Cutout and CutMix in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to apply Cutout augmentation by masking a square region in the image tensor.

Computer Vision

def cutout(image, size):
    h, w = image.shape[1], image.shape[2]
    y = torch.randint(0, h, (1,)).item()
    x = torch.randint(0, w, (1,)).item()
    y1 = max(0, y - size // 2)
    y2 = min(h, y + size // 2)
    x1 = max(0, x - size // 2)
    x2 = min(w, x + size // 2)
    image[:, y1:y2, x1:x2] = [1]
    return image

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

Aimage.mean()

B1

C0

Dtorch.rand(1)

Attempts:

3 left

💡 Hint

Common Mistakes

Using random values instead of zero for masking.

Setting the region to one which brightens the area.

Cutout masks a square region by setting pixel values to zero, effectively removing information from that area.

2fill in blank

medium

Complete the code to mix two images using CutMix by combining patches and labels with a lambda factor.

Computer Vision

def cutmix(image1, image2, label1, label2, alpha=1.0):
    lam = np.random.beta(alpha, alpha)
    h, w = image1.shape[1], image1.shape[2]
    cut_rat = np.sqrt(1. - lam)
    cut_w = int(w * cut_rat)
    cut_h = int(h * cut_rat)
    cx = np.random.randint(w)
    cy = np.random.randint(h)
    x1 = np.clip(cx - cut_w // 2, 0, w)
    y1 = np.clip(cy - cut_h // 2, 0, h)
    x2 = np.clip(cx + cut_w // 2, 0, w)
    y2 = np.clip(cy + cut_h // 2, 0, h)
    image1[:, y1:y2, x1:x2] = image2[:, y1:y2, x1:x2]
    lam = 1 - ((x2 - x1) * (y2 - y1) / (w * h))
    mixed_label = lam * label1 + [1] * label2
    return image1, mixed_label

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

A1 - lam

Blam

Clabel1

D0.5

Attempts:

3 left

💡 Hint

Common Mistakes

Using lam instead of 1 - lam for label2.

Using fixed values like 0.5 instead of calculated proportions.

The label mixing factor for label2 is the complement of lam, which represents the area ratio of the patch from image2.

3fill in blank

hard

Fix the error in the Cutout function where the masked region is incorrectly assigned.

Computer Vision

def cutout_fixed(image, size):
    h, w = image.shape[1], image.shape[2]
    y = torch.randint(0, h, (1,)).item()
    x = torch.randint(0, w, (1,)).item()
    y1 = max(0, y - size // 2)
    y2 = min(h, y + size // 2)
    x1 = max(0, x - size // 2)
    x2 = min(w, x + size // 2)
    image[:, y1:y2, x1:x2] = [1]
    return image

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

Atorch.ones_like(image[:, y1:y2, x1:x2])

Btorch.zeros_like(image[:, y1:y2, x1:x2])

Cimage[:, y1:y2, x1:x2]

Dtorch.rand_like(image[:, y1:y2, x1:x2])

Attempts:

3 left

💡 Hint

Common Mistakes

Assigning scalar zero causes broadcasting errors.

Using ones or random values changes the intended mask effect.

Using torch.zeros_like ensures the masked region is zeroed out with the correct shape and device, fixing assignment errors.

4fill in blank

hard

Fill both blanks to create a CutMix bounding box and calculate the lambda ratio correctly.

Computer Vision

def rand_bbox(size, lam):
    W = size[2]
    H = size[1]
    cut_rat = np.sqrt(1. - lam)
    cut_w = int(W * [1])
    cut_h = int(H * [2])
    cx = np.random.randint(W)
    cy = np.random.randint(H)
    bbx1 = np.clip(cx - cut_w // 2, 0, W)
    bby1 = np.clip(cy - cut_h // 2, 0, H)
    bbx2 = np.clip(cx + cut_w // 2, 0, W)
    bby2 = np.clip(cy + cut_h // 2, 0, H)
    return bbx1, bby1, bbx2, bby2

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

Acut_rat

Blam

C1 - lam

Dnp.sqrt(lam)

Attempts:

3 left

💡 Hint

Common Mistakes

Using lam or 1 - lam directly instead of sqrt(1 - lam).

Using different factors for width and height.

The width and height of the cut box are scaled by cut_rat, which is sqrt(1 - lam), to maintain the correct area ratio.

5fill in blank

hard

Fill all three blanks to implement CutMix that returns mixed images and adjusted labels.

Computer Vision

def cutmix_data(x, y, alpha=1.0):
    if alpha > 0:
        lam = np.random.beta(alpha, alpha)
    else:
        lam = 1
    batch_size = x.size()[0]
    index = torch.randperm(batch_size)
    bbx1, bby1, bbx2, bby2 = rand_bbox(x.size(), lam)
    x[:, :, bby1:bby2, bbx1:bbx2] = x[index, :, bby1:bby2, bbx1:bbx2]
    lam = 1 - ((bbx2 - bbx1) * (bby2 - bby1) / (x.size()[-1] * x.size()[-2]))
    y_a, y_b = y, y[index]
    return x, (y_a, y_b, [1]), lam, [2], [3]

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

Alam

By_a

Cy_b

Dindex

Attempts:

3 left

💡 Hint

Common Mistakes

Returning labels in wrong order.

Returning index instead of labels.

Not returning lam for label weighting.

The function returns the mixed images, a tuple of original and shuffled labels, and the lambda value for label mixing.

Practice

1. What is the main purpose of the Cutout technique in computer vision?

easy

A. To remove a patch from an image to improve model robustness

B. To combine two images by overlaying one on the other

C. To increase image resolution for better detail

D. To convert images to grayscale for simpler processing

Solution

1. Step 1: Understand Cutout's function

   Cutout removes a small patch from an image during training to force the model to learn from other parts.

2. Step 2: Compare options

   Only To remove a patch from an image to improve model robustness describes removing a patch to improve robustness. Others describe different techniques.

3. Final Answer:

   To remove a patch from an image to improve model robustness -> Option A

4. Quick Check:

   Cutout = patch removal [OK]

Hint: Cutout = cut a patch out of the image [OK]

Common Mistakes:

• Confusing Cutout with CutMix
• Thinking Cutout increases resolution
• Assuming Cutout converts image color

2. Which of the following is the correct way to mix labels in CutMix augmentation in Python using PyTorch?

easy

A. new_label = label1 * lambda + label2 * (1 - lambda)

B. new_label = label1 + label2

C. new_label = label1 - label2

D. new_label = label1 / label2

Solution

1. Step 1: Recall CutMix formula

   CutMix creates a new label by mixing two labels weighted by lambda and (1 - lambda).

2. Step 2: Match formula to options

   new_label = label1 * lambda + label2 * (1 - lambda) correctly shows weighted sum of two labels. Others are incorrect operations.

3. Final Answer:

   new_label = label1 * lambda + label2 * (1 - lambda) -> Option A

4. Quick Check:

   CutMix = weighted sum [OK]

Hint: CutMix blends labels weighted by lambda [OK]

Common Mistakes:

• Using addition without weights
• Subtracting or dividing labels incorrectly
• Confusing CutMix with Cutout

3. Given the following code snippet applying Cutout, what will be the shape of the output image tensor?

import torch
import torchvision.transforms as T

cutout = T.RandomErasing(p=1.0, scale=(0.1, 0.1))
image = torch.randn(3, 224, 224)
output = cutout(image)
print(output.shape)

medium

A. torch.Size([3, 112, 112])

B. torch.Size([1, 224, 224])

C. torch.Size([224, 224, 3])

D. torch.Size([3, 224, 224])

Solution

1. Step 1: Understand RandomErasing effect

   RandomErasing (Cutout) masks part of the image but does not change its shape.

2. Step 2: Check input and output shapes

   Input is (3, 224, 224), output remains same shape after Cutout.

3. Final Answer:

   torch.Size([3, 224, 224]) -> Option D

4. Quick Check:

   Cutout keeps shape same [OK]

Hint: Cutout masks but keeps image size [OK]

Common Mistakes:

• Thinking Cutout changes image dimensions
• Confusing channel order with shape
• Assuming output is batch dimension added

4. The following code attempts to apply CutMix but causes an error. What is the main issue?

def cutmix(image1, image2, lam):
    bbx1, bby1, bbx2, bby2 = rand_bbox(image1.size(), lam)
    image1[:, bbx1:bbx2, bby1:bby2] = image2[:, bbx1:bbx2, bby1:bby2]
    return image1

# image1 and image2 are tensors of shape (3, 224, 448)
# lam is a float between 0 and 1

medium

A. rand_bbox returns coordinates in (x, y) but slicing expects (height, width)

B. rand_bbox expects size as tuple (H, W) instead of tensor.size() (C, H, W)

C. The function modifies image1 in-place which is not allowed

D. The function does not return the mixed label

Solution

1. Step 1: Analyze rand_bbox input and slicing

   rand_bbox expects size as (height, width), but image1.size() returns (channels, height, width).

2. Step 2: Identify mismatch in size argument

   Passing image1.size() (C, H, W) instead of (H, W) causes rand_bbox to compute wrong coordinates, leading to slicing errors.

3. Final Answer:

   rand_bbox expects size as tuple (H, W) instead of tensor.size() (C, H, W) -> Option B

4. Quick Check:

   Size argument mismatch = error [OK]

Hint: Pass (H, W) size to rand_bbox, not (C, H, W) [OK]

Common Mistakes:

• Ignoring coordinate order difference
• Assuming in-place modification causes error
• Forgetting to return mixed label

5. You want to improve your image classifier's robustness by combining Cutout and CutMix. Which approach correctly applies both augmentations during training?

hard

A. Apply Cutout to each image separately, then combine them with CutMix

B. Apply Cutout only after training with CutMix is complete

C. Apply CutMix first to combine images, then apply Cutout to mask patches on the mixed image

D. Apply CutMix only on validation data and Cutout only on training data

Solution

1. Step 1: Understand augmentation order

   CutMix combines two images, then Cutout can mask parts of the combined image to increase robustness.

2. Step 2: Evaluate options for correct sequence

   Apply CutMix first to combine images, then apply Cutout to mask patches on the mixed image applies CutMix first, then Cutout, which is the correct order to augment the mixed image effectively.

3. Final Answer:

   Apply CutMix first to combine images, then apply Cutout to mask patches on the mixed image -> Option C

4. Quick Check:

   CutMix then Cutout = best practice [OK]

Hint: Mix images first, then mask patches [OK]

Common Mistakes:

• Applying Cutout before mixing images
• Using augmentations only on validation data
• Applying augmentations after training