ZeroPadding3D 层
ZeroPadding3D class
keras.layers.ZeroPadding3D(
padding=((1, 1), (1, 1), (1, 1)), data_format=None, **kwargs
)
零填充层,用于三维数据（空间或时空）.
示例:
>>> input_shape = (1, 1, 2, 2, 3)
>>> x = np.arange(np.prod(input_shape)).reshape(input_shape)
>>> y = keras.layers.ZeroPadding3D(padding=2)(x)
>>> y.shape
(1, 5, 6, 6, 3)
参数:
padding: 整数,或3个整数的元组,或3个2个整数的元组的元组.
- 如果为整数:相同的对称填充将应用于深度、高度和宽度.
- 如果为3个整数的元组:解释为深度、高度和宽度的三个不同的对称填充值:
(symmetric_dim1_pad, symmetric_dim2_pad, symmetric_dim3_pad).
- 如果为3个2个整数的元组的元组:解释为
((left_dim1_pad, right_dim1_pad), (left_dim2_pad,
right_dim2_pad), (left_dim3_pad, right_dim3_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"对应于形状为
(batch_size, spatial_dim1, spatial_dim2, spatial_dim3, channels)的输入
而"channels_first"对应于形状为
(batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3)的输入.
如果未指定,使用在~/.keras/keras.json中找到的image_data_format值（如果存在）.默认为
"channels_last".
输入形状:
形状为5D张量:
- 如果data_format为"channels_last":
(batch_size, first_axis_to_pad, second_axis_to_pad,
third_axis_to_pad, depth)
- 如果data_format为"channels_first":
(batch_size, depth, first_axis_to_pad, second_axis_to_pad,
third_axis_to_pad)
输出形状:
形状为5D张量:
- 如果data_format为"channels_last":
(batch_size, first_padded_axis, second_padded_axis,
third_axis_to_pad, depth)
- 如果data_format为"channels_first":
(batch_size, depth, first_padded_axis, second_padded_axis,
third_axis_to_pad)