How NOT to save model optimizer in Tensorflow Keras?

user_10870968 0
Viewed 571

I'm reading the official tutorial on save-load in Keras and it seems whether I used save or save_weights methods, then the optimizer parameters are going to be saved at any rate. How can save model's weights only?

keras tensorflow
2 Answers
model.save('./savedmodel.h5', save_format='h5', include_optimizer=False)

If save_format='tf', whether include_optimizer=False or True, it's useless as I tried.

user_140415570

In Keras, to save model weights, do:

model.save_weights('my_model_weights.h5')

To load model weights:

model.load_weights('my_model_weights.h5')

Also see additional example on saving/loading weights by layer name from here.

user_80725460
Related