RT-ODLab/models/detectors/rtpdetr/loss_utils.py

import math
import torch
import torch.nn.functional as F
import torch.distributed as dist
from torchvision.ops.boxes import box_area


# ------------------------- For loss -------------------------
## FocalLoss
def sigmoid_focal_loss(inputs, targets, num_boxes, alpha: float = 0.25, gamma: float = 2):
    """
    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. Default = -1 (no weighting).
        gamma: Exponent of the modulating factor (1 - p_t) to
               balance easy vs hard examples.
    Returns:
        Loss tensor
    """
    prob = inputs.sigmoid()
    ce_loss = F.binary_cross_entropy_with_logits(inputs, targets, reduction="none")
    p_t = prob * targets + (1 - prob) * (1 - targets)
    loss = ce_loss * ((1 - p_t) ** gamma)

    if alpha >= 0:
        alpha_t = alpha * targets + (1 - alpha) * (1 - targets)
        loss = alpha_t * loss

    return loss.mean(1).sum() / num_boxes


# ------------------------- For box -------------------------
def box_cxcywh_to_xyxy(x):
    x_c, y_c, w, h = x.unbind(-1)
    b = [(x_c - 0.5 * w), (y_c - 0.5 * h),
         (x_c + 0.5 * w), (y_c + 0.5 * h)]
    return torch.stack(b, dim=-1)

def box_xyxy_to_cxcywh(x):
    x0, y0, x1, y1 = x.unbind(-1)
    b = [(x0 + x1) / 2, (y0 + y1) / 2,
         (x1 - x0), (y1 - y0)]
    return torch.stack(b, dim=-1)

def bbox2delta(proposals, gt, means=(0., 0., 0., 0.), stds=(1., 1., 1., 1.)):
    # hack for matcher
    if proposals.size() != gt.size():
        proposals = proposals[:, None]
        gt = gt[None]

    proposals = proposals.float()
    gt = gt.float()
    px, py, pw, ph = proposals.unbind(-1)
    gx, gy, gw, gh = gt.unbind(-1)

    dx = (gx - px) / (pw + 0.1)
    dy = (gy - py) / (ph + 0.1)
    dw = torch.log(gw / (pw + 0.1))
    dh = torch.log(gh / (ph + 0.1))
    deltas = torch.stack([dx, dy, dw, dh], dim=-1)

    means = deltas.new_tensor(means).unsqueeze(0)
    stds = deltas.new_tensor(stds).unsqueeze(0)
    deltas = deltas.sub_(means).div_(stds)

    return deltas

def box_iou(boxes1, boxes2):
    area1 = box_area(boxes1)
    area2 = box_area(boxes2)

    lt = torch.max(boxes1[:, None, :2], boxes2[:, :2])  # [N,M,2]
    rb = torch.min(boxes1[:, None, 2:], boxes2[:, 2:])  # [N,M,2]

    wh = (rb - lt).clamp(min=0)  # [N,M,2]
    inter = wh[:, :, 0] * wh[:, :, 1]  # [N,M]

    union = area1[:, None] + area2 - inter

    iou = inter / union
    return iou, union

def generalized_box_iou(boxes1, boxes2):
    """
    Generalized IoU from https://giou.stanford.edu/

    The boxes should be in [x0, y0, x1, y1] format

    Returns a [N, M] pairwise matrix, where N = len(boxes1)
    and M = len(boxes2)
    """
    # degenerate boxes gives inf / nan results
    # so do an early check
    assert (boxes1[:, 2:] >= boxes1[:, :2]).all()
    assert (boxes2[:, 2:] >= boxes2[:, :2]).all()
    iou, union = box_iou(boxes1, boxes2)

    lt = torch.min(boxes1[:, None, :2], boxes2[:, :2])
    rb = torch.max(boxes1[:, None, 2:], boxes2[:, 2:])

    wh = (rb - lt).clamp(min=0)  # [N,M,2]
    area = wh[:, :, 0] * wh[:, :, 1]

    return iou - (area - union) / area


# ------------------------- For distributed -------------------------
def is_dist_avail_and_initialized():
    if not dist.is_available():
        return False
    if not dist.is_initialized():
        return False
    return True

def get_world_size():
    if not is_dist_avail_and_initialized():
        return 1
    return dist.get_world_size()