Non-maximum suppression in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of PyTorch NMS with overlapping boxes

Given the following bounding boxes and scores, what indices does PyTorch's non_max_suppression (NMS) return?

PyTorch

import torch
from torchvision.ops import nms

boxes = torch.tensor([[10, 10, 20, 20], [11, 11, 21, 21], [30, 30, 40, 40]], dtype=torch.float32)
scores = torch.tensor([0.9, 0.8, 0.7])
iou_threshold = 0.5

keep_indices = nms(boxes, scores, iou_threshold)
print(keep_indices.tolist())

A [0, 2]

B [1, 2]

C [0, 1, 2]

D [2]

💡 Hint

NMS keeps the highest scoring box and removes boxes with IoU above threshold.

The first two boxes overlap with IoU > 0.5, so only the highest score box (index 0) is kept. The third box is far and kept as well.

🧠 Conceptual

intermediate

Purpose of Non-Maximum Suppression in Object Detection

What is the main purpose of applying Non-Maximum Suppression (NMS) in object detection pipelines?

A To remove duplicate detections of the same object by keeping only the highest scoring bounding box.

B To increase the number of detected objects by adding more bounding boxes.

C To randomly select bounding boxes to reduce computation.

D To resize bounding boxes to a fixed size.

💡 Hint

Think about why multiple boxes might appear around the same object.

NMS removes overlapping boxes that likely represent the same object, keeping only the one with the highest confidence score.

❓ Hyperparameter

advanced

Effect of IoU Threshold on NMS Output

If you increase the IoU threshold parameter in NMS from 0.3 to 0.7, what is the expected effect on the number of bounding boxes kept?

A All boxes will be removed.

B Fewer boxes will be kept because the suppression is more strict.

C The number of boxes kept will not change.

D More boxes will be kept because the suppression is less strict.

💡 Hint

Higher IoU threshold means boxes need to overlap more to be suppressed.

Increasing the IoU threshold means boxes must overlap more to be suppressed, so fewer boxes are removed and more are kept.

🔧 Debug

advanced

Identify the error in this NMS usage code

What error will this PyTorch code raise when running NMS?

PyTorch

import torch
from torchvision.ops import nms

boxes = torch.tensor([[10, 10, 20, 20], [15, 15, 25, 25]])
scores = [0.9, 0.8]
iou_threshold = 0.5

keep = nms(boxes, scores, iou_threshold)
print(keep)

A No error, code runs fine.

B ValueError because boxes have wrong shape.

C TypeError because scores is a list, not a tensor.

D RuntimeError because iou_threshold is not a tensor.

💡 Hint

Check the data types required by torchvision.ops.nms.

The scores argument must be a torch tensor, but here it is a Python list, causing a TypeError.

❓ Model Choice

expert

Choosing NMS variant for crowded scenes

In a crowded scene with many overlapping objects, which NMS variant is best to reduce missed detections while controlling duplicates?

A Random NMS, to randomly keep boxes and reduce duplicates.

B Soft-NMS, because it reduces scores of overlapping boxes instead of removing them outright.

C No NMS, to keep all detections regardless of overlap.

D Standard NMS, because it strictly removes all overlapping boxes above threshold.

💡 Hint

Consider methods that soften suppression to keep more true positives.

Soft-NMS reduces scores of overlapping boxes instead of removing them, which helps keep true positives in crowded scenes.

Practice

1. What is the main purpose of Non-maximum Suppression (NMS) in object detection using PyTorch?

easy

A. To increase the number of detected boxes

B. To resize images before detection

C. To randomly select boxes for training

D. To remove overlapping bounding boxes and keep only the best ones

Solution

1. Step 1: Understand the role of NMS

   Non-maximum suppression is used to filter out overlapping bounding boxes that represent the same object.

2. Step 2: Identify the goal of NMS

   It keeps only the bounding box with the highest confidence score among overlapping boxes to avoid duplicate detections.

3. Final Answer:

   To remove overlapping bounding boxes and keep only the best ones -> Option D

4. Quick Check:

   NMS purpose = remove overlaps, keep best [OK]

Hint: NMS filters duplicates, keeping only top scoring boxes [OK]

Common Mistakes:

• Thinking NMS increases detected boxes
• Confusing NMS with image resizing
• Assuming NMS randomly selects boxes

2. Which PyTorch function is commonly used to perform Non-maximum Suppression on bounding boxes and scores?

easy

A. torch.sort

B. torch.max

C. torch.ops.torchvision.nms

D. torch.argmax

Solution

1. Step 1: Identify the PyTorch NMS function

   PyTorch provides a dedicated function called torch.ops.torchvision.nms to perform Non-maximum Suppression.

2. Step 2: Differentiate from other functions

   torch.max, torch.sort, and torch.argmax do not perform NMS; they serve different purposes like finding max values or sorting tensors.

3. Final Answer:

   torch.ops.torchvision.nms -> Option C

4. Quick Check:

   PyTorch NMS function = torch.ops.torchvision.nms [OK]

Hint: Use torch.ops.torchvision.nms for Non-maximum Suppression in PyTorch [OK]

Common Mistakes:

• Using torch.max instead of torch.ops.torchvision.nms
• Confusing sorting functions with NMS
• Trying torch.argmax for NMS

3. Given the following PyTorch code snippet, what will be the output tensor of indices after applying NMS?

import torch
boxes = torch.tensor([[10, 10, 20, 20], [11, 11, 21, 21], [30, 30, 40, 40]], dtype=torch.float)
scores = torch.tensor([0.9, 0.8, 0.7])
iou_threshold = 0.5
indices = torch.ops.torchvision.nms(boxes, scores, iou_threshold)
print(indices.tolist())

medium

A. [0, 2]

B. [1, 2]

C. [0, 1, 2]

D. [2]

Solution

1. Step 1: Analyze box overlaps and scores

   Boxes 0 and 1 overlap with IoU > 0.5, box 2 is separate. Box 0 has higher score (0.9) than box 1 (0.8).

2. Step 2: Apply NMS logic

   NMS keeps box 0, removes box 1 due to overlap and lower score, and keeps box 2 as it does not overlap.

3. Final Answer:

   [0, 2] -> Option A

4. Quick Check:

   Keep highest score boxes without high overlap = [0, 2] [OK]

Hint: Keep highest score boxes, remove overlapping lower scores [OK]

Common Mistakes:

• Keeping all boxes ignoring overlap
• Removing box 0 instead of box 1
• Keeping only one box

4. Identify the error in this PyTorch NMS usage and select the correct fix:

import torch
boxes = torch.tensor([[0, 0, 10, 10], [1, 1, 11, 11]], dtype=torch.float)
scores = torch.tensor([0.5, 0.6])
iou_threshold = 0.3
indices = torch.nms(boxes, scores, iou_threshold)
print(indices)

medium

A. Set iou_threshold to 1.0

B. Use torch.ops.torchvision.nms instead of torch.nms

C. Change boxes dtype to int

D. Sort scores before calling nms

Solution

1. Step 1: Check function availability

   torch.nms is not a direct PyTorch function; NMS is accessed via torchvision ops as torch.ops.torchvision.nms.

2. Step 2: Correct function call

   Replacing torch.nms with torch.ops.torchvision.nms fixes the error and runs NMS correctly.

3. Final Answer:

   Use torch.ops.torchvision.nms instead of torch.nms -> Option B

4. Quick Check:

   Correct NMS call = torch.ops.torchvision.nms [OK]

Hint: Use torchvision's nms via torch.ops.torchvision.nms [OK]

Common Mistakes:

• Calling torch.nms directly
• Changing box dtype unnecessarily
• Adjusting IoU threshold without fixing function

5. You have detected multiple overlapping boxes with scores: [0.95, 0.9, 0.85, 0.6]. If you apply Non-maximum Suppression with a very low IoU threshold (e.g., 0.1), what is the expected effect on the number of boxes kept?

hard

A. Most boxes will be removed because even slight overlaps are suppressed

B. All boxes will be kept because the threshold is low

C. Only the box with the lowest score will be kept

D. Boxes will be randomly removed regardless of overlap

Solution

1. Step 1: Understand IoU threshold meaning

   A low IoU threshold means boxes with even small overlaps are considered duplicates and suppressed.

2. Step 2: Predict effect on boxes

   Because boxes overlap slightly, most will be removed except the highest scoring box, reducing the number kept.

3. Final Answer:

   Most boxes will be removed because even slight overlaps are suppressed -> Option A

4. Quick Check:

   Low IoU threshold = strict filtering = fewer boxes [OK]

Hint: Lower IoU threshold means stricter overlap removal [OK]

Common Mistakes:

• Thinking low threshold keeps more boxes
• Assuming random removal
• Believing lowest score box is kept