mmdet/models/losses/iou_loss.py

# Copyright (c) OpenMMLab. All rights reserved.
import math
import warnings

import mmcv
import torch
import torch.nn as nn

from mmdet.core import bbox_overlaps
from ..builder import LOSSES
from .utils import weighted_loss


@mmcv.jit(derivate=True, coderize=True)
@weighted_loss
def iou_loss(pred, target, linear=False, mode='log', eps=1e-6):
    """IoU loss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.
    The loss is calculated as negative log of IoU.

    Args:
        pred (torch.Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (torch.Tensor): Corresponding gt bboxes, shape (n, 4).
        linear (bool, optional): If True, use linear scale of loss instead of
            log scale. Default: False.
        mode (str): Loss scaling mode, including "linear", "square", and "log".
            Default: 'log'
        eps (float): Eps to avoid log(0).

    Return:
        torch.Tensor: Loss tensor.
    """
    assert mode in ['linear', 'square', 'log']
    if linear:
        mode = 'linear'
        warnings.warn('DeprecationWarning: Setting "linear=True" in '
                      'iou_loss is deprecated, please use "mode=`linear`" '
                      'instead.')
    ious = bbox_overlaps(pred, target, is_aligned=True).clamp(min=eps)
    if mode == 'linear':
        loss = 1 - ious
    elif mode == 'square':
        loss = 1 - ious**2
    elif mode == 'log':
        loss = -ious.log()
    else:
        raise NotImplementedError
    return loss


@mmcv.jit(derivate=True, coderize=True)
@weighted_loss
def bounded_iou_loss(pred, target, beta=0.2, eps=1e-3):
    """BIoULoss.

    This is an implementation of paper
    `Improving Object Localization with Fitness NMS and Bounded IoU Loss.
    <https://arxiv.org/abs/1711.00164>`_.

    Args:
        pred (torch.Tensor): Predicted bboxes.
        target (torch.Tensor): Target bboxes.
        beta (float): beta parameter in smoothl1.
        eps (float): eps to avoid NaN.
    """
    pred_ctrx = (pred[:, 0] + pred[:, 2]) * 0.5
    pred_ctry = (pred[:, 1] + pred[:, 3]) * 0.5
    pred_w = pred[:, 2] - pred[:, 0]
    pred_h = pred[:, 3] - pred[:, 1]
    with torch.no_grad():
        target_ctrx = (target[:, 0] + target[:, 2]) * 0.5
        target_ctry = (target[:, 1] + target[:, 3]) * 0.5
        target_w = target[:, 2] - target[:, 0]
        target_h = target[:, 3] - target[:, 1]

    dx = target_ctrx - pred_ctrx
    dy = target_ctry - pred_ctry

    loss_dx = 1 - torch.max(
        (target_w - 2 * dx.abs()) /
        (target_w + 2 * dx.abs() + eps), torch.zeros_like(dx))
    loss_dy = 1 - torch.max(
        (target_h - 2 * dy.abs()) /
        (target_h + 2 * dy.abs() + eps), torch.zeros_like(dy))
    loss_dw = 1 - torch.min(target_w / (pred_w + eps), pred_w /
                            (target_w + eps))
    loss_dh = 1 - torch.min(target_h / (pred_h + eps), pred_h /
                            (target_h + eps))
    # view(..., -1) does not work for empty tensor
    loss_comb = torch.stack([loss_dx, loss_dy, loss_dw, loss_dh],
                            dim=-1).flatten(1)

    loss = torch.where(loss_comb < beta, 0.5 * loss_comb * loss_comb / beta,
                       loss_comb - 0.5 * beta)
    return loss


@mmcv.jit(derivate=True, coderize=True)
@weighted_loss
def giou_loss(pred, target, eps=1e-7):
    r"""`Generalized Intersection over Union: A Metric and A Loss for Bounding
    Box Regression <https://arxiv.org/abs/1902.09630>`_.

    Args:
        pred (torch.Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (torch.Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).

    Return:
        Tensor: Loss tensor.
    """
    gious = bbox_overlaps(pred, target, mode='giou', is_aligned=True, eps=eps)
    loss = 1 - gious
    return loss


@mmcv.jit(derivate=True, coderize=True)
@weighted_loss
def diou_loss(pred, target, eps=1e-7):
    r"""`Implementation of Distance-IoU Loss: Faster and Better
    Learning for Bounding Box Regression, https://arxiv.org/abs/1911.08287`_.

    Code is modified from https://github.com/Zzh-tju/DIoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).
    Return:
        Tensor: Loss tensor.
    """
    # overlap
    lt = torch.max(pred[:, :2], target[:, :2])
    rb = torch.min(pred[:, 2:], target[:, 2:])
    wh = (rb - lt).clamp(min=0)
    overlap = wh[:, 0] * wh[:, 1]

    # union
    ap = (pred[:, 2] - pred[:, 0]) * (pred[:, 3] - pred[:, 1])
    ag = (target[:, 2] - target[:, 0]) * (target[:, 3] - target[:, 1])
    union = ap + ag - overlap + eps

    # IoU
    ious = overlap / union

    # enclose area
    enclose_x1y1 = torch.min(pred[:, :2], target[:, :2])
    enclose_x2y2 = torch.max(pred[:, 2:], target[:, 2:])
    enclose_wh = (enclose_x2y2 - enclose_x1y1).clamp(min=0)

    cw = enclose_wh[:, 0]
    ch = enclose_wh[:, 1]

    c2 = cw**2 + ch**2 + eps

    b1_x1, b1_y1 = pred[:, 0], pred[:, 1]
    b1_x2, b1_y2 = pred[:, 2], pred[:, 3]
    b2_x1, b2_y1 = target[:, 0], target[:, 1]
    b2_x2, b2_y2 = target[:, 2], target[:, 3]

    left = ((b2_x1 + b2_x2) - (b1_x1 + b1_x2))**2 / 4
    right = ((b2_y1 + b2_y2) - (b1_y1 + b1_y2))**2 / 4
    rho2 = left + right

    # DIoU
    dious = ious - rho2 / c2
    loss = 1 - dious
    return loss


@mmcv.jit(derivate=True, coderize=True)
@weighted_loss
def ciou_loss(pred, target, eps=1e-7):
    r"""`Implementation of paper `Enhancing Geometric Factors into
    Model Learning and Inference for Object Detection and Instance
    Segmentation <https://arxiv.org/abs/2005.03572>`_.

    Code is modified from https://github.com/Zzh-tju/CIoU.

    Args:
        pred (Tensor): Predicted bboxes of format (x1, y1, x2, y2),
            shape (n, 4).
        target (Tensor): Corresponding gt bboxes, shape (n, 4).
        eps (float): Eps to avoid log(0).
    Return:
        Tensor: Loss tensor.
    """
    # overlap
    lt = torch.max(pred[:, :2], target[:, :2])
    rb = torch.min(pred[:, 2:], target[:, 2:])
    wh = (rb - lt).clamp(min=0)
    overlap = wh[:, 0] * wh[:, 1]

    # union
    ap = (pred[:, 2] - pred[:, 0]) * (pred[:, 3] - pred[:, 1])
    ag = (target[:, 2] - target[:, 0]) * (target[:, 3] - target[:, 1])
    union = ap + ag - overlap + eps

    # IoU
    ious = overlap / union

    # enclose area
    enclose_x1y1 = torch.min(pred[:, :2], target[:, :2])
    enclose_x2y2 = torch.max(pred[:, 2:], target[:, 2:])
    enclose_wh = (enclose_x2y2 - enclose_x1y1).clamp(min=0)

    cw = enclose_wh[:, 0]
    ch = enclose_wh[:, 1]

    c2 = cw**2 + ch**2 + eps

    b1_x1, b1_y1 = pred[:, 0], pred[:, 1]
    b1_x2, b1_y2 = pred[:, 2], pred[:, 3]
    b2_x1, b2_y1 = target[:, 0], target[:, 1]
    b2_x2, b2_y2 = target[:, 2], target[:, 3]

    w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
    w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps

    left = ((b2_x1 + b2_x2) - (b1_x1 + b1_x2))**2 / 4
    right = ((b2_y1 + b2_y2) - (b1_y1 + b1_y2))**2 / 4
    rho2 = left + right

    factor = 4 / math.pi**2
    v = factor * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2)

    with torch.no_grad():
        alpha = (ious > 0.5).float() * v / (1 - ious + v)

    # CIoU
    cious = ious - (rho2 / c2 + alpha * v)
    loss = 1 - cious.clamp(min=-1.0, max=1.0)
    return loss


@LOSSES.register_module()
class IoULoss(nn.Module):
    """IoULoss.

    Computing the IoU loss between a set of predicted bboxes and target bboxes.

    Args:
        linear (bool): If True, use linear scale of loss else determined
            by mode. Default: False.
        eps (float): Eps to avoid log(0).
        reduction (str): Options are "none", "mean" and "sum".
        loss_weight (float): Weight of loss.
        mode (str): Loss scaling mode, including "linear", "square", and "log".
            Default: 'log'
    """

    def __init__(self,
                 linear=False,
                 eps=1e-6,
                 reduction='mean',
                 loss_weight=1.0,
                 mode='log'):
        super(IoULoss, self).__init__()
        assert mode in ['linear', 'square', 'log']
        if linear:
            mode = 'linear'
            warnings.warn('DeprecationWarning: Setting "linear=True" in '
                          'IOULoss is deprecated, please use "mode=`linear`" '
                          'instead.')
        self.mode = mode
        self.linear = linear
        self.eps = eps
        self.reduction = reduction
        self.loss_weight = loss_weight

    def forward(self,
                pred,
                target,
                weight=None,
                avg_factor=None,
                reduction_override=None,
                **kwargs):
        """Forward function.

        Args:
            pred (torch.Tensor): The prediction.
            target (torch.Tensor): The learning target of the prediction.
            weight (torch.Tensor, optional): The weight of loss for each
                prediction. Defaults to None.
            avg_factor (int, optional): Average factor that is used to average
                the loss. Defaults to None.
            reduction_override (str, optional): The reduction method used to
                override the original reduction method of the loss.
                Defaults to None. Options are "none", "mean" and "sum".
        """
        assert reduction_override in (None, 'none', 'mean', 'sum')
        reduction = (
            reduction_override if reduction_override else self.reduction)
        if (weight is not None) and (not torch.any(weight > 0)) and (
                reduction != 'none'):
            if pred.dim() == weight.dim() + 1:
                weight = weight.unsqueeze(1)
            return (pred * weight).sum()  # 0
        if weight is not None and weight.dim() > 1:
            # TODO: remove this in the future
            # reduce the weight of shape (n, 4) to (n,) to match the
            # iou_loss of shape (n,)
            assert weight.shape == pred.shape
            weight = weight.mean(-1)
        loss = self.loss_weight * iou_loss(
            pred,
            target,
            weight,
            mode=self.mode,
            eps=self.eps,
            reduction=reduction,
            avg_factor=avg_factor,
            **kwargs)
        return loss


@LOSSES.register_module()
class BoundedIoULoss(nn.Module):

    def __init__(self, beta=0.2, eps=1e-3, reduction='mean', loss_weight=1.0):
        super(BoundedIoULoss, self).__init__()
        self.beta = beta
        self.eps = eps
        self.reduction = reduction
        self.loss_weight = loss_weight

    def forward(self,
                pred,
                target,
                weight=None,
                avg_factor=None,
                reduction_override=None,
                **kwargs):
        if weight is not None and not torch.any(weight > 0):
            if pred.dim() == weight.dim() + 1:
                weight = weight.unsqueeze(1)
            return (pred * weight).sum()  # 0
        assert reduction_override in (None, 'none', 'mean', 'sum')
        reduction = (
            reduction_override if reduction_override else self.reduction)
        loss = self.loss_weight * bounded_iou_loss(
            pred,
            target,
            weight,
            beta=self.beta,
            eps=self.eps,
            reduction=reduction,
            avg_factor=avg_factor,
            **kwargs)
        return loss


@LOSSES.register_module()
class GIoULoss(nn.Module):

    def __init__(self, eps=1e-6, reduction='mean', loss_weight=1.0):
        super(GIoULoss, self).__init__()
        self.eps = eps
        self.reduction = reduction
        self.loss_weight = loss_weight

    def forward(self,
                pred,
                target,
                weight=None,
                avg_factor=None,
                reduction_override=None,
                **kwargs):
        if weight is not None and not torch.any(weight > 0):
            if pred.dim() == weight.dim() + 1:
                weight = weight.unsqueeze(1)
            return (pred * weight).sum()  # 0
        assert reduction_override in (None, 'none', 'mean', 'sum')
        reduction = (
            reduction_override if reduction_override else self.reduction)
        if weight is not None and weight.dim() > 1:
            # TODO: remove this in the future
            # reduce the weight of shape (n, 4) to (n,) to match the
            # giou_loss of shape (n,)
            assert weight.shape == pred.shape
            weight = weight.mean(-1)
        loss = self.loss_weight * giou_loss(
            pred,
            target,
            weight,
            eps=self.eps,
            reduction=reduction,
            avg_factor=avg_factor,
            **kwargs)
        return loss


@LOSSES.register_module()
class DIoULoss(nn.Module):

    def __init__(self, eps=1e-6, reduction='mean', loss_weight=1.0):
        super(DIoULoss, self).__init__()
        self.eps = eps
        self.reduction = reduction
        self.loss_weight = loss_weight

    def forward(self,
                pred,
                target,
                weight=None,
                avg_factor=None,
                reduction_override=None,
                **kwargs):
        if weight is not None and not torch.any(weight > 0):
            if pred.dim() == weight.dim() + 1:
                weight = weight.unsqueeze(1)
            return (pred * weight).sum()  # 0
        assert reduction_override in (None, 'none', 'mean', 'sum')
        reduction = (
            reduction_override if reduction_override else self.reduction)
        if weight is not None and weight.dim() > 1:
            # TODO: remove this in the future
            # reduce the weight of shape (n, 4) to (n,) to match the
            # giou_loss of shape (n,)
            assert weight.shape == pred.shape
            weight = weight.mean(-1)
        loss = self.loss_weight * diou_loss(
            pred,
            target,
            weight,
            eps=self.eps,
            reduction=reduction,
            avg_factor=avg_factor,
            **kwargs)
        return loss


@LOSSES.register_module()
class CIoULoss(nn.Module):

    def __init__(self, eps=1e-6, reduction='mean', loss_weight=1.0):
        super(CIoULoss, self).__init__()
        self.eps = eps
        self.reduction = reduction
        self.loss_weight = loss_weight

    def forward(self,
                pred,
                target,
                weight=None,
                avg_factor=None,
                reduction_override=None,
                **kwargs):
        if weight is not None and not torch.any(weight > 0):
            if pred.dim() == weight.dim() + 1:
                weight = weight.unsqueeze(1)
            return (pred * weight).sum()  # 0
        assert reduction_override in (None, 'none', 'mean', 'sum')
        reduction = (
            reduction_override if reduction_override else self.reduction)
        if weight is not None and weight.dim() > 1:
            # TODO: remove this in the future
            # reduce the weight of shape (n, 4) to (n,) to match the
            # giou_loss of shape (n,)
            assert weight.shape == pred.shape
            weight = weight.mean(-1)
        loss = self.loss_weight * ciou_loss(
            pred,
            target,
            weight,
            eps=self.eps,
            reduction=reduction,
            avg_factor=avg_factor,
            **kwargs)
        return loss