UpSampling3D
类keras.layers.UpSampling3D(size=(2, 2, 2), data_format=None, **kwargs)
用于 3D 输入的上采样层。
分别将数据的第 1、第 2 和第 3 维重复 size[0]
、size[1]
和 size[2]
次。
示例
>>> input_shape = (2, 1, 2, 1, 3)
>>> x = np.ones(input_shape)
>>> y = keras.layers.UpSampling3D(size=(2, 2, 2))(x)
>>> y.shape
(2, 2, 4, 2, 3)
参数
"channels_last"
(默认)或 "channels_first"
。输入中维度顺序。"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,则使用 Keras 配置文件 ~/.keras/keras.json
(如果存在)中找到的 image_data_format
值,否则使用 "channels_last"
。默认为 "channels_last"
。输入形状
5D 张量,形状为:- 如果 data_format
为 "channels_last"
:(batch_size, dim1, dim2, dim3, channels)
- 如果 data_format
为 "channels_first"
:(batch_size, channels, dim1, dim2, dim3)
输出形状
5D 张量,形状为:- 如果 data_format
为 "channels_last"
:(batch_size, upsampled_dim1, upsampled_dim2, upsampled_dim3, channels)
- 如果 data_format
为 "channels_first"
:(batch_size, channels, upsampled_dim1, upsampled_dim2, upsampled_dim3)