You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I was trying to figure out how to save and load a trained network. I was following what was written in https://github.com/deepmind/sonnet#tensorflow-saved-model , but cant figure out how to regenerate a my_module object, with the weights from the loaded model.
Thanks!
The text was updated successfully, but these errors were encountered:
Hi,
You can save the model by this: tf.saved_model.save(my_model, "the_saved_model")
And for loading your model back use this: new_model = tf.saved_model.load("the_saved_model")
Hi,
I'm extremely new to both TF and Sonnet.
I was trying to figure out how to save and load a trained network. I was following what was written in https://github.com/deepmind/sonnet#tensorflow-saved-model , but cant figure out how to regenerate a my_module object, with the weights from the loaded model.
Thanks!
The text was updated successfully, but these errors were encountered: