Why model persistence enables deployment in TensorFlow - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to save a trained TensorFlow model.

TensorFlow

model.[1]('my_model')

Drag options to blanks, or click blank then click option'

Acompile

Bload

Cfit

Dsave

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'load' instead of 'save' will cause an error because 'load' is not a method of the model object.

Using 'fit' saves training the model, not saving it.

Using 'compile' prepares the model for training, not saving.

The save method stores the trained model to disk so it can be used later.

2fill in blank

medium

Complete the code to load a saved TensorFlow model.

TensorFlow

loaded_model = tf.keras.models.[1]('my_model')

Drag options to blanks, or click blank then click option'

Asave

Bfit

Cload_model

Dcompile

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'save' instead of 'load_model' will cause an error because 'save' is a method of model, not a function to load.

Using 'fit' is for training, not loading.

Using 'compile' is for preparing the model, not loading.

The function load_model loads a saved model from disk so it can be used for predictions or further training.

3fill in blank

hard

Fix the error in the code to save the model in HDF5 format.

TensorFlow

model.[1]('my_model.h5')

Drag options to blanks, or click blank then click option'

Afit

Bsave

Cload

Dcompile

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'load' instead of 'save' causes an error because 'load' is for loading models.

Using 'fit' or 'compile' does not save the model.

To save a model in HDF5 format, use the save method with a filename ending in '.h5'.

4fill in blank

hard

Fill both blanks to create a dictionary of predictions for inputs greater than 0.5.

TensorFlow

predictions = {x: model.predict([[x]])[0][0] for x in inputs if x [1] 0.5 and model.predict([[x]])[0][0] [2] 0.7}

Drag options to blanks, or click blank then click option'

A>

B<

C==

D!=

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' in the first blank would select inputs less than 0.5, which is incorrect.

Using '>' in the second blank would select predictions greater than 0.7, which is not intended.

The code filters inputs greater than 0.5 and predictions less than 0.7.

5fill in blank

hard

Fill all three blanks to create a dictionary of predictions for inputs where prediction is above 0.6 and input is less than 1.0.

TensorFlow

results = { [1] : [2] for [3] in data if data[[3]] > 0.6 and [3] < 1.0 }

Drag options to blanks, or click blank then click option'

Ax

Bdata[x]

Dy

Attempts:

3 left

💡 Hint

Common Mistakes

Using different variable names for key and loop variable causes errors.

Using 'y' as loop variable without defining it causes errors.

The dictionary comprehension uses 'x' as the key, 'data[x]' as the value, and iterates over 'x' in data.