Cropping layer for 1D input (e.g. temporal sequence).
View aliases
Compat aliases for migration
See Migration guide for more details.
`tf.compat.v1.keras.layers.Cropping1D`
tf.keras.layers.Cropping1D(
cropping=(1, 1), **kwargs
)
It crops along the time dimension (axis 1).
Examples:
input_shape = (2, 3, 2)
x = np.arange(np.prod(input_shape)).reshape(input_shape)
print(x)
[[[ 0 1]
[ 2 3]
[ 4 5]]
[[ 6 7]
[ 8 9]
[10 11]]]
y = tf.keras.layers.Cropping1D(cropping=1)(x)
print(y)
tf.Tensor(
[[[2 3]]
[[8 9]]], shape=(2, 1, 2), dtype=int64)
Input shape | |
---|---|
3D tensor with shape (batch_
|
Output shape | |
---|---|
3D tensor with shape (batch_size, cropped_axis, features)
|