ZeroPadding1D 层
ZeroPadding1D class
keras.layers.ZeroPadding1D(padding=1, data_format=None, **kwargs)
零填充层,用于一维输入（例如时间序列）.
示例:
>>> input_shape = (2, 2, 3)
>>> x = np.arange(np.prod(input_shape)).reshape(input_shape)
>>> x
[[[ 0 1 2]
[ 3 4 5]]
[[ 6 7 8]
[ 9 10 11]]]
>>> y = keras.layers.ZeroPadding1D(padding=2)(x)
>>> y
[[[ 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]]]
参数:
padding: 整数,或包含两个整数的元组,或字典.
- 如果为整数:在填充维度（轴1）的开始和结束处添加多少个零.
- 如果为包含两个整数的元组:在填充维度的开始和结束处添加多少个零（(left_pad, right_pad)）.
data_format: 字符串,取值为 "channels_last"（默认）或 "channels_first".输入中维度的顺序.
"channels_last" 对应输入形状为 (batch_size, axis_to_pad, channels),而 "channels_first" 对应输入形状为 (batch_size, channels, axis_to_pad).
如果未指定,则使用在 ~/.keras/keras.json 文件中找到的 image_data_format 值（如果存在）.默认为 "channels_last".
输入形状:
形状为以下之一的3D张量:
- 如果 data_format 为 "channels_last":
(batch_size, axis_to_pad, features)
- 如果 data_format 为 "channels_first":
(batch_size, features, axis_to_pad)
输出形状:
形状为以下之一的3D张量:
- 如果 data_format 为 "channels_last":
(batch_size, padded_axis, features)
- 如果 data_format 为 "channels_first":
(batch_size, features, padded_axis)