C1_W3 assignment

Course Q&A TensorFlow: Data and Deployment Specialization Browser-based Models with TensorFlow.js
1

Hi
I have an issue with this assignment; I use this code to save the model:

tf.Keras.experimental.export_saved_model(model, saved_model_path)

and get this error

module ‘keras.api._v2.keras.experimental’ has no attribute ‘export_saved_model’

So use this

model.save(saved_model_path)

And create an h5 model and then use the above command and create JSON and bin’s file, but can’t pass the assignment.

2

As of now the tensorflow.keras.experimental does not work anymore. To save your model use the model.save('path') function:

saved_model_path = "./my_model.h5". # or you can simply use 'my_mode.h5'
model.save(saved_model_path) #save your model 

# to reload your model 
model = keras.models.load_model(saved_model_path)

You can check the latest version of the assignment which hints to use model.save at the following path: tensorflow-2-public/C1_W3_Assignment.ipynb at main · https-deeplearning-ai/tensorflow-2-public · GitHub

3

Thanks for your response, as I said before, I used

model.save

and create an h5 model, and convert the model to a JSON file, but I can’t pass the assignment.