Loading a pre-trained model

You are building an application to label images from the social media. This task requires high accuracy and speed. You are going to use a pre-trained ResNet18 model to infer image classes.

Deze oefening maakt deel uit van de cursus

Deep Learning for Images with PyTorch

Cursus bekijken

Oefeninstructies

Import resnet18 and ResNet18_Weights from torchvision.models.
Instantiate the model using resnet18(), setting the weights parameter to weights.
Set model to the evaluation mode.
Initialize the input transforms and assign them to transform.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

# Import resnet18 model
from torchvision.models import ____

# Initialize model with default weights
weights = ResNet18_Weights.DEFAULT
model = ____

# Set model to evaluation mode
model.____

# Initialize the transforms
transform = ____

Code bewerken en uitvoeren