tf.contrib.slim.conv2d 与 tf.nn.conv2d 区别

一般会

import tf.contrib.slim as slim

slim.conv2d

slim.conv2d(inputs, num_outputs, kernel_size, stride = 1, padding = 'SAME')
#其中kernel_size为int单个整数形式,一般为1或3,高与宽都是此数。

tf.nn.conv2d

tf.nn.conv2d(inputs, filter = [height, width, channels, num_outputs], strides=[1,stride,stride,1],padding)
#stride为x轴与y轴方向的步长,一般相同

你可能感兴趣的:(python,tensorflow)