To use pre-trained models in PyTorch, you can use the torchvision.models module, which provides a collection of popular pre-trained models for image classification, object detection, and other computer vision tasks. Here is an example of how to load a pre-trained ResNet-50 model for image classification:
import torch
import torchvision.models as models
model = models.resnet50(pretrained=True)
In this example, we are using the resnet50() function to load the ResNet-50 model pre-trained on the ImageNet dataset. The pretrained=True argument tells PyTorch to download the pre-trained weights for the model.
Once the pre-trained model is loaded, you can use it to make predictions on new data by passing the input through the model’s forward() method. For example:
# Load an image and preprocess it
image = ...
preprocessed_image = ...
# Make a prediction using the loaded model
logits = model(preprocessed_image)
In this example, we are passing the preprocessed image through the loaded ResNet-50 model to get the logits (raw output) of the model for the given input.
I hope this helps! Let me know if you have any other questions or if there’s anything else I can help you with.