Non-maximum suppression in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the PyTorch function for non-maximum suppression.

PyTorch

from torchvision.ops import [1]

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

Arelu

Bnms

Csoftmax

Ddropout

Attempts:

3 left

💡 Hint

Common Mistakes

Importing unrelated functions like relu or softmax.

Trying to import from torch.nn instead of torchvision.ops.

The function for non-maximum suppression in PyTorch is called 'nms' and is imported from torchvision.ops.

2fill in blank

medium

Complete the code to call the non-maximum suppression function with boxes, scores, and threshold.

PyTorch

keep_indices = nms(boxes, scores, [1])

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

A-0.5

B1.5

C0.5

D2.0

Attempts:

3 left

💡 Hint

Common Mistakes

Using values greater than 1 or negative values for the threshold.

Confusing threshold with score values.

The IoU threshold for non-maximum suppression is usually between 0 and 1; 0.5 is a common choice.

3fill in blank

hard

Fix the error in the code by choosing the correct tensor device for boxes and scores before calling nms.

PyTorch

boxes = boxes.to([1])
scores = scores.to([1])
keep = nms(boxes, scores, 0.5)

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

A'cuda'

B'memory'

C'disk'

D'cpu'

Attempts:

3 left

💡 Hint

Common Mistakes

Using invalid device names like 'disk' or 'memory'.

Not moving tensors to the same device before calling nms.

For GPU acceleration, tensors must be on the 'cuda' device before calling nms.

4fill in blank

hard

Fill both blanks to create a dictionary of filtered boxes and scores after applying nms.

PyTorch

filtered = {
    'boxes': boxes[[1]],
    'scores': scores[[2]]
}

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

Akeep

Bindices

Crange(len(boxes))

Dtorch.arange(len(scores))

Attempts:

3 left

💡 Hint

Common Mistakes

Using unrelated variables like 'indices' or ranges that do not correspond to nms output.

Indexing boxes and scores with different variables.

The variable 'keep' contains the indices of boxes and scores to keep after nms filtering.

5fill in blank

hard

Fill all three blanks to compute the final selected boxes and their labels after nms.

PyTorch

keep = nms([1], [2], [3])
selected_boxes = boxes[keep]
selected_labels = labels[keep]

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

Aboxes

Bscores

C0.4

D0.9

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping boxes and scores arguments.

Using threshold values outside the 0-1 range.

The nms function takes boxes, scores, and a threshold (like 0.4) to return indices of selected boxes.