TensorFlow 1 version | View source on GitHub |
Zero-padding layer for 1D input (e.g. temporal sequence).
tf.keras.layers.ZeroPadding1D(
padding=1, **kwargs
)
Examples:
input_shape = (2, 2, 3)
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.ZeroPadding1D(padding=2)(x)
print(y)
tf.Tensor(
[[[ 0 0 0]
[ 0 0 0]
[ 0 1 2]
[ 3 4 5]
[ 0 0 0]
[ 0 0 0]]
[[ 0 0 0]
[ 0 0 0]
[ 6 7 8]
[ 9 10 11]
[ 0 0 0]
[ 0 0 0]]], shape=(2, 6, 3), dtype=int64)
Arguments | |
---|---|
padding
|
Int, or tuple of int (length 2), or dictionary.
|
Input shape:
3D tensor with shape (batch_size, axis_to_pad, features)
Output shape:
3D tensor with shape (batch_size, padded_axis, features)