如何清除使用Keras和Tensorflow(作为后端)创建的模型? [英] How can I clear a model created with Keras and Tensorflow(as backend)?

问题描述

在Jupyter Notebook中用Keras训练神经网络时遇到问题.我创建了具有几个隐藏层的顺序模型.训练模型并保存结果后，我想在同一会话中删除该模型并创建一个新模型，因为我有一个for循环来检查不同参数的结果.但是据我了解到的错误，在更改参数，循环时，我只是在模型中添加了图层(即使我在循环中再次使用network = Sequential()对其进行了初始化).所以我的问题是，如何才能完全清除以前的模型，或者如何在同一会话中初始化一个全新的模型?

I have a problem when training a neural net with Keras in Jupyter Notebook. I created a sequential model with several hidden layers. After training the model and saving the results, I want to delete this model and create a new model in the same session, as I have a for loop that checks the results for different parameters. But as I understand the errors I get, when changing the parameters, when I loop over, I am just adding layers to the model (even though I initialise it again with network = Sequential() inside the loop). So my question is, how can I completely clear the previous model or how can I initialise a completely new model in the same session?

推荐答案

keras.backend.clear_session()应该清除以前的模型.来自 https://keras.io/backend/:

keras.backend.clear_session() should clear the previous model. From https://keras.io/backend/:

销毁当前的TF图并创建一个新的TF图. 有助于避免旧模型/图层造成混乱.

Destroys the current TF graph and creates a new one. Useful to avoid clutter from old models / layers.

这篇关于如何清除使用Keras和Tensorflow(作为后端)创建的模型?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！