YOLO concept in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does YOLO stand for in object detection?

YOLO stands for "You Only Look Once". It means the model detects objects in an image in a single pass, making it very fast.

beginner

How does YOLO divide an image to detect objects?

YOLO splits the image into a grid of cells. Each cell predicts bounding boxes and class probabilities for objects whose centers fall inside it.

beginner

What are bounding boxes in YOLO?

Bounding boxes are rectangles predicted by YOLO that show where an object is located in the image. Each box has coordinates and a confidence score.

intermediate

Why is YOLO considered fast compared to other object detectors?

YOLO processes the whole image in one pass through the neural network, unlike other methods that look at many parts separately. This makes it much faster.

intermediate

What is the role of confidence score in YOLO predictions?

The confidence score tells how sure the model is that a bounding box contains an object and how accurate the box is. It helps filter out weak detections.

What is the main advantage of YOLO over traditional object detection methods?

A It uses multiple passes for higher accuracy

B It detects objects in a single pass, making it faster

C It only detects one object per image

D It requires no training data

YOLO processes the entire image once, which makes it much faster than methods that use multiple passes.

In YOLO, what does each grid cell predict?

A Only the class of objects

B The whole image label

C Image brightness

D Bounding boxes and class probabilities

Each grid cell predicts bounding boxes and the probabilities of different classes for objects inside it.

What does a bounding box in YOLO represent?

A A rectangle locating an object

B A pixel intensity value

C A color filter

D A data augmentation method

Bounding boxes are rectangles that show where objects are located in the image.

Why is the confidence score important in YOLO?

A It decides the color of bounding boxes

B It controls the image size

C It measures the model's certainty about the object and box accuracy

D It sets the learning rate

The confidence score helps decide which bounding boxes are likely to contain real objects.

Which of these is NOT true about YOLO?

A It requires multiple passes over the image

B It predicts multiple bounding boxes per grid cell

C It divides the image into a grid

D It outputs class probabilities for each box

YOLO only needs one pass over the image to make predictions.

Explain how YOLO detects objects in an image using a grid system.

Think about how the image is split and what each part predicts.

Describe why YOLO is faster than other object detection methods and how this affects its use cases.

Consider the difference between looking once versus multiple times.

Practice

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

easy

A. It uses a very slow but highly accurate method.

B. It detects multiple objects in an image quickly in a single pass.

C. It only detects one object per image.

D. It requires multiple passes over the image to detect objects.

Solution

1. Step 1: Understand YOLO's detection method

   YOLO processes the entire image once to detect all objects, unlike methods that scan multiple times.

2. Step 2: Compare options with YOLO's feature

   It detects multiple objects in an image quickly in a single pass correctly states YOLO's speed and single-pass detection. Other options contradict this.

3. Final Answer:

   It detects multiple objects in an image quickly in a single pass. -> Option B

4. Quick Check:

   YOLO speed = single pass detection [OK]

Hint: YOLO means one pass for all objects [OK]

Common Mistakes:

• Thinking YOLO scans image multiple times
• Believing YOLO detects only one object
• Confusing YOLO with slow detection methods

2. Which of the following is the correct way to load a pretrained YOLO model in PyTorch?

easy

A. model = torch.hub.download('yolov5s')

B. model = torch.load('yolov5s.pt')

C. model = torch.yolo.load('yolov5s')

D. model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)

Solution

1. Step 1: Recall PyTorch hub usage for YOLO

   PyTorch hub uses torch.hub.load with repo and model name to load pretrained models.

2. Step 2: Check each option

   model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True) uses correct torch.hub.load syntax with pretrained=True. model = torch.load('yolov5s.pt') loads a file but not via hub. model = torch.yolo.load('yolov5s') and D use invalid methods.

3. Final Answer:

   model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True) -> Option D

4. Quick Check:

   PyTorch hub load syntax = model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True) [OK]

Hint: Use torch.hub.load with repo and model name [OK]

Common Mistakes:

• Using torch.load without specifying hub
• Trying non-existent torch.yolo module
• Confusing download with load

3. Given this PyTorch code snippet using YOLO model:

import torch
model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)
img = torch.zeros((1, 3, 640, 640))
pred = model(img)
print(len(pred.xyxy[0]))

What does the printed number represent?

medium

A. The number of image channels

B. The batch size of the input tensor

C. The number of detected objects in the image

D. The number of model layers

Solution

1. Step 1: Understand pred.xyxy output

   pred.xyxy[0] contains bounding boxes for detected objects in the first image of the batch.

2. Step 2: len(pred.xyxy[0]) counts detected boxes

   Counting these boxes gives the number of objects detected in the image.

3. Final Answer:

   The number of detected objects in the image -> Option C

4. Quick Check:

   Length of pred.xyxy[0] = detected objects count [OK]

Hint: Length of pred.xyxy[0] = detected objects [OK]

Common Mistakes:

• Confusing output length with image channels
• Thinking it shows batch size
• Assuming it counts model layers

4. You run YOLO detection code but get an error: AttributeError: 'NoneType' object has no attribute 'xyxy'. What is the most likely cause?

medium

A. The model was not loaded correctly, so prediction returned None.

B. The input image tensor has wrong shape.

C. YOLO does not support batch size 1.

D. The torch library is outdated.

Solution

1. Step 1: Analyze the error message

   'NoneType' means prediction output is None, so accessing .xyxy fails.

2. Step 2: Identify cause of None output

   If model loading fails or is incorrect, model(img) returns None, causing this error.

3. Final Answer:

   The model was not loaded correctly, so prediction returned None. -> Option A

4. Quick Check:

   None output means model load failed [OK]

Hint: None output means model load failed [OK]

Common Mistakes:

• Blaming input shape without checking model load
• Assuming batch size 1 is unsupported
• Ignoring error message details

5. You want to detect only 'person' objects using a pretrained YOLO model in PyTorch. Which approach correctly filters the detections?

hard

A. Filter pred.xyxy[0] by checking if pred.names[class_id] == 'person' for each detected box.

B. Set model to detect only 'person' by passing classes=['person'] when loading.

C. Use a separate model trained only on persons instead of YOLO.

D. Manually crop image to only person areas before detection.

Solution

1. Step 1: Understand YOLO output structure

   YOLO outputs boxes with class IDs; pred.names maps IDs to labels like 'person'.

2. Step 2: Filter detections by class label

   Filtering pred.xyxy[0] by checking if class label equals 'person' keeps only person detections.

3. Final Answer:

   Filter pred.xyxy[0] by checking if pred.names[class_id] == 'person' for each detected box. -> Option A

4. Quick Check:

   Filter detections by class label = Filter pred.xyxy[0] by checking if pred.names[class_id] == 'person' for each detected box. [OK]

Hint: Filter detections by class label after prediction [OK]

Common Mistakes:

• Trying to limit classes at model load (not supported directly)
• Using separate model unnecessarily
• Cropping image instead of filtering results