Action recognition basics in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load video frames for action recognition.

Computer Vision

import cv2

cap = cv2.VideoCapture('video.mp4')
ret, frame = cap.[1]()
if ret:
    print('Frame loaded')
cap.release()

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

Acapture

Bread

Cload

Dget

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'get' instead of 'read' causes an error.

Using 'load' is not a valid method.

The read() method reads the next video frame from the capture object.

2fill in blank

medium

Complete the code to extract features from frames using a pretrained CNN model.

Computer Vision

from torchvision import models, transforms
import torch

model = models.resnet18(pretrained=True)
model.eval()

preprocess = transforms.Compose([
    transforms.Resize(256),
    transforms.CenterCrop(224),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

input_tensor = preprocess(frame)
input_batch = input_tensor.unsqueeze(0)

with torch.no_grad():
    features = model.[1](input_batch)

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

Aforward

Bpredict

Ctransform

Dfit

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'predict' causes attribute error.

Using 'fit' is for training, not inference.

The forward method runs the input through the model to get output features.

3fill in blank

hard

Fix the error in the code to correctly compute accuracy for action recognition predictions.

Computer Vision

correct = 0
for pred, label in zip(predictions, labels):
    if pred == [1]:
        correct += 1
accuracy = correct / len(labels)
print(f'Accuracy: {accuracy:.2f}')

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

Apred

Bpredictions

Clabels

Dlabel

Attempts:

3 left

💡 Hint

Common Mistakes

Comparing prediction to predictions list causes wrong results.

Comparing to 'pred' always true, inflating accuracy.

We compare each predicted label pred to the true label label to count correct predictions.

4fill in blank

hard

Fill both blanks to create a dictionary of frame indices and their corresponding action labels.

Computer Vision

frame_labels = {i: [1] for i, [2] in enumerate(predicted_actions)}

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

Alabel

Baction

Cpredicted_actions

Dlabel_idx

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'predicted_actions' as loop variable causes error.

Using 'label_idx' is not defined in loop.

We use action as the value and action as the loop variable for predicted actions.

5fill in blank

hard

Fill all three blanks to filter frames with confidence above threshold and create a result dictionary.

Computer Vision

result = {frame_id: [1] for frame_id, (label, conf) in frame_data.items() if conf [2] [3]

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

Alabel

B>

C0.8

Dconf

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'conf' as value instead of label.

Using '<' instead of '>' changes filtering logic.

We keep labels where confidence is greater than 0.8.