tf.layers.conv2d()在用name命名時會自動在其后添加Conv2D
下面是編寫的一個dncnn網絡模型，分別給第一層block1和第17層block17命名為input和output

def dncnn(input, is_training=True, output_channels=1):with tf.variable_scope('block1'):output = tf.layers.conv2d(input, 64, 3, padding='same', activation=tf.nn.relu, name='input')for layers in range(2, 16 + 1):with tf.variable_scope('block%d' % layers):output = tf.layers.conv2d(output, 64, 3, padding='same', name='conv%d' % layers, use_bias=False)output = tf.nn.relu(tf.layers.batch_normalization(output, training=is_training))with tf.variable_scope('block17'):output = tf.layers.conv2d(output, output_channels, 3, padding='same', name='output')return input - output

在輸出pb模型時，導出輸入輸出節點時需要在其后加上/Conv2D

from tensorflow.python.framework.graph_util import convert_variables_to_constants constant_graph = convert_variables_to_constants(self.sess, self.sess.graph_def,["block1/input/Conv2D", "block17/output/Conv2D"])

總結

以上是生活随笔為你收集整理的input/output is not in graph tf.layers.conv2d在name命名时会自动在其后添加Conv2D的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。