MixUp strategy in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create mixed inputs using MixUp.

Computer Vision

mixed_x = lambda x1, x2, lam: lam * x1 + [1] * x2

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

Alam + 1

Blam - 1

C1 - lam

Dlam

Attempts:

3 left

💡 Hint

Common Mistakes

Using lam instead of 1 - lam for the second input weight.

Adding lambda values instead of subtracting.

Using incorrect arithmetic operators.

MixUp combines two inputs weighted by lambda and (1 - lambda).

2fill in blank

medium

Complete the code to mix labels in MixUp.

Computer Vision

mixed_y = lam * y1 + [1] * y2

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

A1 - lam

Blam + 1

Clam

Dlam * 2

Attempts:

3 left

💡 Hint

Common Mistakes

Using lam for both labels.

Multiplying lam by 2 incorrectly.

Adding lam and 1 instead of subtracting.

Labels are mixed with the same weights as inputs: lam and 1 - lam.

3fill in blank

hard

Fix the error in the MixUp lambda sampling code.

Computer Vision

lam = np.random.beta([1], [1])

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

A1.0

B0.5

C0

D2.0

Attempts:

3 left

💡 Hint

Common Mistakes

Using 1.0 which results in uniform distribution.

Using 0 which is invalid for Beta distribution.

Using 2.0 which biases mixing too much.

The MixUp lambda is sampled from a Beta distribution with alpha=beta=0.5 for stronger mixing.

4fill in blank

hard

Fill both blanks to create a MixUp batch of inputs and labels.

Computer Vision

mixed_x = lam * x + [1] * x[[2]]

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

A1 - lam

Blam

Cperm

Dx

Attempts:

3 left

💡 Hint

Common Mistakes

Using lam instead of 1 - lam for the second weight.

Using x instead of permuted indices for the second input.

MixUp uses (1 - lam) for the second input weight and permuted indices to shuffle the batch.

5fill in blank

hard

Fill all three blanks to complete the MixUp label mixing code.

Computer Vision

mixed_y = lam * y + [1] * y[[2]]  # y shape: [3]

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

A1 - lam

Bperm

C(batch_size, num_classes)

D(num_classes, batch_size)

Attempts:

3 left

💡 Hint

Common Mistakes

Using lam instead of 1 - lam.

Using wrong shape for labels.

Not using permuted indices for label mixing.

Labels are mixed with 1 - lam and permuted indices; labels usually have shape (batch_size, num_classes).