SimSiam

Example implementation of the SimSiam architecture.

Reference:

Exploring Simple Siamese Representation Learning, 2020

Tutorials:

Tutorial 4: Train SimSiam on Satellite Images

PyTorchLightningLightning Distributed

This example can be run from the command line with:

python lightly/examples/pytorch/simsiam.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 NegativeCosineSimilarity
from lightly.models.modules import SimSiamPredictionHead, SimSiamProjectionHead
from lightly.transforms import SimSiamTransform


class SimSiam(nn.Module):
    def __init__(self, backbone):
        super().__init__()
        self.backbone = backbone
        self.projection_head = SimSiamProjectionHead(512, 512, 128)
        self.prediction_head = SimSiamPredictionHead(128, 64, 128)

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


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

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

transform = SimSiamTransform(input_size=32)
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 = NegativeCosineSimilarity()
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, p0 = model(x0)
        z1, p1 = model(x1)
        loss = 0.5 * (criterion(z0, p1) + criterion(z1, p0))
        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}")