Loading and inference in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a saved TensorFlow model.

TensorFlow

import tensorflow as tf
model = tf.keras.models.[1]('my_model')

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

Acompile_model

Bsave_model

Cload_model

Dfit_model

Attempts:

3 left

💡 Hint

Common Mistakes

Using save_model instead of load_model

Trying to compile or fit the model during loading

The function load_model loads a saved TensorFlow model from disk.

2fill in blank

medium

Complete the code to make predictions using the loaded model.

TensorFlow

predictions = model.[1](input_data)

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

Atrain

Bfit

Cevaluate

Dpredict

Attempts:

3 left

💡 Hint

Common Mistakes

Using fit or train instead of predict

Using evaluate which returns loss and metrics

The predict method is used to get the model's output for new input data.

3fill in blank

hard

Fix the error in the code to load a model from the file 'model.h5'.

TensorFlow

model = tf.keras.models.load_model([1])

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

Amodel.h5

B"model.h5"

Cmodel

D'model'

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the filename without quotes

Passing a variable name instead of a string

The file path must be a string, so it needs quotes around it.

4fill in blank

hard

Fill both blanks to create a dictionary of predictions for each input sample.

TensorFlow

results = {i: model.[1](sample) for i, sample in enumerate([2])}

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

Apredict

Binput_data

Cfit

Devaluate

Attempts:

3 left

💡 Hint

Common Mistakes

Using fit or evaluate instead of predict

Using wrong variable name for input data

Use predict to get predictions for each sample in input_data.

5fill in blank

hard

Fill all three blanks to load a model, make predictions, and print the results.

TensorFlow

model = tf.keras.models.[1]('saved_model')
preds = model.[2](test_data)
print([3])

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

Aload_model

Bpredict

Cpreds

Dfit

Attempts:

3 left

💡 Hint

Common Mistakes

Using fit instead of predict

Printing the wrong variable

Not using quotes for the model path

Load the model with load_model, predict with predict, and print the predictions stored in preds.