TF之data_format:data_format中的NHWC&NCHW简介、转换的详细攻略
目录
NHWC&NCHW简介
NHWC&NCHW转换
NHWC&NCHW简介
NHWC & NCHW是两种参数呈现的表达方式。在如何表示一组彩色图片的问题上,不同的DL框架有不同的表达。
形式适合的框架NHWC
channels_first
[batch, in_height, in_width, in_channels]
批量批次、高度、宽度、通道数
TensorFlowNCHW
channels_last
[batch, in_channels, in_height, in_width]
批量批次、通道数、高度、宽度
Theano、CaffeNHWC&NCHW转换
1、NHWC → NCHW
import tensorflow as tf
x = tf.reshape(tf.range(24), [1, 3, 4, 2])
out = tf.transpose(x, [0, 3, 1, 2])
print(x.shape)
print(out.shape)
(1, 3, 4, 2)
(1, 2, 3, 4)
2、NCHW → NHWC
import tensorflow as tf
x = tf.reshape(tf.range(24), [1, 2, 3, 4])
out = tf.transpose(x, [0, 2, 3, 1])
print(x.shape)
print(out.shape)
(1, 2, 3, 4)
(1, 3, 4, 2)