CNTK：如何定义 UpSampling2D
CNTK: How to define UpSampling2D
我想知道如何在CNTK 中实现UpSampling2D。我在 API.
中找不到这样的图层
UpSampling2D是池化层的相反操作，通过重复数据的行和列来扩展数据。 UpSampling2D.
的 keras/tensorflow API
通过查看 tensorflow code, they use backend.resize_images operation, but I cannot find resize operation in CNTK API。
答案 1（来自 Frank）
答案 2（来自 David）
Picture from Quora: How do fully convolutional networks upsample their coarse output?
可以通过整形和拼接等基本操作组装而成，例如
>>> x = Input((3, 480, 640))
>>> xr = reshape(x, (3, 480, 1, 640, 1))
>>> xr.shape
(3, 480, 1, 640, 1)
>>> xx = splice(xr, xr, axis=-1) # axis=-1 refers to the last axis
>>> xx.shape
(3, 480, 1, 640, 2)
>>> xy = splice(xx, xx, axis=-3) # axis=-3 refers to the middle axis
>>> xy.shape
(3, 480, 2, 640, 2)
>>> r = reshape(xy, (3, 480*2, 640*2))
>>> r.shape
(3, 960, 1280)
我想知道如何在CNTK 中实现UpSampling2D。我在 API.
中找不到这样的图层UpSampling2D是池化层的相反操作，通过重复数据的行和列来扩展数据。 UpSampling2D.
的 keras/tensorflow API通过查看 tensorflow code, they use backend.resize_images operation, but I cannot find resize operation in CNTK API。
答案 1（来自 Frank）
答案 2（来自 David）
Picture from Quora: How do fully convolutional networks upsample their coarse output?
可以通过整形和拼接等基本操作组装而成，例如
>>> x = Input((3, 480, 640))
>>> xr = reshape(x, (3, 480, 1, 640, 1))
>>> xr.shape
(3, 480, 1, 640, 1)
>>> xx = splice(xr, xr, axis=-1) # axis=-1 refers to the last axis
>>> xx.shape
(3, 480, 1, 640, 2)
>>> xy = splice(xx, xx, axis=-3) # axis=-3 refers to the middle axis
>>> xy.shape
(3, 480, 2, 640, 2)
>>> r = reshape(xy, (3, 480*2, 640*2))
>>> r.shape
(3, 960, 1280)