Pre-trained detection models in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of loading a pre-trained detection model

What is the output type of the variable model after running the following code snippet?

TensorFlow

import tensorflow as tf
model = tf.saved_model.load('ssd_mobilenet_v2_fpnlite_320x320/saved_model')
print(type(model))

A <class 'tensorflow.python.saved_model.load.Loader._recreate_base_user_object.<locals>.UserObject'>

B <class 'tensorflow.python.saved_model.load.Loader'>

C <class 'tensorflow.python.saved_model.load._UserObject'>

D <class 'tensorflow.python.keras.engine.functional.Functional'>

💡 Hint

The loaded model is a TensorFlow SavedModel object, not a Keras model.

TensorFlow's tf.saved_model.load returns a _UserObject representing the loaded SavedModel, which is not a Keras Functional model.

❓ Model Choice

intermediate

Choosing a pre-trained detection model for real-time mobile app

Which pre-trained detection model is best suited for a real-time mobile application requiring fast inference with reasonable accuracy?

A SSD MobileNet V2

B YOLOv3 with Darknet-53 backbone

C Mask R-CNN with ResNet-50 backbone

D Faster R-CNN with ResNet-101 backbone

💡 Hint

Consider model size and speed for mobile devices.

SSD MobileNet V2 is optimized for speed and low resource use, making it suitable for mobile real-time detection.

❓ Hyperparameter

advanced

Effect of changing the confidence threshold in detection output

In a pre-trained object detection model, what happens if you increase the confidence threshold from 0.5 to 0.8 when filtering detection results?

A The detection speed will significantly increase due to fewer objects processed.

B The model retrains itself to improve accuracy automatically.

C More detected objects will be shown, including many false positives.

D Fewer detected objects will be shown, reducing false positives but possibly missing true objects.

💡 Hint

Think about how confidence threshold affects filtering predictions.

Increasing the confidence threshold filters out detections with lower confidence scores, reducing false positives but possibly missing some true detections.

❓ Metrics

advanced

Understanding mAP metric in object detection

What does the mean Average Precision (mAP) metric measure in evaluating a pre-trained object detection model?

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

B The average confidence score of all detected objects.

C The average speed of the model in frames per second.

D The average number of detected objects per image.

💡 Hint

mAP combines precision and recall over classes and IoU thresholds.

mAP summarizes how well the model detects objects correctly across classes and overlap thresholds, combining precision and recall.

🔧 Debug

expert

Debugging missing detections from a pre-trained model

You load a pre-trained SSD MobileNet V2 model and run detection on images, but no objects are detected (empty results). Which is the most likely cause?

A The confidence threshold is set too high, filtering out all detections.

B The input images are not normalized or resized to the model's expected input size.

C The model weights file is corrupted and cannot detect objects.

D The model was trained on a different dataset and cannot detect any objects.

💡 Hint

Check the input preprocessing steps before feeding images to the model.

Pre-trained detection models expect inputs of specific size and normalization; incorrect preprocessing leads to no detections.

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