Loading and inference in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of model prediction after loading

Given the following TensorFlow code that loads a saved model and runs inference on a sample input, what will be the printed output?

TensorFlow

import tensorflow as tf
import numpy as np

model = tf.keras.models.load_model('my_model')
sample_input = np.array([[1.0, 2.0, 3.0]])
prediction = model.predict(sample_input)
print(prediction)

A [[0.3 0.4 0.3]]

B Raises a FileNotFoundError

C [[0.1 0.7 0.2]]

D A numpy array with shape (1, 3) containing probabilities

💡 Hint

The output shape and type depend on the model's last layer and input shape.

The model.predict returns a numpy array with shape matching the output layer. Since the model is loaded successfully, it returns a numpy array of probabilities or values, not a fixed hardcoded array.

❓ Model Choice

intermediate

Choosing the correct method to load a TensorFlow model

Which TensorFlow method correctly loads a saved Keras model for inference?

A tf.keras.load('path_to_model')

B tf.saved_model.load('path_to_model')

C tf.keras.models.load_model('path_to_model')

D tf.load_model('path_to_model')

💡 Hint

Keras models have a specific loading function.

The correct method to load a saved Keras model is tf.keras.models.load_model. The other options are either invalid or used for different purposes.

❓ Hyperparameter

advanced

Effect of batch size on inference speed

When performing inference with a loaded TensorFlow model, how does increasing the batch size generally affect inference speed and memory usage?

A Inference speed per sample increases and memory usage increases

B Inference speed per sample decreases and memory usage increases

C Inference speed per sample decreases and memory usage decreases

D Inference speed per sample increases and memory usage decreases

💡 Hint

Think about processing multiple inputs at once.

Increasing batch size allows the model to process more samples simultaneously, often improving throughput (speed per sample), but it also requires more memory to hold the batch data.

❓ Metrics

advanced

Interpreting inference output probabilities

A loaded TensorFlow classification model outputs the following prediction for a single input: [[0.05, 0.9, 0.05]]. What does this output represent?

A The model predicts class 2 with 90% confidence

B The model predicts class 1 with 90% confidence

C The model predicts class 0 with 90% confidence

D The model output is invalid because probabilities do not sum to 1

💡 Hint

Look at the highest probability and its index.

The output is a probability distribution over classes. The highest value 0.9 is at index 1, so the model predicts class 1 with 90% confidence.

🔧 Debug

expert

Identifying the cause of an error during model loading

You run the following code to load a TensorFlow model saved in 'model_dir', but get the error: "OSError: SavedModel file does not exist at: model_dir". What is the most likely cause?

TensorFlow

import tensorflow as tf
model = tf.keras.models.load_model('model_dir')

A The path 'model_dir' is incorrect or the directory does not contain a saved model

B The model was saved using tf.saved_model.save instead of tf.keras.models.save_model

C The model file is corrupted and cannot be loaded

D TensorFlow version is incompatible with the saved model format

💡 Hint

Check the file path and directory contents.

The error indicates the specified path does not contain the expected saved model files. This usually means the path is wrong or the model was not saved there.

Practice

1. What is the main purpose of tf.keras.models.load_model() in TensorFlow?

easy

A. To visualize the model architecture

B. To load a previously saved model for inference or further training

C. To compile a model with loss and optimizer

D. To create a new model architecture from scratch

Solution

1. Step 1: Understand the function purpose

   tf.keras.models.load_model() is used to load a model that was saved earlier, including its architecture, weights, and optimizer state.

2. Step 2: Differentiate from other functions

   Creating a new model or compiling it are separate steps. Loading is specifically for retrieving a saved model.

3. Final Answer:

   To load a previously saved model for inference or further training -> Option B

4. Quick Check:

   Load saved model = load_model() [OK]

Hint: Load saved models with load_model() function [OK]

Common Mistakes:

• Confusing load_model() with model creation
• Thinking load_model() compiles the model
• Assuming load_model() only loads weights

2. Which of the following is the correct way to get predictions from a loaded TensorFlow model named model on input data new_data?

easy

A. predictions = model.predict(new_data)

B. predictions = model.fit(new_data)

C. predictions = model.evaluate(new_data)

D. predictions = model.compile(new_data)

Solution

1. Step 1: Identify the correct method for inference

   To get predictions from a model, the method predict() is used.

2. Step 2: Understand other methods

   fit() trains the model, evaluate() tests performance, and compile() sets up the model.

3. Final Answer:

   predictions = model.predict(new_data) -> Option A

4. Quick Check:

   Predict new data = model.predict() [OK]

Hint: Use model.predict() to get predictions [OK]

Common Mistakes:

• Using fit() instead of predict() for inference
• Calling evaluate() expecting predictions
• Trying to compile() during prediction

3. Given the following code, what will be the shape of predictions?

import tensorflow as tf
import numpy as np
model = tf.keras.Sequential([
  tf.keras.layers.Dense(3, input_shape=(4,))
])
model.compile(optimizer='adam', loss='mse')
input_data = np.array([[1, 2, 3, 4], [5, 6, 7, 8]])
predictions = model.predict(input_data)

medium

A. (3, 4)

B. (4, 3)

C. (2, 3)

D. (2, 4)

Solution

1. Step 1: Analyze input shape and batch size

   The input data has shape (2, 4) meaning 2 samples, each with 4 features.

2. Step 2: Determine output shape from model layer

   The Dense layer outputs 3 units per sample, so output shape is (2, 3).

3. Final Answer:

   (2, 3) -> Option C

4. Quick Check:

   Input batch 2, output units 3 = (2, 3) [OK]

Hint: Output shape = (batch_size, units in last layer) [OK]

Common Mistakes:

• Confusing input shape with output shape
• Mixing batch size and feature dimensions
• Assuming output shape matches input shape

4. You loaded a model with model = tf.keras.models.load_model('my_model') but get this error when calling model.predict(new_data): ValueError: Error when checking input: expected dense_input to have shape (4,) but got array with shape (3,). What is the likely cause?

medium

A. The input data shape does not match the model's expected input shape

B. The model was not compiled before prediction

C. The model file is corrupted

D. The predict() method was called without training the model

Solution

1. Step 1: Understand the error message

   The error says the model expects input shape (4,), but received (3,), meaning input data shape is wrong.

2. Step 2: Rule out other causes

   Model compilation is not required for prediction, corrupted files cause different errors, and training is not needed for predict().

3. Final Answer:

   The input data shape does not match the model's expected input shape -> Option A

4. Quick Check:

   Input shape mismatch = ValueError [OK]

Hint: Match input data shape to model input shape exactly [OK]

Common Mistakes:

• Ignoring input shape mismatch
• Thinking model must be compiled before predict
• Assuming predict requires training first

5. You have a saved TensorFlow model that expects input shape (None, 5). You want to predict on a single sample with 5 features stored in a list sample = [1, 2, 3, 4, 5]. Which code snippet correctly prepares the input and gets the prediction?

hard

A. input_data = np.array(sample)
prediction = model.predict(input_data)

B. input_data = np.array(sample).reshape(1, 1, 5)
prediction = model.predict(input_data)

C. input_data = np.array(sample).reshape(5, 1)
prediction = model.predict(input_data)

D. import numpy as np
input_data = np.array([sample])
prediction = model.predict(input_data)

Solution

1. Step 1: Understand model input shape

   The model expects input shape (None, 5), where None is batch size, so input must be 2D with shape (batch_size, 5).

2. Step 2: Prepare input data correctly

   Wrapping the sample list in another list creates shape (1, 5), which matches expected input.

3. Step 3: Check other options

   input_data = np.array(sample) prediction = model.predict(input_data) gives shape (5,), not 2D; input_data = np.array(sample).reshape(5, 1) prediction = model.predict(input_data) reshapes to (5,1) which is wrong; input_data = np.array(sample).reshape(1, 1, 5) prediction = model.predict(input_data) reshapes to (1,1,5) which is 3D and incorrect.

4. Final Answer:

   import numpy as np input_data = np.array([sample]) prediction = model.predict(input_data) -> Option D

5. Quick Check:

   Input shape (1,5) matches model input [OK]

Hint: Wrap single sample in list to add batch dimension [OK]

Common Mistakes:

• Passing 1D array instead of 2D batch input
• Incorrect reshaping causing wrong input dimensions
• Adding extra unnecessary dimensions