from ols import OnlineLabelSmoothing
import torch

k = 4  # Number of classes
b = 32  # Batch size
criterion = OnlineLabelSmoothing(alpha=0.5, n_classes=k, smoothing=0.1)
logits = torch.randn(b, k)  # Predictions
y = torch.randint(k, (b,))  # Ground truth

loss = criterion(logits, y)

from ols import OnlineLabelSmoothing

criterion = OnlineLabelSmoothing(alpha=..., n_classes=...)
for epoch in range(...):  # loop over the dataset multiple times
    for i, data in enumerate(...):
        inputs, labels = data
        # zero the parameter gradients
        optimizer.zero_grad()
        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
    print(f'Epoch {epoch} finished!')
    # Update the soft labels for next epoch
    criterion.next_epoch()

import pytorch_lightning as pl
from ols import OnlineLabelSmoothing


class LitClassification(pl.LightningModule):
    def __init__(self):
        super().__init__()
        self.criterion = OnlineLabelSmoothing(alpha=..., n_classes=...)

    def forward(self, x):
        pass

    def configure_optimizers(self):
        pass

    def training_step(self, train_batch, batch_idx):
        pass

    def on_train_epoch_end(self, **kwargs):
        self.criterion.next_epoch()

pip install -r requirements.txt

@misc{zhang2020delving,
      title={Delving Deep into Label Smoothing}, 
      author={Chang-Bin Zhang and Peng-Tao Jiang and Qibin Hou and Yunchao Wei and Qi Han and Zhen Li and Ming-Ming Cheng},
      year={2020},
      eprint={2011.12562},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}