keras: how to save the training history attribute of the history object

by

What I use is the following:

with open('/trainHistoryDict', 'wb') as file_pi:
    pickle.dump(history.history, file_pi)

In this way I save the history as a dictionary in case I want to plot the loss or accuracy later on. Later, when you want to load the history again, you can use:

with open('/trainHistoryDict', "rb") as file_pi:
    history = pickle.load(file_pi)

Why choose pickle over json?

The comment under this answer accurately states:

[Storing the history as json] does not work anymore in tensorflow keras. I had issues with: TypeError: Object of type ‘float32’ is not JSON serializable.

There are ways to tell json how to encode numpy objects, which you can learn about from this other question, so there’s nothing wrong with using json in this case, it’s just more complicated than simply dumping to a pickle file.

More Related Contents:

  1. Keras Sequential model input layer
  2. What is the role of TimeDistributed layer in Keras?
  3. How can I use a weight matrix created by a trained neural network to make predictions in another file?
  4. What is a `”Python”` layer in caffe?
  5. How to apply gradient clipping in TensorFlow?
  6. How does Keras calculate the accuracy?
  7. How to initialize weights in PyTorch?
  8. How to concatenate two layers in keras?
  9. How do I initialize weights in PyTorch?
  10. Does Any one got “AttributeError: ‘str’ object has no attribute ‘decode’ ” , while Loading a Keras Saved Model
  11. Keras custom loss function: Accessing current input pattern
  12. How can I use a pre-trained neural network with grayscale images?
  13. Removing then Inserting a New Middle Layer in a Keras Model
  14. How to use fit_generator with multiple inputs
  15. Multiple outputs in Keras
  16. How to log Keras loss output to a file
  17. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  18. Can I send callbacks to a KerasClassifier?
  19. Keras give input to intermediate layer and get final output
  20. how to implement custom metric in keras?
  21. Understanding Keras LSTMs
  22. Make a custom loss function in keras
  23. Keras replacing input layer
  24. How to get other metrics in Tensorflow 2.0 (not only accuracy)?
  25. Unbalanced data and weighted cross entropy
  26. Is deep learning bad at fitting simple non linear functions outside training scope (extrapolating)?
  27. How do I get the weights of a layer in Keras?
  28. Tensor is not an element of this graph
  29. Keras LSTM input dimension setting
  30. Custom ImageDataGenerator() for half a million images where labels and pixels are in 2 separate DataFrames using Keras (or any other library) [closed]

Leave a Comment