Tensorflow: How can I restore model for training? (Python)

Question

I want to train a cnn for 20000 steps. In the 100th step I want to save all variables and after that I want to re-run my code restoring model and starting from the 100th step. I am trying to make it work with tensorflow documentation: https://www.tensorflow.org/versions/r0.10/how_tos/variables/index.html but I can't. Any help?

Answer 1

Im stuck in something similar but maybe this link can help you. Im new in tensorflow but i think you cant restore and fit without need to training again you model.

Answer 2

此功能仍然不稳定，并且文档已经过时，因此令人困惑，对我有用的（这是来自google的直接在tensorflow上工作的人的建议）是在训练之前在模型的构造函数上使用model_dir参数这将告诉您存储模型的位置，在训练之后，您只需使用相同的model_dir再次实例化模型，它将从生成的文件和检查点中恢复模型。