在 TensorFlow 中在 NHWC 和 NCHW 之间转换

Question

将张量从 NHWC 格式转换为 NCHW 格式，反之亦然的最佳方法是什么？

是否有专门执行此操作的操作，或者我是否需要使用 split/concat 类型操作的某种组合？

Answer 1

您需要做的就是将维度从 NHWC 排列到 NCHW（或相反）。

每个字母的含义可能有助于理解：

N: 批处理中的图像数量
H: 图片的高度
W: 图片的宽度
C：图像的通道数（例如：RGB 为 3，灰度为 1...）

从 NHWC 到 NCHW

图像的形状是 (N, H, W, C)，我们希望输出的形状是 (N, C, H, W)。因此，我们需要应用 tf.transpose 并精心选择排列 perm.

The returned tensor's dimension i will correspond to the input dimension perm[i]

perm[0] = 0  # output dimension 0 will be 'N', which was dimension 0 in the input
perm[1] = 3  # output dimension 1 will be 'C', which was dimension 3 in the input
perm[2] = 1  # output dimension 2 will be 'H', which was dimension 1 in the input
perm[3] = 2  # output dimension 3 will be 'W', which was dimension 2 in the input

实践中：

images_nhwc = tf.placeholder(tf.float32, [None, 200, 300, 3])  # input batch
out = tf.transpose(images_nhwc, [0, 3, 1, 2])
print(out.get_shape())  # the shape of out is [None, 3, 200, 300]

从 NCHW 到 NHWC

图像形状为 (N, C, H, W)，我们希望输出的形状为 (N, H, W, C)。因此，我们需要应用 tf.transpose 并精心选择排列 perm.

The returned tensor's dimension i will correspond to the input dimension perm[i]

perm[0] = 0  # output dimension 0 will be 'N', which was dimension 0 in the input
perm[1] = 2  # output dimension 1 will be 'H', which was dimension 2 in the input
perm[2] = 3  # output dimension 2 will be 'W', which was dimension 3 in the input
perm[3] = 1  # output dimension 3 will be 'C', which was dimension 1 in the input

实践中：

images_nchw = tf.placeholder(tf.float32, [None, 3, 200, 300])  # input batch
out = tf.transpose(images_nchw, [0, 2, 3, 1])
print(out.get_shape())  # the shape of out is [None, 200, 300, 3]

Answer 2

将'NCHW'转换为'NHWC'

from keras import backend
backend.set_image_data_format('channels_last') #channels_first for NCHW

在 TensorFlow 中在 NHWC 和 NCHW 之间转换

Convert between NHWC and NCHW in TensorFlow

tensorflow

从 NHWC 到 NCHW

从 NCHW 到 NHWC