在TensorFlow

Question

将张量从NHWC格式转换为NCHW格式的最佳方法是什么，反之亦然？

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

Answer 1

您需要做的就是从NHWC到NCHW（或相反）的尺寸排列。

每封信的含义可能有助于理解：

• N ：批次中的图片数量
• H ：图片的高度
• W ：图片的宽度
• C ：图像的通道数（例如：3表示RGB，1表示灰度......）

从NHWC到NCHW

图像形状为(N, H, W, C)，我们希望输出具有形状(N, C, H, W)。因此，我们需要将tf.transpose应用于选择良好的排列perm。

  

返回张量的维度i将对应于输入维度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

在实践中：

images_nhwc = tf.placeholder(tf.float32, [None, 200, 300, 3])  # input batch
out = tf.transpose(x, [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)，我们希望输出具有形状(N, H, W, C)。因此，我们需要将tf.transpose应用于选择良好的排列perm。

  

返回张量的维度i将对应于输入维度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

在实践中：

images_nchw = tf.placeholder(tf.float32, [None, 3, 200, 300])  # input batch
out = tf.transpose(x, [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