Shortcuts

Source code for torchvision.ops.focal_loss

import torch
import torch.nn.functional as F

from ..utils import _log_api_usage_once


[docs]def sigmoid_focal_loss( inputs: torch.Tensor, targets: torch.Tensor, alpha: float = 0.25, gamma: float = 2, reduction: str = "none", ): """ Original implementation from https://github.com/facebookresearch/fvcore/blob/master/fvcore/nn/focal_loss.py . Loss used in RetinaNet for dense detection: https://arxiv.org/abs/1708.02002. Args: inputs: A float tensor of arbitrary shape. The predictions for each example. targets: A float tensor with the same shape as inputs. Stores the binary classification label for each element in inputs (0 for the negative class and 1 for the positive class). alpha: (optional) Weighting factor in range (0,1) to balance positive vs negative examples or -1 for ignore. Default = 0.25 gamma: Exponent of the modulating factor (1 - p_t) to balance easy vs hard examples. reduction: 'none' | 'mean' | 'sum' 'none': No reduction will be applied to the output. 'mean': The output will be averaged. 'sum': The output will be summed. Returns: Loss tensor with the reduction option applied. """ if not torch.jit.is_scripting() and not torch.jit.is_tracing(): _log_api_usage_once(sigmoid_focal_loss) p = torch.sigmoid(inputs) ce_loss = F.binary_cross_entropy_with_logits(inputs, targets, reduction="none") p_t = p * targets + (1 - p) * (1 - targets) loss = ce_loss * ((1 - p_t) ** gamma) if alpha >= 0: alpha_t = alpha * targets + (1 - alpha) * (1 - targets) loss = alpha_t * loss if reduction == "mean": loss = loss.mean() elif reduction == "sum": loss = loss.sum() return loss

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources