YOLO concept in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the YOLO model from the ultralytics package.

PyTorch

from ultralytics import [1]

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

Acv2

Btorch

CYOLO

Dnumpy

Attempts:

3 left

💡 Hint

Common Mistakes

Importing torch instead of YOLO

Importing unrelated packages like cv2 or numpy

The YOLO model is imported from the ultralytics package using from ultralytics import YOLO.

2fill in blank

medium

Complete the code to load a pre-trained YOLOv8n model.

PyTorch

model = YOLO([1])

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

A'yolov8n.pt'

B'model.pth'

C'yolov5s.pt'

D'resnet50.pth'

Attempts:

3 left

💡 Hint

Common Mistakes

Using weights from other models like YOLOv5 or ResNet

Using incorrect file extensions

To load the YOLOv8n pre-trained model, use the weights file 'yolov8n.pt'.

3fill in blank

hard

Fix the error in the code to run inference on an image using the YOLO model.

PyTorch

results = model.[1]('image.jpg')

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

Aeval

Bpredict

Ctrain

Dinfer

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'train' which is for training the model

Using 'eval' or 'infer' which are not valid YOLO methods

The correct method to run inference on an image with the YOLO model is predict.

4fill in blank

hard

Fill both blanks to extract bounding boxes and confidence scores from YOLO results.

PyTorch

boxes = results.[1].xyxy
confidences = results.[2].conf

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

Aboxes

Bmasks

Cpred

Dlabels

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'pred' which is not an attribute of results

Using 'masks' which is for segmentation tasks

Using 'labels' which are not the correct attribute

The results.boxes contains the predictions including bounding boxes and confidence scores.

5fill in blank

hard

Fill all three blanks to run training on a custom dataset with YOLO.

PyTorch

model.train(data=[1], epochs=[2], imgsz=[3])

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

A'custom.yaml'

B50

C640

D'yolov8n.pt'

Attempts:

3 left

💡 Hint

Common Mistakes

Using the model weights file as data argument

Confusing epochs with image size

Using incorrect types for arguments

To train YOLO on a custom dataset, specify the data config file, number of epochs, and image size.