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.