pythonadvanced

Transfer Learning with TorchVision

Fine-tune a pretrained ResNet for custom image classification with PyTorch and TorchVision.

pythonPress ⌘/Ctrl + Shift + C to copy

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import models, transforms, datasets
from torch.utils.data import DataLoader

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

dataset = datasets.FakeData(size=200, image_size=(3,224,224), num_classes=5, transform=transform)
loader  = DataLoader(dataset, batch_size=16, shuffle=True)

model = models.resnet18(weights=models.ResNet18_Weights.DEFAULT)
for p in model.parameters():
    p.requires_grad = False
model.fc = nn.Linear(model.fc.in_features, 5)

optimizer = optim.Adam(model.fc.parameters(), lr=1e-3)
criterion = nn.CrossEntropyLoss()

model.train()
for images, labels in loader:
    optimizer.zero_grad()
    outputs = model(images)
    loss = criterion(outputs, labels)
    loss.backward()
    optimizer.step()
print('Fine-tuning complete')