machine-learning - 从 tensorflow 模型检查点提取权重值

Question

我正在 tensorflow 中训练模型，并且正在为我的模型做检查点。我在 Checkpoints 目录中，有四个文件，即，

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

现在我想提取图表中每一层的权重值，我该怎么做？

我尝试过这个:

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

您的恢复方式错误

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')