Python CV ecosystem (OpenCV, PIL, torchvision) in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

What is the output of this OpenCV image shape code?

Given an image loaded with OpenCV, what will be the output of the shape attribute?

Computer Vision

import cv2
img = cv2.imread('sample.jpg')
print(img.shape)

A (height, width, channels) tuple representing image dimensions

B (width, height, channels) tuple representing image dimensions

C A single integer representing total pixels

D Raises an error because shape attribute does not exist

💡 Hint

OpenCV loads images as NumPy arrays with shape (rows, columns, channels).

OpenCV loads images as NumPy arrays with shape (height, width, channels). The shape attribute returns a tuple in this order.

❓ Model Choice

intermediate

Which torchvision model is best for image classification on ImageNet?

You want to use a pretrained model from torchvision for classifying images into 1000 classes. Which model is designed specifically for this?

A torchvision.models.segmentation.fcn_resnet50(pretrained=True)

B torchvision.models.resnet50(pretrained=True)

C torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)

D torchvision.models.video.r3d_18(pretrained=True)

💡 Hint

Image classification models output class probabilities for fixed classes.

ResNet50 is a standard image classification model pretrained on ImageNet with 1000 classes. The others are for segmentation, detection, or video tasks.

❓ Metrics

advanced

How to correctly compute accuracy for a torchvision classification model?

You have model outputs as logits and true labels as integers. Which code snippet correctly computes accuracy?

A

preds = outputs.argmax(dim=1)
accuracy = (preds == labels).sum().item()

B

preds = outputs.max(dim=0)
accuracy = (preds == labels).float().mean().item()

C

preds = outputs.argmax(dim=1)
accuracy = (preds == labels).float().mean().item()

D

preds = outputs.argmax(dim=1)
accuracy = (preds == labels).float().sum().item() / len(labels)

💡 Hint

Accuracy is the fraction of correct predictions over total samples.

Option C correctly finds predicted classes by argmax over dimension 1, compares with labels, converts to float, averages, and extracts scalar.

🔧 Debug

advanced

Why does this PIL image conversion code raise an error?

Code snippet: from PIL import Image img = Image.open('photo.png') img = img.convert('HSV')

Computer Vision

from PIL import Image
img = Image.open('photo.png')
img = img.convert('HSV')

A No error, image converts successfully

B FileNotFoundError because 'photo.png' does not exist

C ValueError because 'HSV' is not a supported mode in PIL

D TypeError because convert expects an integer

💡 Hint

PIL supports specific modes like 'RGB', 'L', 'RGBA'.

The convert method accepts 'HSV' as a valid mode in PIL, so no error is raised.

🧠 Conceptual

expert

What is the main difference between OpenCV and PIL in image processing?

Choose the statement that best describes a key difference between OpenCV and PIL libraries.

A PIL is designed for real-time computer vision, OpenCV is not

B PIL supports video processing, OpenCV does not

C OpenCV cannot read PNG images, PIL can

D OpenCV uses BGR color order by default, PIL uses RGB

💡 Hint

Think about default color channel order in each library.

OpenCV loads images in BGR order by default, while PIL uses RGB order. This often causes color confusion if not handled.

Practice

1. Which Python library is best known for fast image and video processing tasks?

easy

A. PIL (Pillow)

B. OpenCV

C. torchvision

D. matplotlib

Solution

1. Step 1: Understand library purposes

   OpenCV is designed for fast image and video processing, widely used in computer vision.

2. Step 2: Compare with other libraries

   PIL is mainly for image editing, torchvision is for ML image datasets, matplotlib is for plotting.

3. Final Answer:

   OpenCV -> Option B

4. Quick Check:

   Fast image/video processing = OpenCV [OK]

Hint: OpenCV = fast image/video tasks, PIL = editing, torchvision = ML prep [OK]

Common Mistakes:

• Confusing PIL as the fastest for video processing
• Thinking torchvision handles video processing
• Assuming matplotlib is for image processing

2. Which of the following is the correct way to read an image using OpenCV in Python?

easy

A. img = cv2.imread('image.jpg')

B. img = Image.open('image.jpg')

C. img = torchvision.io.read_image('image.jpg')

D. img = plt.imread('image.jpg')

Solution

1. Step 1: Identify OpenCV image reading syntax

   OpenCV uses cv2.imread() to load images from files.

2. Step 2: Differentiate from other libraries

   PIL uses Image.open(), torchvision uses torchvision.io.read_image(), matplotlib uses plt.imread().

3. Final Answer:

   img = cv2.imread('image.jpg') -> Option A

4. Quick Check:

   OpenCV image read = cv2.imread() [OK]

Hint: OpenCV reads images with cv2.imread() [OK]

Common Mistakes:

• Using Image.open() which is from PIL, not OpenCV
• Using plt.imread() which is for plotting, not OpenCV
• Confusing torchvision's read_image with OpenCV

3. What will be the shape and color format of the image loaded by this OpenCV code?

import cv2
img = cv2.imread('image.jpg')
print(img.shape)

medium

A. (height, width, 3) with RGB color order

B. (width, height, 3) with BGR color order

C. (width, height, 3) with RGB color order

D. (height, width, 3) with BGR color order

Solution

1. Step 1: Understand OpenCV image shape

   OpenCV loads images as NumPy arrays with shape (height, width, channels).

2. Step 2: Know OpenCV color format

   OpenCV uses BGR color order by default, not RGB.

3. Final Answer:

   (height, width, 3) with BGR color order -> Option D

4. Quick Check:

   OpenCV shape = (H, W, 3), color = BGR [OK]

Hint: OpenCV images: shape (H,W,3), color BGR [OK]

Common Mistakes:

• Assuming RGB color order instead of BGR
• Swapping width and height in shape
• Thinking OpenCV loads grayscale by default

4. This code tries to convert a PIL image to a NumPy array for OpenCV processing but causes an error:

from PIL import Image
import numpy as np
img_pil = Image.open('image.jpg')
img_cv = np.array(img_pil)

What is the likely cause and fix?

medium

A. PIL image must be converted to grayscale first

B. Color channels are in wrong order; convert RGB to BGR after np.array()

C. Use img_pil.convert('RGB') before np.array() to ensure 3 channels

D. No error; code works fine as is

Solution

1. Step 1: Identify PIL image mode issue

   PIL images may not be in RGB mode by default; could be 'P' or 'L' mode causing np.array to have unexpected shape.

2. Step 2: Fix by converting to RGB mode

   Use img_pil.convert('RGB') to ensure 3 color channels before converting to NumPy array.

3. Final Answer:

   Use img_pil.convert('RGB') before np.array() to ensure 3 channels -> Option C

4. Quick Check:

   PIL to NumPy needs RGB mode [OK]

Hint: Convert PIL image to RGB before np.array() [OK]

Common Mistakes:

• Assuming np.array always works without convert()
• Ignoring color channel order differences
• Trying to convert to grayscale unnecessarily

5. You want to prepare an image for a PyTorch model using torchvision transforms. Which sequence correctly converts a PIL image to a tensor normalized for pretrained models?

hard

A. Use torchvision.transforms.ToTensor() then torchvision.transforms.Normalize(mean, std)

B. Use cv2.imread() then convert to tensor manually

C. Use PIL.Image.open() then convert to NumPy array and normalize manually

D. Use torchvision.transforms.Normalize() only on PIL image

Solution

1. Step 1: Understand torchvision transform pipeline

   To prepare images for PyTorch models, convert PIL image to tensor with ToTensor(), which scales pixels to [0,1].

2. Step 2: Normalize tensor with mean and std

   Use Normalize() with pretrained model's mean and std to standardize input.

3. Final Answer:

   Use torchvision.transforms.ToTensor() then torchvision.transforms.Normalize(mean, std) -> Option A

4. Quick Check:

   ToTensor + Normalize = correct PyTorch prep [OK]

Hint: Use ToTensor() then Normalize() for PyTorch image prep [OK]

Common Mistakes:

• Trying to normalize PIL images directly
• Using OpenCV images without conversion
• Skipping normalization step