TensorFlow Object Detection API - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained TensorFlow object detection model.

TensorFlow

model = tf.saved_model.load('[1]')

Drag options to blanks, or click blank then click option'

Aload_model()

Bmodel.compile()

Cpath/to/saved_model

Dtf.keras.Model()

Attempts:

3 left

💡 Hint

Common Mistakes

Trying to call model.compile() before loading the model.

Using tf.keras.Model() which creates a new model instead of loading.

The tf.saved_model.load() function loads a saved TensorFlow model from the given directory path.

2fill in blank

medium

Complete the code to prepare an image tensor for object detection input.

TensorFlow

input_tensor = tf.convert_to_tensor(image)[1]

Drag options to blanks, or click blank then click option'

A[tf.newaxis, ...]

B.numpy()

C.reshape(-1)

D.astype('float32')

Attempts:

3 left

💡 Hint

Common Mistakes

Not adding a batch dimension causes shape errors.

Using .numpy() converts tensor to numpy array, which is not needed here.

Adding [tf.newaxis, ...] adds a batch dimension, which is required for the model input.

3fill in blank

hard

Fix the error in the code to get detection results from the model.

TensorFlow

detections = model(input_tensor)[1]

Drag options to blanks, or click blank then click option'

A[0]

B.items()

C.numpy()

D.pop()

Attempts:

3 left

💡 Hint

Common Mistakes

Calling .numpy() directly on the model output dictionary causes errors.

Using .items() or .pop() is not correct here.

The model returns a dictionary of tensors inside a batch dimension, so we select the first element with [0].

4fill in blank

hard

Fill both blanks to filter detection boxes with scores above 0.5.

TensorFlow

high_score_idxs = tf.where(detections['detection_scores'] [1] [2])

Drag options to blanks, or click blank then click option'

A>

B0.5

C<

D0.7

Attempts:

3 left

💡 Hint

Common Mistakes

Using less than < instead of greater than >.

Using the wrong threshold value.

We use tf.where() to find indices where detection scores are greater than 0.5.

5fill in blank

hard

Fill all three blanks to create a dictionary of filtered detection boxes and classes.

TensorFlow

filtered_detections = {
  'boxes': tf.gather(detections['detection_boxes'], [1]),
  'scores': tf.gather(detections['detection_scores'], [2]),
  'classes': tf.gather(detections['detection_classes'], [3])
}

Drag options to blanks, or click blank then click option'

Ahigh_score_idxs

Bdetections['detection_scores']

Chigh_score_idxs[:, 0]

Ddetections['detection_boxes']

Attempts:

3 left

💡 Hint

Common Mistakes

Using the full tensor instead of indices in tf.gather().

Not flattening indices for classes causes shape errors.

We use tf.gather() with the indices of high scoring detections to filter boxes, scores, and classes. Since tf.where() returns a 2D tensor, we select the first column for classes.

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