Randomly flip each image horizontally and vertically
layer_random_flip(object, mode = "horizontal_and_vertical", seed = NULL, ...)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.
String indicating which flip mode to use. Can be "horizontal",
"vertical", or "horizontal_and_vertical". Defaults to
"horizontal_and_vertical". "horizontal" is a left-right flip and
"vertical" is a top-bottom flip.
Integer. Used to create a random seed.
standard layer arguments.
This layer will flip the images based on the mode attribute.
During inference time, the output will be identical to input. Call the layer
with training = TRUE to flip the input.
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:
(..., height, width, channels), in "channels_last" format.
https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomFlip
https://keras.io/api/layers/preprocessing_layers/image_augmentation/random_flip
Other image augmentation layers:
layer_random_contrast(),
layer_random_crop(),
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_contrast(),
layer_random_crop(),
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()