$ pip install byol-pytorch

import torch
from byol_pytorch import BYOL
from torchvision import models

resnet = models.resnet50(pretrained=True)

learner = BYOL(
    resnet,
    image_size = 256,
    hidden_layer = 'avgpool'
)

opt = torch.optim.Adam(learner.parameters(), lr=3e-4)

def sample_unlabelled_images():
    return torch.randn(20, 3, 256, 256)

for _ in range(100):
    images = sample_unlabelled_images()
    loss = learner(images)
    opt.zero_grad()
    loss.backward()
    opt.step()
    learner.update_moving_average() # update moving average of target encoder

# save your improved network
torch.save(resnet.state_dict(), './improved-net.pt')

learner = BYOL(
    resnet,
    image_size = 256,
    hidden_layer = 'avgpool',
    projection_size = 256,           # the projection size
    projection_hidden_size = 4096,   # the hidden dimension of the MLP for both the projection and prediction
    moving_average_decay = 0.99      # the moving average decay factor for the target encoder, already set at what paper recommends
)

augment_fn = nn.Sequential(
    kornia.augmentations.RandomHorizontalFlip()
)

learner = BYOL(
    resnet,
    image_size = 256,
    hidden_layer = -2,
    augment_fn = augment_fn
)

@misc{grill2020bootstrap,
    title = {Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning},
    author = {Jean-Bastien Grill and Florian Strub and Florent Altché and Corentin Tallec and Pierre H. Richemond and Elena Buchatskaya and Carl Doersch and Bernardo Avila Pires and Zhaohan Daniel Guo and Mohammad Gheshlaghi Azar and Bilal Piot and Koray Kavukcuoglu and Rémi Munos and Michal Valko},
    year = {2020},
    eprint = {2006.07733},
    archivePrefix = {arXiv},
    primaryClass = {cs.LG}
}