原文:https://www.cnblogs.com/nowornever-L/p/6991295.html
1. TensorFlow 生成的 .ckpt 和 .pb 都有什么用?
The .ckpt is the model given by tensorflow which includes all the weights/parameters in the model. The .pb file stores the computational graph. To make tensorflow work we need both the graph and the parameters. There are two ways to get the graph: (1) use the python program that builds it in the first place (tensorflowNetworkFunctions.py). (2) Use a .pb file (which would have to be generated by tensorflowNetworkFunctions.py). .ckpt file is were all the intelligence is.
2. TensorFlow saving into/loading a graph from a file
正好看到 StackOverflow 上有位仁兄问过相关的问题,整理的不错
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
From what I‘ve gathered so far, there are several different ways of dumping a TensorFlow graph
However, I haven‘t been able to clear up several questions regarding these different methods:
|
1 Answer
up vote down voteaccepted |
There are many ways to approach the problem of saving a model in TensorFlow, which can make it a bit confusing. The documentation on this topic is taking shape, but doesn‘t cover all of the details in your question. Taking each of your sub-questions in turn:
|
||||||||
|
原文地址:https://www.cnblogs.com/Ph-one/p/9516622.html