YOLO concept overview in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the YOLO model from TensorFlow Hub.

TensorFlow

import tensorflow_hub as [1]

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

Amodel

Btf

Ckeras

Dhub

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'tf' instead of 'hub' to import tensorflow_hub.

Trying to import YOLO directly from tensorflow instead of tensorflow_hub.

The TensorFlow Hub library is imported as 'hub' to load pre-trained models like YOLO.

2fill in blank

medium

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

TensorFlow

model = hub.load('[1]')

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

Ahttps://tfhub.dev/tensorflow/mobilenet_v2/1

Bhttps://tfhub.dev/tensorflow/resnet_v2_50/1

Chttps://tfhub.dev/tensorflow/yolo_v3/1

Dhttps://tfhub.dev/tensorflow/inception_v3/1

Attempts:

3 left

💡 Hint

Common Mistakes

Using URLs for other models like ResNet or MobileNet instead of YOLO.

Missing the correct version number in the URL.

The YOLO v3 model URL on TensorFlow Hub is used to load the pre-trained YOLO model.

3fill in blank

hard

Fix the error in the code to preprocess an input image for YOLO model prediction.

TensorFlow

input_tensor = tf.image.resize(image, ([1], [1])) / 255.0

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

A416

B224

C128

D512

Attempts:

3 left

💡 Hint

Common Mistakes

Using 224 which is common for classification but not YOLO.

Not resizing the image to the correct input size.

YOLO models typically require input images resized to 416x416 pixels and normalized between 0 and 1.

4fill in blank

hard

Fill both blanks to extract bounding boxes and class scores from YOLO output.

TensorFlow

boxes, scores = model([1])
classes = tf.argmax(scores, axis=[2])

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

Ainput_tensor

B0

C1

Doutput_tensor

Attempts:

3 left

💡 Hint

Common Mistakes

Using axis=0 which would select the wrong dimension.

Passing an undefined variable like 'output_tensor' to the model.

The model takes the preprocessed input tensor. Class scores are along axis 1, so argmax uses axis=1.

5fill in blank

hard

Fill all three blanks to filter detected objects with confidence above 0.5 and prepare final results.

TensorFlow

conf_mask = scores[:, [1]] > [2]
filtered_boxes = tf.boolean_mask(boxes, conf_mask)
filtered_scores = tf.boolean_mask(scores[:, [3]], conf_mask)

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

A0

B0.5

C1

D2

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong column indices for confidence scores.

Using a threshold other than 0.5 which is standard for filtering.

Confidence scores are in column 0, so scores[:,0]. We filter scores greater than 0.5. The filtered scores use the same column 0.

Practice

1. What is the main idea behind the YOLO (You Only Look Once) model in object detection?

easy

A. It splits the image into a grid and predicts bounding boxes and classes for each cell.

B. It processes each object separately in multiple passes.

C. It uses a sliding window to scan the image multiple times.

D. It detects objects by comparing image patches with a database.

Solution

1. Step 1: Understand YOLO's approach to image processing

   YOLO divides the input image into a grid and predicts bounding boxes and class probabilities for each grid cell in one pass.

2. Step 2: Compare with other detection methods

   Unlike sliding window or multiple passes, YOLO predicts all objects at once, making it fast and efficient.

3. Final Answer:

   It splits the image into a grid and predicts bounding boxes and classes for each cell. -> Option A

4. Quick Check:

   YOLO grid prediction = It splits the image into a grid and predicts bounding boxes and classes for each cell. [OK]

Hint: YOLO predicts all objects in one grid pass [OK]

Common Mistakes:

• Thinking YOLO scans image multiple times
• Confusing YOLO with sliding window methods
• Believing YOLO processes objects one by one

2. Which of the following is the correct way to describe YOLO's output format?

easy

A. A single large tensor containing bounding box coordinates and class probabilities for all grid cells.

B. A list of detected objects with coordinates and classes, one by one.

C. Multiple small tensors each representing a detected object separately.

D. A heatmap showing object presence without bounding boxes.

Solution

1. Step 1: Recall YOLO's output structure

   YOLO outputs a single large tensor that encodes bounding boxes and class probabilities for every grid cell simultaneously.

2. Step 2: Eliminate other options

   Options A and C describe separate outputs per object, which is not how YOLO works. A heatmap showing object presence without bounding boxes describes a heatmap, which is not YOLO's output.

3. Final Answer:

   A single large tensor containing bounding box coordinates and class probabilities for all grid cells. -> Option A

4. Quick Check:

   YOLO outputs one big tensor = A single large tensor containing bounding box coordinates and class probabilities for all grid cells. [OK]

Hint: YOLO outputs one big tensor for all predictions [OK]

Common Mistakes:

• Thinking YOLO outputs separate tensors per object
• Confusing YOLO output with heatmaps
• Assuming YOLO outputs a list instead of a tensor

3. Given a YOLO model that splits an image into a 7x7 grid and predicts 2 bounding boxes per cell with 20 classes, what is the shape of the output tensor?

medium

A. (7, 7, 28)

B. (7, 7, 50)

C. (7, 7, 44)

D. (7, 7, 30)

Solution

1. Step 1: Calculate output features per grid cell

   Each cell predicts 2 bounding boxes. Each box has 5 values (x, y, width, height, confidence), so 2*5=10. Plus 20 class probabilities, total 10+20=30 per cell.

2. Step 2: Calculate total output tensor shape

   Grid size is 7x7, so output shape is (7, 7, 30). But (7, 7, 50) says (7,7,50), so check carefully.

3. Step 3: Re-examine calculations

   Actually, each bounding box has 5 values, so 2 boxes = 10 values. Adding 20 class probabilities gives 30 per cell, so output shape is (7,7,30).

4. Final Answer:

   (7, 7, 30) -> Option D

5. Quick Check:

   Output shape = grid size * (2*5 + 20) = (7,7,30) [OK]

Hint: Output depth = 2*5 + number_of_classes [OK]

Common Mistakes:

• Adding bounding boxes and classes incorrectly
• Confusing number of boxes with classes
• Miscounting bounding box parameters

4. You wrote a YOLO model that outputs a tensor of shape (7, 7, 25) but your dataset has 3 bounding boxes per cell and 20 classes. What is the likely error?

medium

A. Number of classes should be 5, not 20.

B. Output tensor depth is too small; should be 3*5 + 20 = 35, not 25.

C. Output tensor shape is correct; no error.

D. Grid size should be 5x5, not 7x7.

Solution

1. Step 1: Calculate expected output depth

   Each bounding box has 5 values, so 3 boxes = 15 values. Adding 20 classes gives 15 + 20 = 35 values per grid cell.

2. Step 2: Compare with given output shape

   The model outputs (7, 7, 25), which is less than expected 35, indicating the output tensor depth is too small.

3. Final Answer:

   Output tensor depth is too small; should be 3*5 + 20 = 35, not 25. -> Option B

4. Quick Check:

   Output depth mismatch = Output tensor depth is too small; should be 3*5 + 20 = 35, not 25. [OK]

Hint: Check output depth = boxes*5 + classes [OK]

Common Mistakes:

• Ignoring bounding box parameters count
• Assuming output shape is always (7,7,25)
• Mixing grid size with output depth

5. You want to improve YOLO's real-time detection speed on a mobile device. Which approach is best while keeping reasonable accuracy?

hard

A. Reduce the grid size to 3x3 and keep 2 bounding boxes per cell.

B. Increase the number of bounding boxes per cell to 5 for better coverage.

C. Use a smaller backbone network and reduce input image size.

D. Increase input image size to get more details.

Solution

1. Step 1: Understand speed vs accuracy trade-offs

   Reducing model size and input resolution speeds up inference but may reduce accuracy slightly.

2. Step 2: Evaluate options for mobile optimization

   Reduce the grid size to 3x3 and keep 2 bounding boxes per cell reduces grid size too much, hurting detection detail. Increase the number of bounding boxes per cell to 5 for better coverage increases complexity, slowing down. Increase input image size to get more details increases input size, slowing down.

3. Step 3: Choose best option

   Using a smaller backbone and smaller input size balances speed and accuracy well for mobile devices.

4. Final Answer:

   Use a smaller backbone network and reduce input image size. -> Option C

5. Quick Check:

   Smaller model + input = faster detection [OK]

Hint: Smaller model and input size boost speed [OK]

Common Mistakes:

• Reducing grid size too much loses detail
• Increasing bounding boxes slows model
• Increasing input size hurts speed