UpSampling1D层
UpSampling1D class
keras.layers.UpSampling1D(size=2, **kwargs)
一维输入的上采样层.
沿时间轴将每个时间步重复 size 次.
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.UpSampling1D(size=2)(x)
>>> y
[[[ 0. 1. 2.]
[ 0. 1. 2.]
[ 3. 4. 5.]
[ 3. 4. 5.]]
[[ 6. 7. 8.]
[ 6. 7. 8.]
[ 9. 10. 11.]
[ 9. 10. 11.]]]
参数: size: 整数.上采样因子.
输入形状:
形状为 (batch_size, steps, features) 的 3D 张量.
输出形状:
形状为 (batch_size, upsampled_steps, features) 的 3D 张量.