Is there a way to save and recover a trained Neural Network in PyBrain, so that I don't have to retrain it each time I run the script?
相关问题
- _convertToOneOfMany in PyBrain
- How to denormalise (de-standardise) neural net pre
- What is `target` in `ClassificationDataSet` good f
- Creating custom connectivity in PyBrain neural net
- Pybrain time series prediction using LSTM recurren
相关文章
- Creating custom connectivity in PyBrain neural net
- Pybrain time series prediction using LSTM recurren
- 从ANN和提高准确性不稳定的输出值(Unstable output values from ANN
- Matching Binary operators in Tuples to Dictionary
- don't print results of a function
- 如何训练神经网络监督的数据集采用pybrain黑箱优化?(How to train a neural
- 怎么办监督deepbelief在PyBrain培训?(How to do supervised de
- Unstable output values from ANN and improving accu
The
NetworkWriter
andNetworkReader
work great. I noticed that upon saving and loading viapickle
, that the network is no longer changeable via training-functions. Thus, I would recommend using theNetworkWriter
-method.NetworkWriter is the way to go. Using Pickle you can't retrain network as Jorg tells.
You need something like this:
PyBrain's Neural Networks can be saved and loaded using either python's built in pickle/cPickle module, or by using PyBrain's XML NetworkWriter.
Note cPickle is implemented in C, and therefore should be much faster than pickle. Usage should mostly be the same as pickle, so just import and use cPickle instead.