What is transfer learning in PyTorch for computer vision?

What is transfer learning in PyTorch for computer vision?

Transfer learning is a technique where a pre-trained model is fine-tuned on a new dataset. In PyTorch, you can use models like ResNet or VGG that have been trained on large datasets like ImageNet.

How do I implement transfer learning in PyTorch?

To implement transfer learning in PyTorch, you typically load a pre-trained model, modify the final layers to fit your specific task, and then train the model on your dataset.

Can you show me a code example?

Sure! Here's a simple example:

import torch
import torchvision.models as models

# Load a pre-trained model
model = models.resnet18(pretrained=True)

# Modify the final layer
num_ftrs = model.fc.in_features
model.fc = torch.nn.Linear(num_ftrs, num_classes)

# Now you can train the model on your dataset.