Crop the central portion of the images to target height and width
layer_center_crop(object, height, width, ...)
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.
Integer, the height of the output shape.
Integer, the width of the output shape.
standard layer arguments.
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:
(..., target_height, target_width, channels)
.
If the input height/width is even and the target height/width is odd (or inversely), the input image is left-padded by 1 pixel.
https://www.tensorflow.org/api_docs/python/tf/keras/layers/CenterCrop
https://keras.io/api/layers/preprocessing_layers/image_preprocessing/center_crop
Other image preprocessing layers:
layer_rescaling()
,
layer_resizing()
Other preprocessing layers:
layer_category_encoding()
,
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_width()
,
layer_random_zoom()
,
layer_rescaling()
,
layer_resizing()
,
layer_string_lookup()
,
layer_text_vectorization()