Pre-trained detection models in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

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

TensorFlow

import tensorflow_hub as hub
model = hub.load('[1]')

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

Ahttps://tfhub.dev/tensorflow/ssd_mobilenet_v2/2

Bhttps://tfhub.dev/tensorflow/resnet50/1

Chttps://tfhub.dev/tensorflow/bert_en_uncased_L-12_H-768_A-12/3

Dhttps://tfhub.dev/google/imagenet/inception_v3/classification/5

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing a classification model URL instead of a detection model URL.

Using a BERT model URL which is for NLP, not detection.

The URL 'https://tfhub.dev/tensorflow/ssd_mobilenet_v2/2' points to a pre-trained SSD MobileNet V2 detection model suitable for object detection tasks.

2fill in blank

medium

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

TensorFlow

import tensorflow as tf
image = tf.io.read_file('image.jpg')
image = tf.image.decode_jpeg(image, channels=3)
input_tensor = tf.expand_dims(image, axis=[1])

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

A2

B-1

C1

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Adding the batch dimension at the wrong axis causing shape errors.

Not adding a batch dimension at all.

The detection model expects a batch dimension, so we add a new axis at position 0 to create a batch of one image.

3fill in blank

hard

Fix the error in the code to run the detection model and get predictions.

TensorFlow

detections = model([1])

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

Aimage.numpy()

Binput_tensor

Cimage

Dtf.convert_to_tensor(image)

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the raw image tensor without batch dimension.

Passing a numpy array instead of a tensor.

The model expects a batch input tensor, so we must pass 'input_tensor' which has the batch dimension, not the raw image tensor.

4fill in blank

hard

Fill both blanks to extract detection boxes and scores from the model output.

TensorFlow

boxes = detections['[1]'][0].numpy()
scores = detections['[2]'][0].numpy()

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

Adetection_boxes

Bdetection_scores

Cdetection_classes

Dnum_detections

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'detection_classes' or 'num_detections' instead of boxes or scores.

Not removing the batch dimension by indexing [0].

The detection boxes are stored under 'detection_boxes' and the confidence scores under 'detection_scores' keys in the detections dictionary.

5fill in blank

hard

Fill all three blanks to filter detection results with scores above 0.5 and print the number of valid detections.

TensorFlow

valid_indices = [i for i, score in enumerate(scores) if score [1] [2]]
valid_boxes = boxes[valid_indices]
print('Number of detections:', [3](valid_boxes))

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

A>

B0.5

Clen

D==

Attempts:

3 left

💡 Hint

Common Mistakes

Using '==' instead of '>' causing no detections to pass.

Using sum() instead of len() to count boxes.

Not filtering scores correctly.

We filter scores greater than 0.5 using '>' and 0.5, then count valid boxes with len().

Practice

1. What is the main advantage of using a pre-trained detection model in TensorFlow?

easy

A. You can detect objects without training the model yourself

B. It always gives 100% accurate results

C. It requires no input image preprocessing

D. It only works with black and white images

Solution

1. Step 1: Understand pre-trained model purpose

   Pre-trained detection models are trained on large datasets and ready to use for object detection tasks without extra training.

2. Step 2: Identify the main benefit

   This means you save time and resources by not training from scratch and can detect objects directly.

3. Final Answer:

   You can detect objects without training the model yourself -> Option A

4. Quick Check:

   Pre-trained means ready to use without training [OK]

Hint: Pre-trained means no training needed before use [OK]

Common Mistakes:

• Thinking pre-trained models are always perfect
• Ignoring the need for image preprocessing
• Assuming models only work on certain image types

2. Which of the following is the correct way to load a pre-trained detection model from TensorFlow Hub?

easy

A. model = hub.load_model('ssd_mobilenet_v2')

B. model = tf.load_model('ssd_mobilenet_v2')

C. model = hub.load('https://tfhub.dev/tensorflow/ssd_mobilenet_v2/2')

D. model = tfhub.load('ssd_mobilenet_v2')

Solution

1. Step 1: Recall TensorFlow Hub loading syntax

   The correct function to load models from TensorFlow Hub is hub.load() with the full URL or handle.

2. Step 2: Identify the correct option

   model = hub.load('https://tfhub.dev/tensorflow/ssd_mobilenet_v2/2') uses hub.load() with a valid URL, which is the correct method.

3. Final Answer:

   model = hub.load('https://tfhub.dev/tensorflow/ssd_mobilenet_v2/2') -> Option C

4. Quick Check:

   Use hub.load() with URL to load models [OK]

Hint: Use hub.load() with full model URL [OK]

Common Mistakes:

• Using tf.load_model which does not exist
• Confusing hub.load_model with hub.load
• Missing full URL in hub.load

3. Given the following code snippet, what is the shape of the input tensor passed to the detection model?

import tensorflow as tf
image = tf.io.read_file('image.jpg')
image = tf.image.decode_jpeg(image, channels=3)
input_tensor = tf.expand_dims(tf.image.convert_image_dtype(image, tf.float32), 0)
print(input_tensor.shape)

medium

A. (height, width, 3)

B. (1, height, width, 3)

C. (3, height, width)

D. (height, width)

Solution

1. Step 1: Understand image preprocessing steps

   The image is decoded to shape (height, width, 3) for RGB channels, then converted to float32.

2. Step 2: Analyze tf.expand_dims usage

   tf.expand_dims adds a batch dimension at axis 0, making shape (1, height, width, 3).

3. Final Answer:

   (1, height, width, 3) -> Option B

4. Quick Check:

   Batch dimension added first, then image shape [OK]

Hint: expand_dims adds batch size as first dimension [OK]

Common Mistakes:

• Forgetting batch dimension
• Mixing channel order
• Confusing shape with no batch

4. You run a pre-trained detection model but get an error: ValueError: Input tensor must have 4 dimensions. What is the most likely cause?

medium

A. The input tensor is missing the batch dimension

B. The input image was not converted to float32

C. The model URL is incorrect

D. The image file is corrupted

Solution

1. Step 1: Understand model input requirements

   Pre-trained detection models expect input tensors with shape (batch_size, height, width, channels), which means 4 dimensions.

2. Step 2: Identify cause of 4D tensor error

   If the input tensor lacks the batch dimension, it will have only 3 dimensions, causing this error.

3. Final Answer:

   The input tensor is missing the batch dimension -> Option A

4. Quick Check:

   Batch dimension missing causes 4D input error [OK]

Hint: Check if input tensor has batch dimension (4 dims) [OK]

Common Mistakes:

• Assuming float32 conversion fixes dimension error
• Blaming model URL for input shape errors
• Ignoring batch dimension requirement

5. You want to detect objects in multiple images using a pre-trained TensorFlow detection model. Which approach correctly prepares a batch of images for the model?

hard

A. Run the model separately on each image without batching

B. Pass a list of image file paths directly to the model

C. Concatenate images along the channel axis to shape (height, width, batch_size*3)

D. Stack individual preprocessed images into a tensor with shape (batch_size, height, width, 3)

Solution

1. Step 1: Understand batch input format

   Pre-trained detection models expect a 4D tensor with batch size as the first dimension, so multiple images must be stacked into one tensor.

2. Step 2: Evaluate options for batch preparation

   Stack individual preprocessed images into a tensor with shape (batch_size, height, width, 3) correctly stacks images into shape (batch_size, height, width, 3). Options B and C do not produce valid input tensors. Run the model separately on each image without batching works but is inefficient.

3. Final Answer:

   Stack individual preprocessed images into a tensor with shape (batch_size, height, width, 3) -> Option D

4. Quick Check:

   Batch images as 4D tensor for detection [OK]

Hint: Batch images by stacking into 4D tensor [OK]

Common Mistakes:

• Passing file paths instead of tensors
• Concatenating along wrong axis
• Ignoring batch processing benefits