如何使用 TensorFlow 在 Returnn 中加载经过训练的网络的权重

Question

当尝试将保存的权重加载到训练有素的多个时期时使用以下代码返回网络：

import tensorflow as tf
from returnn.Config import Config
from returnn.TFNetwork import TFNetwork

for i in range(1,11):
    modelFilePath = path/to/model/ + 'network.' + '%03d' % (i,)

    returnnConfig = Config()
    returnnConfig.load_file(path/to/configFile)
    returnnTfNetwork = TFNetwork(config=path/to/configFile, train_flag=False, eval_flag=True)

    returnnTfNetwork.construct_from_dict(returnnConfig.typed_value('network'))

    with tf.Session() as sess:
        returnnTfNetwork.load_params_from_file(modelFilePath, sess)

我收到以下错误：

Variables to restore which are not in checkpoint:
global_step_1

Variables in checkpoint which are not needed for restore:
global_step

Probably we can restore these:
(None)

Error, some entry is missing in the checkpoint

Answer 1

问题是你在循环中每次都重新创建TFNetwork，并且每次都会为全局步骤创建一个新变量，必须调用不同的变量，因为每个变量都必须有一个唯一的名字.

你可以在循环中做这样的事情：

tf.reset_default_graph()

如何使用 TensorFlow 在 Returnn 中加载经过训练的网络的权重

How to load the weights of a trained network in Returnn with TensorFlow

python

tensorflow

returnn