Keras as TensorFlow's high-level API - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is Keras in the context of TensorFlow?

Keras is a simple and user-friendly high-level API within TensorFlow that helps you build and train neural networks easily without dealing with low-level details.

beginner

Why do we use Keras instead of raw TensorFlow code?

Keras makes building models faster and easier by providing simple building blocks like layers and models, so you can focus on designing your network instead of complex code.

intermediate

What are the two main ways to build models in Keras?

You can build models using the Sequential API, which stacks layers one after another, or the Functional API, which allows more flexible and complex model designs.

beginner

How does Keras handle training a model?

Keras uses the .compile() method to set the optimizer, loss function, and metrics, and the .fit() method to train the model on your data, showing progress with loss and accuracy.

intermediate

What is the role of callbacks in Keras?

Callbacks are tools that let you customize what happens during training, like saving the best model, stopping early if no improvement, or adjusting learning rates.

Which of the following best describes Keras in TensorFlow?

A A low-level library for matrix operations

B A hardware accelerator

C A data visualization tool

D A high-level API for building and training neural networks

Keras is designed as a high-level API to simplify building and training neural networks within TensorFlow.

What method do you use in Keras to start training a model?

A .fit()

B .evaluate()

C .predict()

D .compile()

The .fit() method trains the model on your data after you have compiled it.

Which Keras API allows you to build models by stacking layers one after another?

A Functional API

B Sequential API

C Subclassing API

D Estimator API

The Sequential API is the simple way to build models by stacking layers in order.

What is the purpose of the .compile() method in Keras?

A To set optimizer, loss function, and metrics before training

B To define the model architecture

C To make predictions on new data

D To save the model to disk

The .compile() method prepares the model for training by setting the optimizer, loss, and metrics.

Which of these is NOT a typical use of Keras callbacks?

A Stopping training early if no improvement

B Saving the best model during training

C Changing the model architecture during training

D Adjusting learning rates dynamically

Callbacks customize training behavior but do not change the model architecture during training.

Explain how Keras simplifies building and training neural networks in TensorFlow.

Think about how Keras hides complex details and provides simple tools.

Describe the difference between the Sequential API and the Functional API in Keras.

Consider model complexity and flexibility.

Practice

1. What is the main purpose of Keras in TensorFlow?

easy

A. To replace TensorFlow's core functionalities

B. To provide a simple way to build and train neural networks

C. To visualize data with charts and graphs

D. To manage databases for machine learning

Solution

1. Step 1: Understand Keras role in TensorFlow

   Keras is designed as a user-friendly API to build and train neural networks easily within TensorFlow.

2. Step 2: Compare options with Keras purpose

   Options B, C, and D describe unrelated tasks. Only To provide a simple way to build and train neural networks correctly states Keras's main purpose.

3. Final Answer:

   To provide a simple way to build and train neural networks -> Option B

4. Quick Check:

   Keras purpose = simple neural network building [OK]

Hint: Keras makes neural networks easy to build and train [OK]

Common Mistakes:

• Thinking Keras replaces TensorFlow core
• Confusing Keras with data visualization tools
• Assuming Keras manages databases

2. Which of the following is the correct way to import Keras from TensorFlow?

easy

A. from tensorflow import keras

B. import tensorflow.keras as tfk

C. import keras

D. from keras import tensorflow

Solution

1. Step 1: Recall the standard import syntax for Keras in TensorFlow

   The recommended way is to import Keras as a module from TensorFlow using 'from tensorflow import keras'.

2. Step 2: Evaluate each option

   import keras imports standalone keras (not recommended). import tensorflow.keras as tfk is valid syntax but aliases it as 'tfk' (keras not directly available). from keras import tensorflow reverses the import incorrectly. Only from tensorflow import keras is correct.

3. Final Answer:

   from tensorflow import keras -> Option A

4. Quick Check:

   Correct import = from tensorflow import keras [OK]

Hint: Use 'from tensorflow import keras' to import Keras [OK]

Common Mistakes:

• Using 'import keras' without tensorflow prefix
• Swapping import order incorrectly
• Trying to alias with invalid syntax

3. What will be the output shape of the model defined below?

from tensorflow import keras
model = keras.Sequential([
    keras.layers.Dense(10, input_shape=(5,)),
    keras.layers.Dense(3)
])
print(model.output_shape)

medium

A. (3, 5)

B. (5, 3)

C. (None, 3)

D. (None, 10)

Solution

1. Step 1: Analyze model layers and input shape

   The first Dense layer outputs 10 units for each input of shape (5,). The second Dense layer outputs 3 units. The batch size is None (unknown).

2. Step 2: Determine final output shape

   The model output shape is (None, 3), where None is batch size and 3 is output units of last layer.

3. Final Answer:

   (None, 3) -> Option C

4. Quick Check:

   Output shape = (None, 3) [OK]

Hint: Output shape matches last layer units with batch size None [OK]

Common Mistakes:

• Confusing input shape with output shape
• Using batch size 5 instead of None
• Mixing layer output units

4. Identify the error in the following Keras model code:

from tensorflow import keras
model = keras.Sequential()
model.add(keras.layers.Dense(10))
model.add(keras.layers.Dense(1))
model.compile(optimizer='adam', loss='mse')
model.summary()
model.fit(x_train, y_train, epochs=5)

medium

A. Missing input shape in first Dense layer

B. Incorrect optimizer name

C. Loss function 'mse' is invalid

D. fit method missing batch_size argument

Solution

1. Step 1: Check model layer definitions

   The first Dense layer lacks an input shape, which is required for the model to know input dimensions.

2. Step 2: Verify compile and fit parameters

   Optimizer 'adam' and loss 'mse' are valid. Batch size is optional in fit. So no error there.

3. Final Answer:

   Missing input shape in first Dense layer -> Option A

4. Quick Check:

   Input shape missing = error [OK]

Hint: Always specify input shape in first layer [OK]

Common Mistakes:

• Assuming batch_size is mandatory in fit
• Thinking 'mse' is invalid loss
• Confusing optimizer names

5. You want to build a Keras model that accepts images of size 28x28 with 1 color channel and outputs 10 class probabilities. Which model definition is correct?

hard

A. model = keras.Sequential([
keras.layers.Flatten(input_shape=(28,28)),
keras.layers.Dense(10)
])

B. model = keras.Sequential([
keras.layers.Dense(128, input_shape=(28,28,1), activation='relu'),
keras.layers.Dense(10, activation='softmax')
])

C. model = keras.Sequential([
keras.layers.Conv2D(32, (3,3), input_shape=(28,28)),
keras.layers.Dense(10, activation='softmax')
])

D. model = keras.Sequential([
keras.layers.Flatten(input_shape=(28,28,1)),
keras.layers.Dense(128, activation='relu'),
keras.layers.Dense(10, activation='softmax')
])

Solution

1. Step 1: Check input shape and layer compatibility

   Images have shape (28,28,1). Flatten layer must match this shape exactly to convert to vector.

2. Step 2: Verify output layer for classification

   Output layer with 10 units and softmax activation correctly outputs class probabilities.

3. Step 3: Evaluate each option

   model = keras.Sequential([ keras.layers.Flatten(input_shape=(28,28,1)), keras.layers.Dense(128, activation='relu'), keras.layers.Dense(10, activation='softmax') ]) correctly uses Flatten with input_shape (28,28,1) and final Dense with softmax. model = keras.Sequential([ keras.layers.Dense(128, input_shape=(28,28,1), activation='relu'), keras.layers.Dense(10, activation='softmax') ]) incorrectly uses Dense with 3D input. model = keras.Sequential([ keras.layers.Conv2D(32, (3,3), input_shape=(28,28)), keras.layers.Dense(10, activation='softmax') ]) misses channel dimension and uses Conv2D incorrectly. model = keras.Sequential([ keras.layers.Flatten(input_shape=(28,28)), keras.layers.Dense(10) ]) misses channel dimension and lacks activation.

4. Final Answer:

   model = keras.Sequential([ keras.layers.Flatten(input_shape=(28,28,1)), keras.layers.Dense(128, activation='relu'), keras.layers.Dense(10, activation='softmax') ]) -> Option D

5. Quick Check:

   Correct input shape and softmax output = model = keras.Sequential([ keras.layers.Flatten(input_shape=(28,28,1)), keras.layers.Dense(128, activation='relu'), keras.layers.Dense(10, activation='softmax') ]) [OK]

Hint: Match input shape exactly and use softmax for classes [OK]

Common Mistakes:

• Ignoring channel dimension in input shape
• Using Dense layer directly on 3D input
• Missing softmax activation for classification