Question

我遇到Tensorflow恢复模型的问题。我有一个脚本，根据一组训练文件生成几个模型。这些模型使用

创建自己的变量scopings

tf.variable_scope(myPrefix).

训练结束后，我可以使用

恢复模型

tf.train.Saver(model_vars).restore(sess, model)

将model_vars计算为

all_vars = tf.all_variables()                                                                                  
model_vars=[k for k in all_vars if k.name.startswith(myPrefix)]

虽然模型确实似乎加载，但运行它们会产生占位符错误（参见下文，85314_tr_10是我的前缀）。

我很确定我不会跳过任何占位符。该模型只有两个（x和y），这些是我制作的eval来电使用的：

predictions = sess.run(pred, feed_dict={x: test_data, y:test_labels})

这是错误跟踪：

W tensorflow/core/common_runtime/executor.cc:1076] 0x2ea0e60 Compute status: Invalid argument: You must feed a value for placeholder tensor '85314_tr_10/Placeholder' with dtype float
         [[Node: 85314_tr_10/Placeholder = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Traceback (most recent call last):
  File "../prediction/views.py", line 507, in <module>
    predict("","85314","True","2015-11-12T09:08:00Z","2015-11-12T10:08:00Z")
  File "../prediction/views.py", line 472, in predict
    predictions= prediction.eval(feed_dict={x: test_data,y:test_labels}, session=sess)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 460, in eval
    return _eval_using_default_session(self, feed_dict, self.graph, session)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2910, in _eval_using_default_session
    return session.run(tensors, feed_dict)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 368, in run
    results = self._do_run(target_list, unique_fetch_targets, feed_dict_string)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 444, in _do_run
    e.code)

非常感谢任何帮助！

Tensorflow在模型恢复后抱怨占位符

0 个答案: