在TensorFlow中转换NHWC和NCHW

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？

是否有专门用于执行此操作的操作,或者我是否需要使用split/concat类型操作的某些组合？

Answer 1

您需要做的就是从NHWC到NCHW(或相反)的尺寸排列.

每个字母的含义可能有助于理解:

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

从NHWC到NCHW

图像形状是(N, H, W, C),我们希望输出具有形状(N, C, H, W).因此,我们需要应用tf.transpose精心选择的排列perm.

返回的张量维度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

图像形状是(N, C, H, W),我们希望输出具有形状(N, H, W, C).因此,我们需要应用tf.transpose精心选择的排列perm.

返回的张量维度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]