Barlow Twins

Example implementation of the Barlow Twins architecture.

Reference:

Barlow Twins: Self-Supervised Learning via Redundancy Reduction, 2021

PyTorchLightningLightning Distributed

This example can be run from the command line with:

python lightly/examples/pytorch/barlowtwins.py

# Note: The model and training settings do not follow the reference settings
# from the paper. The settings are chosen such that the example can easily be
# run on a small dataset with a single GPU.

import torch
import torchvision
from torch import nn

from lightly.loss import BarlowTwinsLoss
from lightly.models.modules import BarlowTwinsProjectionHead
from lightly.transforms.byol_transform import (
    BYOLTransform,
    BYOLView1Transform,
    BYOLView2Transform,
)


class BarlowTwins(nn.Module):
    def __init__(self, backbone):
        super().__init__()
        self.backbone = backbone
        self.projection_head = BarlowTwinsProjectionHead(512, 2048, 2048)

    def forward(self, x):
        x = self.backbone(x).flatten(start_dim=1)
        z = self.projection_head(x)
        return z


resnet = torchvision.models.resnet18()
backbone = nn.Sequential(*list(resnet.children())[:-1])
model = BarlowTwins(backbone)

device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

# BarlowTwins uses BYOL augmentations.
# We disable resizing and gaussian blur for cifar10.
transform = BYOLTransform(
    view_1_transform=BYOLView1Transform(input_size=32, gaussian_blur=0.0),
    view_2_transform=BYOLView2Transform(input_size=32, gaussian_blur=0.0),
)
dataset = torchvision.datasets.CIFAR10(
    "datasets/cifar10", download=True, transform=transform
)
# or create a dataset from a folder containing images or videos:
# dataset = LightlyDataset("path/to/folder", transform=transform)

dataloader = torch.utils.data.DataLoader(
    dataset,
    batch_size=256,
    shuffle=True,
    drop_last=True,
    num_workers=8,
)

criterion = BarlowTwinsLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.06)

print("Starting Training")
for epoch in range(10):
    total_loss = 0
    for batch in dataloader:
        x0, x1 = batch[0]
        x0 = x0.to(device)
        x1 = x1.to(device)
        z0 = model(x0)
        z1 = model(x1)
        loss = criterion(z0, z1)
        total_loss += loss.detach()
        loss.backward()
        optimizer.step()
        optimizer.zero_grad()
    avg_loss = total_loss / len(dataloader)
    print(f"epoch: {epoch:>02}, loss: {avg_loss:.5f}")