d()
layer_cropping_2d()
layer_cropping_3d()
layer_dense()
layer_depthwise_conv_1d()
layer_depthwise_conv_2d()
layer_discretization()
layer_dot()
layer_dropout()
layer_einsum_dense()
layer_embedding()
layer_feature_space()
layer_flatten()
layer_flax_module_wrapper()
layer_gaussian_dropout()
layer_gaussian_noise()
layer_global_average_pooling_1d()
layer_global_average_pooling_2d()
layer_global_average_pooling_3d()
layer_global_max_pooling_1d()
layer_global_max_pooling_2d()
layer_global_max_pooling_3d()
layer_group_normalization()
layer_group_query_attention()
layer_gru()
layer_hashed_crossing()
layer_hashing()
layer_identity()
layer_integer_lookup()
layer_jax_model_wrapper()
layer_lambda()
layer_layer_normalization()
layer_lstm()
layer_masking()
layer_max_pooling_1d()
layer_max_pooling_2d()
layer_max_pooling_3d()
layer_maximum()
layer_mel_spectrogram()
layer_minimum()
layer_multi_head_attention()
layer_multiply()
layer_normalization()
layer_permute()
layer_random_brightness()
layer_random_contrast()
layer_random_crop()
layer_random_flip()
layer_random_rotation()
layer_random_translation()
layer_repeat_vector()
layer_rescaling()
layer_reshape()
layer_resizing()
layer_rnn()
layer_separable_conv_1d()
layer_separable_conv_2d()
layer_simple_rnn()
layer_spatial_dropout_1d()
layer_spatial_dropout_2d()
layer_spatial_dropout_3d()
layer_spectral_normalization()
layer_string_lookup()
layer_subtract()
layer_text_vectorization()
layer_tfsm()
layer_time_distributed()
layer_torch_module_wrapper()
layer_unit_normalization()
layer_upsampling_1d()
layer_upsampling_2d()
layer_upsampling_3d()
layer_zero_padding_1d()
layer_zero_padding_2d()
layer_zero_padding_3d()
rnn_cell_gru()
rnn_cell_lstm()
rnn_cell_simple()
rnn_cells_stack()