Object detection concepts in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

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

TensorFlow

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

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

Atext_classification_model

Blinear_regression_model

Cssd_mobilenet_v2_fpnlite_320x320/saved_model

Drandom_forest_model

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing a model path for a different task like text classification or regression.

Using an incorrect or non-existent model path.

The correct path points to a pre-trained object detection model saved in TensorFlow's SavedModel format.

2fill in blank

medium

Complete the code to convert an image to a tensor suitable for object detection input.

TensorFlow

input_tensor = tf.convert_to_tensor(image)[1]

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

A.expand_dims(axis=0)

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.

Object detection models expect a batch dimension, so we add one with expand_dims(axis=0).

3fill in blank

hard

Fix the error in the code to extract detection boxes from the model output dictionary.

TensorFlow

boxes = detections['[1]']

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

Aboxes_detected

Bdetection_boxes

Cbbox

Ddetection_coords

Attempts:

3 left

💡 Hint

Common Mistakes

Using incorrect or non-existent dictionary keys causes KeyError.

Guessing keys without checking model output structure.

The standard key for bounding boxes in TensorFlow object detection output is detection_boxes.

4fill in blank

hard

Fill both blanks to filter detection scores above a threshold and get corresponding boxes.

TensorFlow

scores = detections['detection_scores']
filtered_boxes = boxes[scores [1] [2]]

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

A>

B0.5

C<

D0.8

Attempts:

3 left

💡 Hint

Common Mistakes

Using '<' instead of '>' filters out confident detections.

Choosing too high or too low threshold affects results.

We select boxes where the detection score is greater than 0.5 to keep confident detections.

5fill in blank

hard

Fill all three blanks to create a dictionary of detected class names and their scores above threshold.

TensorFlow

classes = detections['detection_classes']
scores = detections['detection_scores']
result = {str(classes[i]): scores[i] for i in range(len(scores)) if scores[i] [1] [2] and classes[i] != [3]

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

A>

B0.6

C0

D==

Attempts:

3 left

💡 Hint

Common Mistakes

Using '==' instead of '!=' excludes all classes except background.

Using too low threshold includes many false positives.

This code keeps detections with scores above 0.6 and ignores background class labeled as 0.

Practice

1. What is the main goal of object detection in TensorFlow?

easy

A. To find and label objects in images with bounding boxes

B. To generate captions for images

C. To classify images into categories without localization

D. To enhance image resolution

Solution

1. Step 1: Understand object detection task

   Object detection locates objects in images and labels them with boxes.

2. Step 2: Compare options with definition

   Only To find and label objects in images with bounding boxes describes finding and labeling objects with boxes, matching object detection.

3. Final Answer:

   To find and label objects in images with bounding boxes -> Option A

4. Quick Check:

   Object detection = find and label objects [OK]

Hint: Object detection = find + label objects with boxes [OK]

Common Mistakes:

• Confusing object detection with image classification
• Thinking object detection generates captions
• Mixing up image enhancement with detection

2. Which part of an object detection model is responsible for extracting features from images?

easy

A. Head

B. Backbone

C. Loss function

D. Anchor generator

Solution

1. Step 1: Identify model components

   Backbone extracts features; head predicts boxes and classes.

2. Step 2: Match roles to options

   Backbone matches feature extraction role, so Backbone is correct.

3. Final Answer:

   Backbone -> Option B

4. Quick Check:

   Feature extractor = Backbone [OK]

Hint: Backbone extracts features, head predicts boxes [OK]

Common Mistakes:

• Confusing head with feature extractor
• Thinking loss function extracts features
• Mixing anchor generator with backbone

3. Given this TensorFlow code snippet for object detection model summary, what is the output shape of the backbone's last layer?

import tensorflow as tf
base_model = tf.keras.applications.MobileNetV2(input_shape=(224,224,3), include_top=False)
print(base_model.output_shape)

medium

A. (None, 7, 7, 1280)

B. (None, 14, 14, 512)

C. (None, 224, 224, 3)

D. (None, 1, 1, 1000)

Solution

1. Step 1: Understand MobileNetV2 output shape

   MobileNetV2 with include_top=False outputs feature maps of shape (None, 7, 7, 1280) for 224x224 input.

2. Step 2: Match output shape to options

   (None, 7, 7, 1280) matches expected output shape; others do not.

3. Final Answer:

   (None, 7, 7, 1280) -> Option A

4. Quick Check:

   MobileNetV2 backbone output = (None,7,7,1280) [OK]

Hint: MobileNetV2 backbone outputs 7x7x1280 feature maps [OK]

Common Mistakes:

• Confusing input shape with output shape
• Choosing output with wrong spatial dimensions
• Assuming include_top=True output shape

4. Identify the error in this TensorFlow object detection training code snippet:

model.compile(optimizer='adam', loss='categorical_crossentropy')
model.fit(train_images, train_boxes, epochs=5)

medium

A. fit method missing batch_size argument

B. Missing optimizer parameter in compile

C. Using 'categorical_crossentropy' loss instead of a detection loss

D. train_boxes should be train_labels

Solution

1. Step 1: Check loss function suitability

   Object detection needs specialized loss (e.g., localization + classification), not plain categorical_crossentropy.

2. Step 2: Validate other code parts

   Optimizer is given, train_boxes is correct for boxes, batch_size is optional.

3. Final Answer:

   Using 'categorical_crossentropy' loss instead of a detection loss -> Option C

4. Quick Check:

   Detection needs special loss, not categorical_crossentropy [OK]

Hint: Detection needs combined loss, not plain classification loss [OK]

Common Mistakes:

• Using classification loss for detection
• Confusing train_boxes with labels
• Assuming batch_size is mandatory

5. You want to improve an object detection model's accuracy on small objects. Which approach is best to try first?

hard

A. Remove the backbone and use only the head

B. Reduce number of training epochs

C. Use grayscale images instead of color

D. Increase input image resolution and adjust anchor box sizes

Solution

1. Step 1: Understand small object detection challenges

   Small objects need higher resolution and anchors matching their size for better detection.

2. Step 2: Evaluate options for improving small object accuracy

   Increasing resolution and adjusting anchors directly helps; reducing epochs or removing backbone harms performance; grayscale reduces info.

3. Final Answer:

   Increase input image resolution and adjust anchor box sizes -> Option D

4. Quick Check:

   Small objects = higher res + proper anchors [OK]

Hint: Small objects need bigger input and matching anchors [OK]

Common Mistakes:

• Reducing epochs thinking it helps accuracy
• Removing backbone reduces feature quality
• Using grayscale loses color info needed for detection