Inception的输出shape

来源:4-6 Inception-mobile_net(1)

算法工程大神

2021-07-14

conv1 = tf.layers.conv2d(x_image,
32, # output channel number
(3,3), # kernel size
padding = ‘same’,
activation = tf.nn.relu,
name = ‘conv1’)

pooling1 = tf.layers.max_pooling2d(conv1,
(2, 2), # kernel size
(2, 2), # stride
name = ‘pool1’)

inception_2a = inception_block(pooling1,
[16, 16, 16],
name = ‘inception_2a’)
inception_2b = inception_block(inception_2a,
[16, 16, 16],
name = ‘inception_2b’)

pooling2 = tf.layers.max_pooling2d(inception_2b,
(2, 2), # kernel size
(2, 2), # stride
name = ‘pool2’)

inception_3a = inception_block(pooling2,
[16, 16, 16],
name = ‘inception_3a’)
inception_3b = inception_block(inception_3a,
[16, 16, 16],
name = ‘inception_3b’)

pooling3 = tf.layers.max_pooling2d(inception_3b,
(2, 2), # kernel size
(2, 2), # stride
name = ‘pool3’)

flatten = tf.layers.flatten(pooling3)
y_ = tf.layers.dense(flatten, 10)
老师Inception这节的整个过程各个操作后的shape您能解答一下吗

写回答

1回答

正十七

2021-07-23

参考这个问题:https://coding.imooc.com/learn/questiondetail/nlz2pX1ANAKXaG4Q.html

直接把inception_* 的这些tensor都放到sess.run里,得到的值就可以看到shape了。

0
0

深度学习之神经网络(CNN/RNN/GAN)算法原理+实战

深度学习算法工程师必学,深入理解深度学习核心算法CNN RNN GAN

2617 学习 · 935 问题

查看课程