从张量流模型检查点提取权重值

Question

我正在张量流中训练模型，并且正在为模型做检查点。在Checkpoints目录中，我有四个文件，

• checkpoint
• model.cpkt-0.data-00000-of-00001
• model.cpkt-0.index
• model.cpkt-0.meta

现在，我要提取图形中每一层的权重值，该怎么做？

我尝试了这个：

import tensorflow as tf
sess = tf.InteractiveSession()

saver = tf.train.import_meta_graph('model.cpkt-0.meta')
w = saver.restore(sess, 'model.cpkt-0.data-00000-of-00001')

但是我收到以下错误：

Unable to open table file ./model.cpkt-0.data-00000-of-00001: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?

Answer 1

您的恢复方式有误

saver.restore(sess, 'model.cpkt-0')
# get the graph
g = tf.get_default_graph()
w1 = g.get_tensor_by_name('some_variable_name as per your definition in the model')