Multi-input and multi-output models in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output shape of a multi-input model

Consider a TensorFlow model with two inputs: one of shape (None, 10) and another of shape (None, 5). Both inputs are concatenated and passed through a Dense layer with 8 units. What is the shape of the model's output?

TensorFlow

import tensorflow as tf

input1 = tf.keras.Input(shape=(10,))
input2 = tf.keras.Input(shape=(5,))

concat = tf.keras.layers.Concatenate()([input1, input2])
output = tf.keras.layers.Dense(8)(concat)

model = tf.keras.Model(inputs=[input1, input2], outputs=output)

print(model.output_shape)

A (None, 8)

B (None, 10)

C (None, 15)

D (None, 5)

💡 Hint

The Dense layer outputs a tensor with shape (batch_size, units).

The two inputs are concatenated along the last axis, resulting in shape (None, 15). The Dense layer with 8 units transforms this to (None, 8).

❓ Model Choice

intermediate

Choosing the correct multi-output model architecture

You want to build a TensorFlow model that takes one input of shape (20,) and produces two outputs: one for regression (a single continuous value) and one for classification (3 classes). Which model architecture below correctly implements this?

A One input layer, two Dense layers with 3 units each and relu activation for outputs.

B Two input layers, one output layer with 4 units and softmax activation.

C One input layer, one Dense layer with 4 units and sigmoid activation for both outputs.

D One input layer, shared Dense layers, then two separate Dense layers: one with 1 unit (no activation) for regression, one with 3 units and softmax for classification.

💡 Hint

Regression output usually has 1 unit without activation; classification output uses softmax for multiple classes.

Option D correctly uses one input, shared layers, and two output heads: one for regression (1 unit, linear) and one for classification (3 units, softmax).

❓ Hyperparameter

advanced

Choosing loss functions for multi-output models

You have a multi-output model with two outputs: a regression output and a 4-class classification output. Which combination of loss functions is appropriate to compile this model?

A {'regression_output': 'mse', 'classification_output': 'categorical_crossentropy'}

B {'regression_output': 'binary_crossentropy', 'classification_output': 'mse'}

C {'regression_output': 'categorical_crossentropy', 'classification_output': 'mse'}

D {'regression_output': 'mse', 'classification_output': 'binary_crossentropy'}

💡 Hint

Regression uses mean squared error; multi-class classification uses categorical crossentropy.

Mean squared error (mse) is suitable for regression outputs. Categorical crossentropy is used for multi-class classification with one-hot labels.

🔧 Debug

advanced

Debugging multi-input model input mismatch error

You defined a TensorFlow model with two inputs: input1 shape (None, 8) and input2 shape (None, 4). When training, you get a ValueError about input shapes not matching. Which of the following is the most likely cause?

A You used different batch sizes for input1 and input2 arrays.

B You passed a single numpy array instead of a list or tuple of two arrays as input data.

C You forgot to compile the model before training.

D You used a Dense layer instead of Conv2D in the model.

💡 Hint

Multi-input models expect inputs as a list or tuple matching the input layers.

Passing a single array instead of a list/tuple of arrays causes shape mismatch errors because the model expects multiple inputs.

🧠 Conceptual

expert

Understanding training metrics in multi-output models

A multi-output model has two outputs: output A (regression) and output B (classification). You compile the model with metrics={'output_A': ['mae'], 'output_B': ['accuracy']}. During training, what will the reported 'accuracy' metric represent?

A The overall accuracy combining regression and classification outputs.

B The average accuracy of both outputs A and B.

C The classification accuracy of output B only.

D The mean absolute error of output A converted to accuracy.

💡 Hint

Metrics are reported per output when specified as a dictionary.

The 'accuracy' metric applies only to output B (classification). Output A uses 'mae' metric separately.

Practice

1. What is the main purpose of a multi-input model in TensorFlow?

easy

A. To accept more than one data source at the same time

B. To predict multiple outputs from a single input

C. To train faster using GPU acceleration

D. To reduce the number of layers in the model

Solution

1. Step 1: Understand multi-input models

   Multi-input models are designed to take multiple data sources as inputs simultaneously.

2. Step 2: Differentiate from multi-output models

   Multi-output models predict multiple outputs but usually from a single input source.

3. Final Answer:

   To accept more than one data source at the same time -> Option A

4. Quick Check:

   Multi-input = multiple data sources [OK]

Hint: Multi-input means many inputs, not many outputs [OK]

Common Mistakes:

• Confusing multi-input with multi-output
• Thinking multi-input reduces layers
• Assuming multi-input speeds training automatically

2. Which of the following is the correct way to define two inputs in a TensorFlow Keras model?

easy

A. inputs = tf.keras.Input(shape=(10, 5))

B. inputs = tf.keras.Input(shape=(10,)), tf.keras.Input(shape=(5,))

C. inputs = [tf.keras.Input(shape=(10,)), tf.keras.Input(shape=(5,))]

D. inputs = tf.keras.Input(shape=(10,)); inputs = tf.keras.Input(shape=(5,))

Solution

1. Step 1: Recall how to define multiple inputs

   Multiple inputs should be stored as a list of Input layers in Keras.

2. Step 2: Check each option

   inputs = [tf.keras.Input(shape=(10,)), tf.keras.Input(shape=(5,))] correctly creates a list of two Input layers. inputs = tf.keras.Input(shape=(10,)), tf.keras.Input(shape=(5,)) creates a tuple but does not assign it properly. inputs = tf.keras.Input(shape=(10, 5)) defines a single input with combined shape. inputs = tf.keras.Input(shape=(10,)); inputs = tf.keras.Input(shape=(5,)) overwrites the first input with the second.

3. Final Answer:

   inputs = [tf.keras.Input(shape=(10,)), tf.keras.Input(shape=(5,))] -> Option C

4. Quick Check:

   Multiple inputs = list of Input layers [OK]

Hint: Use a list to hold multiple Input layers [OK]

Common Mistakes:

• Using a tuple instead of a list for inputs
• Overwriting inputs instead of storing both
• Combining shapes into one input incorrectly

3. What will be the output shape of the following multi-output model?

input1 = tf.keras.Input(shape=(8,))
input2 = tf.keras.Input(shape=(4,))
x1 = tf.keras.layers.Dense(5)(input1)
x2 = tf.keras.layers.Dense(3)(input2)
output1 = tf.keras.layers.Dense(2)(x1)
output2 = tf.keras.layers.Dense(1)(x2)
model = tf.keras.Model(inputs=[input1, input2], outputs=[output1, output2])
print([o.shape for o in model.outputs])

medium

A. [TensorShape([None, 2]), TensorShape([None, 1])]

B. [TensorShape([8, 2]), TensorShape([4, 1])]

C. [TensorShape([None, 5]), TensorShape([None, 3])]

D. [TensorShape([None, 8]), TensorShape([None, 4])]

Solution

1. Step 1: Trace output layers shapes

   output1 is Dense(2) applied to x1, so shape is (None, 2). output2 is Dense(1) applied to x2, so shape is (None, 1).

2. Step 2: Understand batch dimension

   TensorFlow uses None for batch size, so output shapes include None as first dimension.

3. Final Answer:

   [TensorShape([None, 2]), TensorShape([None, 1])] -> Option A

4. Quick Check:

   Output shapes match Dense layer units [OK]

Hint: Output shape = batch size null + Dense units [OK]

Common Mistakes:

• Confusing input shape with output shape
• Ignoring batch dimension null
• Mixing intermediate layer shapes with output shapes

4. Identify the error in this multi-output model definition:

input = tf.keras.Input(shape=(10,))
x = tf.keras.layers.Dense(8)(input)
output1 = tf.keras.layers.Dense(4)(x)
output2 = tf.keras.layers.Dense(3)(x)
model = tf.keras.Model(inputs=input, outputs=[output1, output2])

medium

A. inputs should be a list when there are multiple outputs

B. outputs should be a single tensor, not a list

C. inputs must be a list even if only one input exists

D. No error, the model is defined correctly

Solution

1. Step 1: Check inputs parameter

   inputs can be a single Input layer if there is only one input source.

2. Step 2: Check outputs parameter

   outputs can be a list of tensors to define multiple outputs.

3. Final Answer:

   No error, the model is defined correctly -> Option D

4. Quick Check:

   Single input + multiple outputs = valid model [OK]

Hint: Single input can be passed directly, outputs can be list [OK]

Common Mistakes:

• Thinking inputs must always be a list
• Believing outputs cannot be a list
• Assuming multiple outputs require multiple inputs

5. You want to build a model that takes two inputs: an image (shape 64x64x3) and a vector of 10 features. It should output two predictions: a 5-class classification and a single continuous value. Which is the correct way to define the model inputs and outputs?

hard

A. inputs = [tf.keras.Input(shape=(64,64,3)), tf.keras.Input(shape=(10,))]; outputs = tf.keras.layers.Dense(6)(inputs)

B. inputs = [tf.keras.Input(shape=(64,64,3)), tf.keras.Input(shape=(10,))]; outputs = [tf.keras.layers.Dense(5, activation='softmax')(x), tf.keras.layers.Dense(1)(y)]

C. inputs = tf.keras.Input(shape=(64,64,3)); outputs = [tf.keras.layers.Dense(5)(inputs), tf.keras.layers.Dense(1)(inputs)]

D. inputs = tf.keras.Input(shape=(74,)); outputs = [tf.keras.layers.Dense(5)(inputs), tf.keras.layers.Dense(1)(inputs)]

Solution

1. Step 1: Define inputs separately for image and vector

   Two inputs require two Input layers with correct shapes: (64,64,3) for image and (10,) for vector.

2. Step 2: Define outputs separately for classification and regression

   Outputs are two layers: one Dense with 5 units and softmax for classification, one Dense with 1 unit for continuous value.

3. Final Answer:

   inputs = [tf.keras.Input(shape=(64,64,3)), tf.keras.Input(shape=(10,))]; outputs = [tf.keras.layers.Dense(5, activation='softmax')(x), tf.keras.layers.Dense(1)(y)] -> Option B

4. Quick Check:

   Separate inputs and outputs for multi-input/output model [OK]

Hint: Match each input and output with separate Input and Dense layers [OK]

Common Mistakes:

• Combining inputs into one vector incorrectly
• Using single input for different data types
• Outputting combined units instead of separate outputs