Difference between Keras model.save() and model.save_weights()?

Machine LearningTensorflowNeural NetworkKeras

Machine Learning Problem Overview

To save a model in Keras, what are the differences between the output files of:

  1. model.save()
  2. model.save_weights()
  3. ModelCheckpoint() in the callback

The saved file from model.save() is larger than the model from model.save_weights(), but significantly larger than a JSON or Yaml model architecture file. Why is this?

Restating this: Why is size(model.save()) + size(something) = size(model.save_weights()) + size(model.to_json()), what is that "something"?

Would it be more efficient to just model.save_weights() and model.to_json(), and load from these than to just do model.save() and load_model()?

What are the differences?

Machine Learning Solutions

Solution 1 - Machine Learning

save() saves the weights and the model structure to a single HDF5 file. I believe it also includes things like the optimizer state. Then you can use that HDF5 file with load() to reconstruct the whole model, including weights.

save_weights() only saves the weights to HDF5 and nothing else. You need extra code to reconstruct the model from a JSON file.

Solution 2 - Machine Learning

  • model.save_weights(): Will only save the weights so if you need, you are able to apply them on a different architecture
  • mode.save(): Will save the architecture of the model + the the weights + the training configuration + the state of the optimizer

Solution 3 - Machine Learning

Just to add what ModelCheckPoint's output is, if it's relevant for anyone else: used as a callback during model training, it can either save the whole model or just the weights depending on what state the save_weights_only argument is set to. TRUE and weights only are saved, akin to calling model.save_weights(). FALSE (default) and the whole model is saved, as in calling model.save().

Solution 4 - Machine Learning

Adding to the answers above, as of tf.keras version '2.7.0', the model can be saved in 2 formats using model.save() i.e., the TensorFlow SavedModel format, and the older Keras H5 format. The recommended format is SavedModel and it is the default when model.save() is called. To save to .h5(HDF5) format, use model.save('my_model', save_format='h5') More

Categories
Recommended Machine Learning Solutions
Recommended Tensorflow Solutions
Recommended Neural Network Solutions
Recommended Keras Solutions

Previous Solution:

Cannot find module '@angular/compiler'

Angular

Next Solution:

ASP.NET Core Localization with help of SharedResources

asp.netasp.net Coreasp.net Core-Middlewareasp.net Core-Localization

Attributions

All content for this solution is sourced from the original question on Stackoverflow.

The content on this page is licensed under the Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) license.

Content TypeOriginal AuthorOriginal Content on Stackoverflow
Questionmikal94305View Question on Stackoverflow
Solution 1 - Machine LearningDr. SnoopyView Answer on Stackoverflow
Solution 2 - Machine LearningAymenView Answer on Stackoverflow
Solution 3 - Machine LearninghumbleHackerView Answer on Stackoverflow
Solution 4 - Machine LearningdalonloboView Answer on Stackoverflow