YOLO-Tutorial-v2/yolo/models/yolov8_e2e/matcher.py

import torch
import torch.nn as nn
import torch.nn.functional as F
from utils.box_ops import bbox_iou


# -------------------------- Task Aligned Assigner --------------------------
class TaskAlignedAssigner(nn.Module):
    """
        This code referenced to https://github.com/ultralytics/ultralytics
    """
    def __init__(self,
                 num_classes     = 80,
                 topk_candidates = 10,
                 alpha           = 0.5,
                 beta            = 6.0, 
                 eps             = 1e-9):
        super(TaskAlignedAssigner, self).__init__()
        self.topk_candidates = topk_candidates
        self.num_classes = num_classes
        self.bg_idx = num_classes
        self.alpha = alpha
        self.beta = beta
        self.eps = eps

    @torch.no_grad()
    def forward(self,
                pd_scores,
                pd_bboxes,
                anc_points,
                gt_labels,
                gt_bboxes):
        self.bs = pd_scores.size(0)
        self.n_max_boxes = gt_bboxes.size(1)

        mask_pos, align_metric, overlaps = self.get_pos_mask(
            pd_scores, pd_bboxes, gt_labels, gt_bboxes, anc_points)

        target_gt_idx, fg_mask, mask_pos = select_highest_overlaps(
            mask_pos, overlaps, self.n_max_boxes)

        # Assigned target
        target_labels, target_bboxes, target_scores = self.get_targets(
            gt_labels, gt_bboxes, target_gt_idx, fg_mask)

        # normalize
        align_metric *= mask_pos
        pos_align_metrics = align_metric.amax(axis=-1, keepdim=True)  # b, max_num_obj
        pos_overlaps = (overlaps * mask_pos).amax(axis=-1, keepdim=True)  # b, max_num_obj
        norm_align_metric = (align_metric * pos_overlaps / (pos_align_metrics + self.eps)).amax(-2).unsqueeze(-1)
        target_scores = target_scores * norm_align_metric

        return target_labels, target_bboxes, target_scores, fg_mask.bool(), target_gt_idx

    def get_pos_mask(self, pd_scores, pd_bboxes, gt_labels, gt_bboxes, anc_points):
        # get in_gts mask, (b, max_num_obj, h*w)
        mask_in_gts = select_candidates_in_gts(anc_points, gt_bboxes)
        # get anchor_align metric, (b, max_num_obj, h*w)
        align_metric, overlaps = self.get_box_metrics(pd_scores, pd_bboxes, gt_labels, gt_bboxes, mask_in_gts)
        # get topk_metric mask, (b, max_num_obj, h*w)
        mask_topk = self.select_topk_candidates(align_metric)
        # merge all mask to a final mask, (b, max_num_obj, h*w)
        mask_pos = mask_topk * mask_in_gts

        return mask_pos, align_metric, overlaps

    def get_box_metrics(self, pd_scores, pd_bboxes, gt_labels, gt_bboxes, mask_in_gts):
        """Compute alignment metric given predicted and ground truth bounding boxes."""
        na = pd_bboxes.shape[-2]
        mask_in_gts = mask_in_gts.bool()  # b, max_num_obj, h*w
        overlaps = torch.zeros([self.bs, self.n_max_boxes, na], dtype=pd_bboxes.dtype, device=pd_bboxes.device)
        bbox_scores = torch.zeros([self.bs, self.n_max_boxes, na], dtype=pd_scores.dtype, device=pd_scores.device)

        ind = torch.zeros([2, self.bs, self.n_max_boxes], dtype=torch.long)  # 2, b, max_num_obj
        ind[0] = torch.arange(end=self.bs).view(-1, 1).expand(-1, self.n_max_boxes)  # b, max_num_obj
        ind[1] = gt_labels.squeeze(-1)  # b, max_num_obj
        # Get the scores of each grid for each gt cls
        bbox_scores[mask_in_gts] = pd_scores[ind[0], :, ind[1]][mask_in_gts]  # b, max_num_obj, h*w

        # (b, max_num_obj, 1, 4), (b, 1, h*w, 4)
        pd_boxes = pd_bboxes.unsqueeze(1).expand(-1, self.n_max_boxes, -1, -1)[mask_in_gts]
        gt_boxes = gt_bboxes.unsqueeze(2).expand(-1, -1, na, -1)[mask_in_gts]
        overlaps[mask_in_gts] = bbox_iou(gt_boxes, pd_boxes, xywh=False, CIoU=True).squeeze(-1).clamp_(0)

        align_metric = bbox_scores.pow(self.alpha) * overlaps.pow(self.beta)
        return align_metric, overlaps

    def select_topk_candidates(self, metrics, largest=True):
        """
        Args:
            metrics: (b, max_num_obj, h*w).
            topk_mask: (b, max_num_obj, topk) or None
        """
        # (b, max_num_obj, topk)
        topk_metrics, topk_idxs = torch.topk(metrics, self.topk_candidates, dim=-1, largest=largest)
        topk_mask = (topk_metrics.max(-1, keepdim=True)[0] > self.eps).expand_as(topk_idxs)
        # (b, max_num_obj, topk)
        topk_idxs.masked_fill_(~topk_mask, 0)

        # (b, max_num_obj, topk, h*w) -> (b, max_num_obj, h*w)
        count_tensor = torch.zeros(metrics.shape, dtype=torch.int8, device=topk_idxs.device)
        ones = torch.ones_like(topk_idxs[:, :, :1], dtype=torch.int8, device=topk_idxs.device)
        for k in range(self.topk_candidates):
            # Expand topk_idxs for each value of k and add 1 at the specified positions
            count_tensor.scatter_add_(-1, topk_idxs[:, :, k:k + 1], ones)
        # count_tensor.scatter_add_(-1, topk_idxs, torch.ones_like(topk_idxs, dtype=torch.int8, device=topk_idxs.device))
        # Filter invalid bboxes
        count_tensor.masked_fill_(count_tensor > 1, 0)

        return count_tensor.to(metrics.dtype)

    def get_targets(self, gt_labels, gt_bboxes, target_gt_idx, fg_mask):
        # Assigned target labels, (b, 1)
        batch_ind = torch.arange(end=self.bs, dtype=torch.int64, device=gt_labels.device)[..., None]
        target_gt_idx = target_gt_idx + batch_ind * self.n_max_boxes  # (b, h*w)
        target_labels = gt_labels.long().flatten()[target_gt_idx]  # (b, h*w)

        # Assigned target boxes, (b, max_num_obj, 4) -> (b, h*w, 4)
        target_bboxes = gt_bboxes.view(-1, 4)[target_gt_idx]

        # Assigned target scores
        target_labels.clamp_(0)

        # 10x faster than F.one_hot()
        target_scores = torch.zeros((target_labels.shape[0], target_labels.shape[1], self.num_classes),
                                    dtype=torch.int64,
                                    device=target_labels.device)  # (b, h*w, 80)
        target_scores.scatter_(2, target_labels.unsqueeze(-1), 1)

        fg_scores_mask = fg_mask[:, :, None].repeat(1, 1, self.num_classes)  # (b, h*w, 80)
        target_scores = torch.where(fg_scores_mask > 0, target_scores, 0)

        return target_labels, target_bboxes, target_scores
    

# -------------------------- Basic Functions --------------------------
def select_candidates_in_gts(xy_centers, gt_bboxes, eps=1e-9):
    """select the positive anchors's center in gt
    Args:
        xy_centers (Tensor): shape(bs*n_max_boxes, num_total_anchors, 4)
        gt_bboxes (Tensor): shape(bs, n_max_boxes, 4)
    Return:
        (Tensor): shape(bs, n_max_boxes, num_total_anchors)
    """
    n_anchors = xy_centers.size(0)
    bs, n_max_boxes, _ = gt_bboxes.size()
    _gt_bboxes = gt_bboxes.reshape([-1, 4])
    xy_centers = xy_centers.unsqueeze(0).repeat(bs * n_max_boxes, 1, 1)
    gt_bboxes_lt = _gt_bboxes[:, 0:2].unsqueeze(1).repeat(1, n_anchors, 1)
    gt_bboxes_rb = _gt_bboxes[:, 2:4].unsqueeze(1).repeat(1, n_anchors, 1)
    b_lt = xy_centers - gt_bboxes_lt
    b_rb = gt_bboxes_rb - xy_centers
    bbox_deltas = torch.cat([b_lt, b_rb], dim=-1)
    bbox_deltas = bbox_deltas.reshape([bs, n_max_boxes, n_anchors, -1])
    return (bbox_deltas.min(axis=-1)[0] > eps).to(gt_bboxes.dtype)

def select_highest_overlaps(mask_pos, overlaps, n_max_boxes):
    """if an anchor box is assigned to multiple gts,
        the one with the highest iou will be selected.
    Args:
        mask_pos (Tensor): shape(bs, n_max_boxes, num_total_anchors)
        overlaps (Tensor): shape(bs, n_max_boxes, num_total_anchors)
    Return:
        target_gt_idx (Tensor): shape(bs, num_total_anchors)
        fg_mask (Tensor): shape(bs, num_total_anchors)
        mask_pos (Tensor): shape(bs, n_max_boxes, num_total_anchors)
    """
    fg_mask = mask_pos.sum(-2)
    if fg_mask.max() > 1:  # one anchor is assigned to multiple gt_bboxes
        mask_multi_gts = (fg_mask.unsqueeze(1) > 1).expand(-1, n_max_boxes, -1)  # (b, n_max_boxes, h*w)
        max_overlaps_idx = overlaps.argmax(1)  # (b, h*w)

        is_max_overlaps = torch.zeros(mask_pos.shape, dtype=mask_pos.dtype, device=mask_pos.device)
        is_max_overlaps.scatter_(1, max_overlaps_idx.unsqueeze(1), 1)

        mask_pos = torch.where(mask_multi_gts, is_max_overlaps, mask_pos).float()  # (b, n_max_boxes, h*w)
        fg_mask = mask_pos.sum(-2)
    # Find each grid serve which gt(index)
    target_gt_idx = mask_pos.argmax(-2)  # (b, h*w)

    return target_gt_idx, fg_mask, mask_pos

def iou_calculator(box1, box2, eps=1e-9):
    """Calculate iou for batch
    Args:
        box1 (Tensor): shape(bs, n_max_boxes, 1, 4)
        box2 (Tensor): shape(bs, 1, num_total_anchors, 4)
    Return:
        (Tensor): shape(bs, n_max_boxes, num_total_anchors)
    """
    box1 = box1.unsqueeze(2)  # [N, M1, 4] -> [N, M1, 1, 4]
    box2 = box2.unsqueeze(1)  # [N, M2, 4] -> [N, 1, M2, 4]
    px1y1, px2y2 = box1[:, :, :, 0:2], box1[:, :, :, 2:4]
    gx1y1, gx2y2 = box2[:, :, :, 0:2], box2[:, :, :, 2:4]
    x1y1 = torch.maximum(px1y1, gx1y1)
    x2y2 = torch.minimum(px2y2, gx2y2)
    overlap = (x2y2 - x1y1).clip(0).prod(-1)
    area1 = (px2y2 - px1y1).clip(0).prod(-1)
    area2 = (gx2y2 - gx1y1).clip(0).prod(-1)
    union = area1 + area2 - overlap + eps

    return overlap / union