[英]How to resume training from *.meta in tensorflow?
In the latest version of tensorflow, when I save the model I find two files are produced: model_xxx and model_xxx.meta. 在最新版本的tensorflow中,当我保存模型时,我发现生成了两个文件:model_xxx和model_xxx.meta。
Does model_xxx.meta specify the network? model_xxx.meta是否指定网络? Can I resume training using model_xxx and model_xxx.meta without specify the network in the code?
我可以在不指定代码网络的情况下使用model_xxx和model_xxx.meta恢复训练吗? What about training queue structure, are they stored in model_xxx.meta?
训练队列的结构如何,它们存储在model_xxx.meta中吗?
Not sure if this will work for you, but at least for DNNCLassifiers
you can specify the model_dir
parameter when creating it and that will construct the model from the files and then you can continue the training. 不知道这是否对您
DNNCLassifiers
,但是至少对于DNNCLassifiers
您可以在创建模型时指定model_dir
参数,该参数将从文件中构建模型,然后您可以继续进行训练。
For the DNNClassifiers
you specify model_dir
when first creating the object and the training will store checkpoints and other files on this directory. 对于
DNNClassifiers
您在首次创建对象时指定model_dir
,并且训练会将检查点和其他文件存储在此目录中。 You can come then after that, and create another DNNClassifier
specifying the same model_dir
and that will restore your pre-trained model. 然后,您可以接着创建另一个
DNNClassifier
该DNNClassifier
指定相同的model_dir
,这将还原您的预训练模型。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.