TensorFlow Object Detection API - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Model Choice

intermediate

Choosing the right pre-trained model for fast object detection

You want to detect objects in real-time video on a mobile device using TensorFlow Object Detection API. Which pre-trained model is best suited for this task?

A SSD MobileNet V2, because it balances speed and accuracy well for mobile devices.

B Faster R-CNN ResNet101, because it has the highest accuracy regardless of speed.

C Mask R-CNN, because it provides instance segmentation which is faster than detection.

D YOLOv3, because it is included by default in TensorFlow Object Detection API.

💡 Hint

Think about the trade-off between speed and accuracy on limited hardware.

SSD MobileNet V2 is optimized for speed and works well on mobile devices. Faster R-CNN models are more accurate but slower. Mask R-CNN is for segmentation and slower. YOLOv3 is not included by default in TensorFlow Object Detection API.

❓ Predict Output

intermediate

Output shape of detection model predictions

Given a TensorFlow Object Detection API model loaded and run on an input image batch of shape (1, 300, 300, 3), what is the shape of the 'detection_boxes' output tensor?

TensorFlow

detections = model(input_tensor)
detection_boxes = detections['detection_boxes']
print(detection_boxes.shape)

A (100, 4)

B (1, 100, 4)

C (1, 300, 300, 4)

D (1, 10, 4)

💡 Hint

Detection models usually output a fixed number of boxes per image in the batch.

The detection_boxes tensor shape is (batch_size, max_detections, 4), where 4 represents box coordinates. The default max detections is 100.

❓ Hyperparameter

advanced

Effect of increasing batch size during training

When training a TensorFlow Object Detection API model, what is the most likely effect of increasing the batch size from 4 to 32 without changing the learning rate?

A Training will cause immediate overfitting due to larger batch size.

B Training will be slower per step and the model will always achieve better accuracy.

C Training speed and accuracy will remain unchanged because batch size does not affect training.

D Training will be faster per step but may cause the model to converge to a worse minimum.

💡 Hint

Consider how batch size affects gradient estimates and training dynamics.

Larger batch sizes speed up training per step but can reduce the noise in gradient updates, potentially leading to convergence to sharp or worse minima without adjusting learning rate.

❓ Metrics

advanced

Understanding mAP metric in object detection

What does the mean Average Precision (mAP) metric measure in TensorFlow Object Detection API evaluation?

A The speed of the model inference measured in frames per second.

B The average recall of the model ignoring precision.

C The average precision across all classes and IoU thresholds, reflecting detection accuracy.

D The total number of correctly detected objects regardless of false positives.

💡 Hint

Think about what precision and recall mean in detection tasks.

mAP summarizes precision-recall curves over all classes and IoU thresholds, giving a single accuracy score for detection quality.

🔧 Debug

expert

Debugging frozen graph loading error

You try to load a frozen detection graph in TensorFlow Object Detection API but get the error: 'ValueError: GraphDef cannot be parsed'. What is the most likely cause?

A The frozen graph file is corrupted or incomplete, causing parsing failure.

B The TensorFlow version is too new and does not support frozen graphs.

C The label map file is missing or incorrectly formatted.

D The input image size does not match the model's expected input size.

💡 Hint

Consider what causes GraphDef parsing errors when loading models.

Parsing errors usually mean the frozen graph file is corrupted, truncated, or not a valid protobuf file.

Practice

1. What is the main purpose of the TensorFlow Object Detection API?

easy

A. To translate languages

B. To generate text from images

C. To find and locate objects in images or videos

D. To create 3D models from photos

Solution

1. Step 1: Understand the API's function

   The TensorFlow Object Detection API is designed to detect objects by finding their locations in images or videos.

2. Step 2: Compare options with the API's purpose

   Only To find and locate objects in images or videos matches this purpose, while others describe unrelated tasks.

3. Final Answer:

   To find and locate objects in images or videos -> Option C

4. Quick Check:

   Object detection = find objects [OK]

Hint: Remember: Object Detection means locating objects [OK]

Common Mistakes:

• Confusing object detection with image translation
• Thinking it generates text from images
• Mixing it up with 3D modeling

2. Which of the following is the correct way to load a pre-trained object detection model in TensorFlow Object Detection API?

easy

A. model = tf.saved_model.load('path_to_model')

B. model = tf.keras.models.load_model('path_to_model')

C. model = tf.load_model('path_to_model')

D. model = tf.object_detection.load('path_to_model')

Solution

1. Step 1: Identify the correct TensorFlow function for loading saved models

   TensorFlow uses tf.saved_model.load() to load saved models, including object detection models.

2. Step 2: Check other options for correctness

   tf.keras.models.load_model() loads Keras models, not specifically object detection saved models; tf.load_model() and tf.object_detection.load() do not exist.

3. Final Answer:

   model = tf.saved_model.load('path_to_model') -> Option A

4. Quick Check:

   Use tf.saved_model.load() for saved models [OK]

Hint: Use tf.saved_model.load() to load detection models [OK]

Common Mistakes:

• Using tf.keras.models.load_model() for detection models
• Trying non-existent functions like tf.load_model()
• Confusing model loading with training functions

3. Given the following code snippet, what will be the output type of detection_boxes after running detection on an image?

import tensorflow as tf
model = tf.saved_model.load('ssd_mobilenet_v2')
image = tf.constant(image_np)
input_tensor = tf.expand_dims(image, 0)
output_dict = model(input_tensor)
detection_boxes = output_dict['detection_boxes']

medium

A. A tensor of shape [1, num_detections, 4] with box coordinates

B. A list of bounding box coordinates as tuples

C. A numpy array of class labels

D. A scalar float value representing confidence

Solution

1. Step 1: Understand the output of TensorFlow Object Detection model

   The model returns a dictionary with keys like 'detection_boxes', which is a tensor containing bounding box coordinates for detected objects.

2. Step 2: Check the shape and type of detection_boxes

   It is a tensor with shape [1, num_detections, 4], where 4 represents box coordinates (ymin, xmin, ymax, xmax).

3. Final Answer:

   A tensor of shape [1, num_detections, 4] with box coordinates -> Option A

4. Quick Check:

   detection_boxes = tensor with box coords [OK]

Hint: Detection boxes are tensors with shape [1, N, 4] [OK]

Common Mistakes:

• Thinking detection_boxes is a list or numpy array
• Confusing boxes with class labels or scores
• Expecting a scalar instead of a tensor

4. You run the following code but get a KeyError: 'detection_scores'. What is the most likely cause?

output_dict = model(input_tensor)
scores = output_dict['detection_scores']

medium

A. The image is not preprocessed

B. The input_tensor shape is incorrect

C. The model was not loaded properly

D. The model output dictionary keys are bytes, not strings

Solution

1. Step 1: Understand the KeyError cause

   A KeyError means the key 'detection_scores' is not found in output_dict.

2. Step 2: Check common output format issue

   TensorFlow Object Detection API sometimes returns keys as bytes (b'detection_scores'), so using string keys causes KeyError.

3. Final Answer:

   The model output dictionary keys are bytes, not strings -> Option D

4. Quick Check:

   Use bytes keys or decode keys to strings [OK]

Hint: Check if output keys are bytes, not strings [OK]

Common Mistakes:

• Assuming input shape error causes KeyError
• Thinking model loading failed without error
• Ignoring key type mismatch in output dictionary

5. You want to improve detection accuracy on a custom dataset using TensorFlow Object Detection API. Which approach is best?

hard

A. Use the model without any training on your data

B. Fine-tune a pre-trained model on your dataset

C. Train a model from scratch with random weights

D. Only increase the number of detection classes without training

Solution

1. Step 1: Understand transfer learning benefits

   Fine-tuning a pre-trained model uses learned features and adapts them to your data, improving accuracy efficiently.

2. Step 2: Evaluate other options

   Training from scratch requires much data and time; using a model without training won't adapt to new data; increasing classes without training won't improve accuracy.

3. Final Answer:

   Fine-tune a pre-trained model on your dataset -> Option B

4. Quick Check:

   Fine-tuning = best for custom data accuracy [OK]

Hint: Fine-tune pre-trained models for better custom results [OK]

Common Mistakes:

• Training from scratch without enough data
• Using pre-trained model without adaptation
• Changing classes without retraining