Bounding box handling in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a bounding box in object detection?

A bounding box is a rectangle that tightly encloses an object in an image, defined by coordinates usually as (x_min, y_min, x_max, y_max). It helps locate and identify objects.

beginner

How do you convert bounding boxes from (x, y, width, height) format to (x_min, y_min, x_max, y_max)?

You keep x_min = x, y_min = y, then calculate x_max = x + width - 1 and y_max = y + height - 1.

intermediate

What is Intersection over Union (IoU) in bounding box handling?

IoU measures how much two bounding boxes overlap. It is the area of overlap divided by the area of union of the two boxes. It helps evaluate detection accuracy.

intermediate

Why is Non-Maximum Suppression (NMS) used in bounding box handling?

NMS removes duplicate bounding boxes that detect the same object by keeping only the box with the highest confidence score and discarding others with high overlap.

beginner

How can bounding boxes be normalized for neural network input?

Bounding box coordinates can be divided by the image width and height to scale them between 0 and 1, making them independent of image size.

What does the bounding box format (x_min, y_min, x_max, y_max) represent?

A Center coordinates only

B Center coordinates and width/height

C Top-left and bottom-right corners of the box

D Width and height only

The format (x_min, y_min, x_max, y_max) defines the top-left and bottom-right corners of the bounding box.

What is the main purpose of Non-Maximum Suppression (NMS)?

A To remove overlapping boxes for the same object

B To increase the number of bounding boxes

C To resize images

D To normalize bounding box coordinates

NMS removes overlapping bounding boxes that detect the same object, keeping only the best one.

How is Intersection over Union (IoU) calculated?

A Difference between box widths

B Area of overlap divided by area of union

C Sum of areas of two boxes

D Distance between box centers

IoU is the ratio of the overlapping area to the combined area of two bounding boxes.

Why normalize bounding box coordinates before feeding to a model?

A To convert coordinates to pixels

B To remove bounding boxes

C To increase coordinate values

D To make coordinates relative to image size

Normalization scales coordinates between 0 and 1, making them independent of image size.

Which PyTorch tensor shape is typical for a batch of bounding boxes?

A [batch_size, num_boxes, 4]

B [4, num_boxes]

C [num_boxes, batch_size]

D [batch_size, 4]

Bounding boxes are usually stored as [batch_size, number_of_boxes, 4_coordinates].

Explain how Non-Maximum Suppression (NMS) works and why it is important in bounding box handling.

Think about how multiple boxes might detect the same object and how to keep only one.

Describe the process to calculate Intersection over Union (IoU) between two bounding boxes.

Imagine two rectangles overlapping and how much they share.

Practice

1. What do the four numbers in a bounding box usually represent in PyTorch object detection tasks?

easy

A. Width, height, depth, and color

B. Center x, center y, width, height

C. Top-left corner x and y, width, height

D. Left, top, right, bottom coordinates of the box

Solution

1. Step 1: Understand bounding box format

   Bounding boxes in PyTorch detection models are often represented by four numbers indicating the edges: left (x_min), top (y_min), right (x_max), and bottom (y_max).

2. Step 2: Compare options with standard format

   Left, top, right, bottom coordinates of the box matches this format exactly, while others describe different formats or unrelated values.

3. Final Answer:

   Left, top, right, bottom coordinates of the box -> Option D

4. Quick Check:

   Bounding box = left, top, right, bottom [OK]

Hint: Remember bounding box edges are left, top, right, bottom [OK]

Common Mistakes:

• Confusing center coordinates with edges
• Mixing width and height with coordinates
• Assuming depth or color are part of bounding box

2. Which PyTorch tensor shape correctly represents a batch of 5 bounding boxes, each with 4 coordinates?

easy

A. torch.Size([5, 4])

B. torch.Size([4, 5])

C. torch.Size([5])

D. torch.Size([4])

Solution

1. Step 1: Identify bounding box tensor shape

   Each bounding box has 4 coordinates. For 5 boxes, the tensor shape should be (5, 4), meaning 5 rows (boxes) and 4 columns (coordinates).

2. Step 2: Match options with correct shape

   torch.Size([5, 4]) matches (5, 4). torch.Size([4, 5]) reverses dimensions, and C and D are one-dimensional, which is incorrect.

3. Final Answer:

   torch.Size([5, 4]) -> Option A

4. Quick Check:

   Batch size 5 and 4 coords = (5, 4) [OK]

Hint: Batch size first, coordinates second in tensor shape [OK]

Common Mistakes:

• Swapping batch and coordinate dimensions
• Using 1D tensor for multiple boxes
• Confusing number of boxes with number of coordinates

3. Given the following PyTorch code, what is the output?

import torch
boxes = torch.tensor([[1, 2, 4, 6], [0, 0, 3, 3]])
widths = boxes[:, 2] - boxes[:, 0]
heights = boxes[:, 3] - boxes[:, 1]
areas = widths * heights
print(areas.tolist())

medium

A. [10, 9]

B. [15, 9]

C. [12, 9]

D. [12, 6]

Solution

1. Step 1: Calculate widths and heights

   For box 1: width = 4 - 1 = 3, height = 6 - 2 = 4. For box 2: width = 3 - 0 = 3, height = 3 - 0 = 3.

2. Step 2: Calculate areas

   Area box 1 = 3 * 4 = 12, area box 2 = 3 * 3 = 9.

3. Final Answer:

   [12, 9] -> Option C

4. Quick Check:

   Area = width * height = [12, 9] [OK]

Hint: Area = (right-left) * (bottom-top) for each box [OK]

Common Mistakes:

• Subtracting coordinates in wrong order
• Mixing width with height values
• Forgetting to multiply widths and heights

4. Identify the error in this PyTorch code snippet for checking if points lie inside bounding boxes:

import torch
boxes = torch.tensor([1, 1, 5, 5])
points = torch.tensor([[3, 3], [6, 6]])
inside = (points[:, 0] >= boxes[:, 0]) & (points[:, 0] <= boxes[:, 2]) & (points[:, 1] >= boxes[:, 1]) & (points[:, 1] <= boxes[:, 3])
print(inside)

medium

A. The comparison between points and boxes tensors will fail due to shape mismatch

B. The logical AND operator '&' cannot be used with tensors

C. The code should use .all() to combine conditions

D. Points coordinates are reversed in the comparisons

Solution

1. Step 1: Check tensor shapes for broadcasting

   Boxes shape is (4,), points shape is (2,2). Comparing points[:, 0] (shape 2) with boxes[:, 0] causes shape mismatch as boxes is 1D.

2. Step 2: Understand broadcasting rules

   Direct element-wise comparison fails because points and boxes dimensions don't align for broadcasting in this code.

3. Final Answer:

   The comparison between points and boxes tensors will fail due to shape mismatch -> Option A

4. Quick Check:

   Shape mismatch causes error in element-wise comparison [OK]

Hint: Check tensor shapes before element-wise comparisons [OK]

Common Mistakes:

• Assuming PyTorch auto-broadcasts all shapes
• Using bitwise operators incorrectly
• Mixing coordinate order in comparisons

5. You want to convert bounding boxes from (left, top, right, bottom) format to (center_x, center_y, width, height) in PyTorch. Which code snippet correctly performs this conversion for a tensor boxes of shape (N, 4)?

hard

A. centers = boxes[:, :2] - boxes[:, 2:]
sizes = boxes[:, 2:] + boxes[:, :2]
converted = torch.cat([centers, sizes], dim=1)

B. centers = (boxes[:, :2] + boxes[:, 2:]) / 2
sizes = boxes[:, 2:] - boxes[:, :2]
converted = torch.cat([centers, sizes], dim=1)

C. centers = boxes[:, 2:] - boxes[:, :2]
sizes = (boxes[:, :2] + boxes[:, 2:]) / 2
converted = torch.cat([sizes, centers], dim=1)

D. centers = boxes[:, :2] * boxes[:, 2:]
sizes = boxes[:, 2:] / boxes[:, :2]
converted = torch.cat([centers, sizes], dim=1)

Solution

1. Step 1: Calculate center coordinates

   Center x and y are the average of left and right, top and bottom: (left + right)/2, (top + bottom)/2, which is (boxes[:, :2] + boxes[:, 2:]) / 2.

2. Step 2: Calculate width and height

   Width and height are right - left and bottom - top: boxes[:, 2:] - boxes[:, :2].

3. Step 3: Concatenate centers and sizes

   Combine centers and sizes along dimension 1 to get (center_x, center_y, width, height).

4. Final Answer:

   centers = (boxes[:, :2] + boxes[:, 2:]) / 2 sizes = boxes[:, 2:] - boxes[:, :2] converted = torch.cat([centers, sizes], dim=1) -> Option B

5. Quick Check:

   Center = avg edges, size = difference edges [OK]

Hint: Center = average edges; size = difference edges [OK]

Common Mistakes:

• Swapping center and size calculations
• Using addition instead of subtraction for sizes
• Concatenating in wrong order