Saving and loading models in ML Python - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the output of this model saving code?

Consider the following code that trains a simple model and saves it. What will be printed after saving?

ML Python

import tensorflow as tf
from tensorflow.keras import layers

model = tf.keras.Sequential([
    layers.Dense(10, activation='relu', input_shape=(5,)),
    layers.Dense(1)
])
model.compile(optimizer='adam', loss='mse')

import numpy as np
x = np.random.random((10, 5))
y = np.random.random((10, 1))
model.fit(x, y, epochs=1, verbose=0)

model.save('my_model')
print('Model saved successfully')

A

Model saved successfully
Warning: Overwriting existing model

B No output

C Error: model.save() requires a file extension

D Model saved successfully

💡 Hint

The model.save() method saves the model in TensorFlow SavedModel format by default if no extension is given.

The code trains a simple model and saves it to the folder 'my_model'. Since no error occurs, the print statement outputs 'Model saved successfully'.

❓ Model Choice

intermediate

Which method correctly loads a saved Keras model?

You have saved a Keras model using model.save('my_model'). Which code snippet correctly loads this model?

A loaded_model = tf.keras.models.load_model('my_model')

B loaded_model = tf.keras.load('my_model')

C loaded_model = tf.load_model('my_model')

D loaded_model = tf.keras.models.Model.load('my_model')

💡 Hint

Look for the official Keras function to load models.

The correct function to load a saved Keras model is tf.keras.models.load_model(path). Other options are invalid or do not exist.

❓ Hyperparameter

advanced

Which saving format preserves custom objects in Keras models?

You have a Keras model with a custom layer. You want to save and load it without losing the custom layer. Which saving format should you use?

A Save model architecture as JSON only

B Save as HDF5 file with .h5 extension

C Save weights only with model.save_weights()

D Save as TensorFlow SavedModel format (folder)

💡 Hint

Custom objects are best preserved in one specific format.

Saving as HDF5 (.h5) preserves custom layers and objects better than SavedModel format, which may require extra steps to load custom objects.

❓ Metrics

advanced

After loading a saved model, which metric will NOT be available automatically?

You save a compiled Keras model with accuracy metric and load it later. Which metric will NOT be available without recompiling?

A Custom metric defined outside the model

B Loss function

C Model weights

D Accuracy metric

💡 Hint

Think about metrics that require custom code to be recognized.

Custom metrics defined outside the model are not saved automatically and require passing custom_objects when loading or recompiling.

🔧 Debug

expert

Why does this code raise an error when loading a model?

You saved a model with a custom activation function but get an error when loading it with tf.keras.models.load_model('my_model'). Why?

ML Python

def custom_activation(x):
    return tf.nn.relu(x) * tf.math.sigmoid(x)

model = tf.keras.Sequential([
    tf.keras.layers.Dense(10, activation=custom_activation, input_shape=(5,)),
    tf.keras.layers.Dense(1)
])
model.save('my_model')

# Later loading
loaded_model = tf.keras.models.load_model('my_model')

A The model was not compiled before saving

B The input_shape is missing in the loading code

C The custom activation function is not passed in custom_objects during loading

D The model.save() method does not support custom layers

💡 Hint

Custom functions must be provided when loading models that use them.

When loading a model with custom functions, you must pass them in the custom_objects argument to load_model, otherwise it raises an error.

Practice

1. What is the main purpose of saving a trained machine learning model?

easy

A. To increase the model's training speed

B. To reuse the model later without retraining

C. To improve the model's accuracy automatically

D. To delete the training data after use

Solution

1. Step 1: Understand model saving

   Saving a model stores its learned parameters so it can be reused later.

2. Step 2: Identify the main benefit

   This avoids retraining, saving time and resources.

3. Final Answer:

   To reuse the model later without retraining -> Option B

4. Quick Check:

   Saving = reuse without retraining [OK]

Hint: Saving means keep model for later use without retraining [OK]

Common Mistakes:

• Thinking saving improves accuracy automatically
• Confusing saving with speeding up training
• Believing saving deletes data

2. Which of the following is the correct way to save a Keras model named model to a file called my_model.h5?

easy

A. model.save('my_model.h5')

B. save_model('my_model.h5', model)

C. model.save_model('my_model.h5')

D. save('model', 'my_model.h5')

Solution

1. Step 1: Recall Keras save syntax

   Keras models are saved using model.save(filename).

2. Step 2: Match correct syntax

   model.save('my_model.h5') matches this syntax exactly.

3. Final Answer:

   model.save('my_model.h5') -> Option A

4. Quick Check:

   model.save(filename) saves model [OK]

Hint: Use model.save('filename') to save Keras models [OK]

Common Mistakes:

• Using incorrect function names like save_model or save
• Swapping argument order
• Calling save_model as a method on model

3. What will be the output of the following code snippet?

from tensorflow.keras.models import load_model
model = load_model('saved_model.h5')
predictions = model.predict([[5.1, 3.5, 1.4, 0.2]])
print(predictions)

medium

A. The model architecture printed as text

B. An error because load_model requires a directory, not a file

C. A list of class labels as strings

D. A numpy array of prediction probabilities

Solution

1. Step 1: Understand load_model usage

   load_model loads a saved Keras model from a file.

2. Step 2: Predict method output

   model.predict returns a numpy array of prediction probabilities for input data.

3. Final Answer:

   A numpy array of prediction probabilities -> Option D

4. Quick Check:

   load_model + predict = numpy array output [OK]

Hint: load_model loads model; predict returns probabilities array [OK]

Common Mistakes:

• Thinking load_model only loads from directories
• Expecting printed model architecture from predict
• Assuming predict returns class labels directly

4. You try to load a saved model using load_model('model.h5') but get an error: OSError: Unable to open file (file signature not found). What is the most likely cause?

medium

A. The model file is too large to load

B. You forgot to import load_model from keras

C. The file 'model.h5' is corrupted or not a valid model file

D. The model was saved with a different Python version

Solution

1. Step 1: Analyze the error message

   OSError about file signature means the file is not recognized as a valid HDF5 model file.

2. Step 2: Identify common causes

   This usually happens if the file is corrupted or not a saved model file.

3. Final Answer:

   The file 'model.h5' is corrupted or not a valid model file -> Option C

4. Quick Check:

   File signature error = corrupted or invalid file [OK]

Hint: File signature errors mean corrupted or wrong file type [OK]

Common Mistakes:

• Assuming Python version mismatch causes this error
• Forgetting to import but error message differs
• Thinking file size causes signature errors

5. You have a trained model saved as model_v1.h5. You want to load it, continue training on new data, then save the updated model as model_v2.h5. Which code snippet correctly does this?

hard

A. from tensorflow.keras.models import load_model
model = load_model('model_v1.h5')
model.fit(new_data, new_labels, epochs=5)
model.save('model_v2.h5')

B. model = load('model_v1.h5')
model.train(new_data, new_labels)
save_model(model, 'model_v2.h5')

C. load_model('model_v1.h5')
train_model(new_data, new_labels)
save('model_v2.h5')

D. from keras import load
model = load('model_v1.h5')
model.fit(new_data, new_labels)
model.save('model_v2.h5')

Solution

1. Step 1: Load the saved model correctly

   Use load_model('model_v1.h5') from tensorflow.keras.models to load the model.

2. Step 2: Continue training and save updated model

   Call model.fit() with new data, then save with model.save('model_v2.h5').

3. Final Answer:

   from tensorflow.keras.models import load_model model = load_model('model_v1.h5') model.fit(new_data, new_labels, epochs=5) model.save('model_v2.h5') -> Option A

4. Quick Check:

   Load, fit, save = from tensorflow.keras.models import load_model model = load_model('model_v1.h5') model.fit(new_data, new_labels, epochs=5) model.save('model_v2.h5') [OK]

Hint: Load with load_model, fit new data, then save again [OK]

Common Mistakes:

• Using undefined functions like load or save_model
• Forgetting to import load_model
• Not calling fit before saving updated model