コンテンツへスキップ

参考 ultralytics/models/utils/ops.py

備考

このファイルはhttps://github.com/ultralytics/ultralytics/blob/main/ ultralytics/models/utils/ops .py にあります。もし問題を発見したら、Pull Request🛠️ を投稿して修正にご協力ください。ありがとうございました!



ultralytics.models.utils.ops.HungarianMatcher

ベース: Module

HungarianMatcherを実装したモジュール。 を実装したモジュールである。

HungarianMatcherは、予測されたバウンディングボックスとグラウンドトゥルースのバウンディングボックスに対して、分類スコアとバウンディングボックス座標、そしてオプションでマスク予測値を考慮したコスト関数を用いて最適な割り当てを行います。 関数を使って最適な割り当てを行います。

属性:

名称 タイプ 説明
cost_gain dict

コスト係数の辞書:class'、'bbox'、'giou'、'mask'、'dice'。

use_fl bool

分類コストの計算にフォーカルロスを使用するかどうかを示す。

with_mask bool

モデルがマスク予測を行うかどうかを示す。

num_sample_points int

マスクコスト計算に使用するサンプルポイントの数。

alpha float

フォーカルロスの計算におけるアルファ係数。

gamma float

フォーカルロスの計算におけるガンマ係数。

方法:

名称 説明
forward

バッチに対して バッチに対する予測と地上真理の割り当てを計算する。

_cost_mask

マスクが予測される場合、マスク・コストとダイス・コストを計算する。

ソースコード ultralytics/models/utils/ops.py
class HungarianMatcher(nn.Module):
    """
    A module implementing the HungarianMatcher, which is a differentiable module to solve the assignment problem in an
    end-to-end fashion.

    HungarianMatcher performs optimal assignment over the predicted and ground truth bounding boxes using a cost
    function that considers classification scores, bounding box coordinates, and optionally, mask predictions.

    Attributes:
        cost_gain (dict): Dictionary of cost coefficients: 'class', 'bbox', 'giou', 'mask', and 'dice'.
        use_fl (bool): Indicates whether to use Focal Loss for the classification cost calculation.
        with_mask (bool): Indicates whether the model makes mask predictions.
        num_sample_points (int): The number of sample points used in mask cost calculation.
        alpha (float): The alpha factor in Focal Loss calculation.
        gamma (float): The gamma factor in Focal Loss calculation.

    Methods:
        forward(pred_bboxes, pred_scores, gt_bboxes, gt_cls, gt_groups, masks=None, gt_mask=None): Computes the
            assignment between predictions and ground truths for a batch.
        _cost_mask(bs, num_gts, masks=None, gt_mask=None): Computes the mask cost and dice cost if masks are predicted.
    """

    def __init__(self, cost_gain=None, use_fl=True, with_mask=False, num_sample_points=12544, alpha=0.25, gamma=2.0):
        """Initializes HungarianMatcher with cost coefficients, Focal Loss, mask prediction, sample points, and alpha
        gamma factors.
        """
        super().__init__()
        if cost_gain is None:
            cost_gain = {"class": 1, "bbox": 5, "giou": 2, "mask": 1, "dice": 1}
        self.cost_gain = cost_gain
        self.use_fl = use_fl
        self.with_mask = with_mask
        self.num_sample_points = num_sample_points
        self.alpha = alpha
        self.gamma = gamma

    def forward(self, pred_bboxes, pred_scores, gt_bboxes, gt_cls, gt_groups, masks=None, gt_mask=None):
        """
        Forward pass for HungarianMatcher. This function computes costs based on prediction and ground truth
        (classification cost, L1 cost between boxes and GIoU cost between boxes) and finds the optimal matching between
        predictions and ground truth based on these costs.

        Args:
            pred_bboxes (Tensor): Predicted bounding boxes with shape [batch_size, num_queries, 4].
            pred_scores (Tensor): Predicted scores with shape [batch_size, num_queries, num_classes].
            gt_cls (torch.Tensor): Ground truth classes with shape [num_gts, ].
            gt_bboxes (torch.Tensor): Ground truth bounding boxes with shape [num_gts, 4].
            gt_groups (List[int]): List of length equal to batch size, containing the number of ground truths for
                each image.
            masks (Tensor, optional): Predicted masks with shape [batch_size, num_queries, height, width].
                Defaults to None.
            gt_mask (List[Tensor], optional): List of ground truth masks, each with shape [num_masks, Height, Width].
                Defaults to None.

        Returns:
            (List[Tuple[Tensor, Tensor]]): A list of size batch_size, each element is a tuple (index_i, index_j), where:
                - index_i is the tensor of indices of the selected predictions (in order)
                - index_j is the tensor of indices of the corresponding selected ground truth targets (in order)
                For each batch element, it holds:
                    len(index_i) = len(index_j) = min(num_queries, num_target_boxes)
        """

        bs, nq, nc = pred_scores.shape

        if sum(gt_groups) == 0:
            return [(torch.tensor([], dtype=torch.long), torch.tensor([], dtype=torch.long)) for _ in range(bs)]

        # We flatten to compute the cost matrices in a batch
        # [batch_size * num_queries, num_classes]
        pred_scores = pred_scores.detach().view(-1, nc)
        pred_scores = F.sigmoid(pred_scores) if self.use_fl else F.softmax(pred_scores, dim=-1)
        # [batch_size * num_queries, 4]
        pred_bboxes = pred_bboxes.detach().view(-1, 4)

        # Compute the classification cost
        pred_scores = pred_scores[:, gt_cls]
        if self.use_fl:
            neg_cost_class = (1 - self.alpha) * (pred_scores**self.gamma) * (-(1 - pred_scores + 1e-8).log())
            pos_cost_class = self.alpha * ((1 - pred_scores) ** self.gamma) * (-(pred_scores + 1e-8).log())
            cost_class = pos_cost_class - neg_cost_class
        else:
            cost_class = -pred_scores

        # Compute the L1 cost between boxes
        cost_bbox = (pred_bboxes.unsqueeze(1) - gt_bboxes.unsqueeze(0)).abs().sum(-1)  # (bs*num_queries, num_gt)

        # Compute the GIoU cost between boxes, (bs*num_queries, num_gt)
        cost_giou = 1.0 - bbox_iou(pred_bboxes.unsqueeze(1), gt_bboxes.unsqueeze(0), xywh=True, GIoU=True).squeeze(-1)

        # Final cost matrix
        C = (
            self.cost_gain["class"] * cost_class
            + self.cost_gain["bbox"] * cost_bbox
            + self.cost_gain["giou"] * cost_giou
        )
        # Compute the mask cost and dice cost
        if self.with_mask:
            C += self._cost_mask(bs, gt_groups, masks, gt_mask)

        # Set invalid values (NaNs and infinities) to 0 (fixes ValueError: matrix contains invalid numeric entries)
        C[C.isnan() | C.isinf()] = 0.0

        C = C.view(bs, nq, -1).cpu()
        indices = [linear_sum_assignment(c[i]) for i, c in enumerate(C.split(gt_groups, -1))]
        gt_groups = torch.as_tensor([0, *gt_groups[:-1]]).cumsum_(0)  # (idx for queries, idx for gt)
        return [
            (torch.tensor(i, dtype=torch.long), torch.tensor(j, dtype=torch.long) + gt_groups[k])
            for k, (i, j) in enumerate(indices)
        ]

__init__(cost_gain=None, use_fl=True, with_mask=False, num_sample_points=12544, alpha=0.25, gamma=2.0)

HungarianMatcherをコスト係数、フォーカルロス、マスク予測、サンプルポイント、アルファガンマ係数で初期化します。 ガンマ係数。

ソースコード ultralytics/models/utils/ops.py
def __init__(self, cost_gain=None, use_fl=True, with_mask=False, num_sample_points=12544, alpha=0.25, gamma=2.0):
    """Initializes HungarianMatcher with cost coefficients, Focal Loss, mask prediction, sample points, and alpha
    gamma factors.
    """
    super().__init__()
    if cost_gain is None:
        cost_gain = {"class": 1, "bbox": 5, "giou": 2, "mask": 1, "dice": 1}
    self.cost_gain = cost_gain
    self.use_fl = use_fl
    self.with_mask = with_mask
    self.num_sample_points = num_sample_points
    self.alpha = alpha
    self.gamma = gamma

forward(pred_bboxes, pred_scores, gt_bboxes, gt_cls, gt_groups, masks=None, gt_mask=None)

HungarianMatcherのフォワードパス。この関数は、予測およびグランドトゥルース (分類コスト、ボックス間のL1コスト、ボックス間のGIoUコスト)を計算し、これらのコストに基づいて予測値とグランドトゥルース間の最適なマッチングを求める。 を求めます。

パラメーター

名称 タイプ 説明 デフォルト
pred_bboxes Tensor

batch_size, num_queries, 4]の形状を持つ予測バウンディングボックス。

必須
pred_scores Tensor

batch_size, num_queries, num_classes]の形状を持つ予測スコア。

必須
gt_cls Tensor

形状 [num_gts, ] を持つ基底真理クラス。

必須
gt_bboxes Tensor

num_gts, 4]の形状を持つグラウンドトゥルースのバウンディングボックス。

必須
gt_groups List[int]

バッチサイズに等しい長さのリスト. バッチサイズに等しい長さのリスト.

必須
masks Tensor

batch_size, num_queries, height, width]の形状を持つ予測マスク。 デフォルトはNone。

None
gt_mask List[Tensor]

各マスクの形状 [num_masks, Height, Width]。 デフォルトは None。

None

リターンズ

タイプ 説明
List[Tuple[Tensor, Tensor]]

サイズbatch_sizeのリストで、各要素はタプル(index_i, index_j)である: - index_iは、選択された予測値のインデックスのtensor (順番)。 - index_j は、対応する選択された地上真理ターゲットのインデックスのtensor (順番)。 各バッチ要素について len(index_i) = len(index_j) = min(num_queries, num_target_boxes)

ソースコード ultralytics/models/utils/ops.py
def forward(self, pred_bboxes, pred_scores, gt_bboxes, gt_cls, gt_groups, masks=None, gt_mask=None):
    """
    Forward pass for HungarianMatcher. This function computes costs based on prediction and ground truth
    (classification cost, L1 cost between boxes and GIoU cost between boxes) and finds the optimal matching between
    predictions and ground truth based on these costs.

    Args:
        pred_bboxes (Tensor): Predicted bounding boxes with shape [batch_size, num_queries, 4].
        pred_scores (Tensor): Predicted scores with shape [batch_size, num_queries, num_classes].
        gt_cls (torch.Tensor): Ground truth classes with shape [num_gts, ].
        gt_bboxes (torch.Tensor): Ground truth bounding boxes with shape [num_gts, 4].
        gt_groups (List[int]): List of length equal to batch size, containing the number of ground truths for
            each image.
        masks (Tensor, optional): Predicted masks with shape [batch_size, num_queries, height, width].
            Defaults to None.
        gt_mask (List[Tensor], optional): List of ground truth masks, each with shape [num_masks, Height, Width].
            Defaults to None.

    Returns:
        (List[Tuple[Tensor, Tensor]]): A list of size batch_size, each element is a tuple (index_i, index_j), where:
            - index_i is the tensor of indices of the selected predictions (in order)
            - index_j is the tensor of indices of the corresponding selected ground truth targets (in order)
            For each batch element, it holds:
                len(index_i) = len(index_j) = min(num_queries, num_target_boxes)
    """

    bs, nq, nc = pred_scores.shape

    if sum(gt_groups) == 0:
        return [(torch.tensor([], dtype=torch.long), torch.tensor([], dtype=torch.long)) for _ in range(bs)]

    # We flatten to compute the cost matrices in a batch
    # [batch_size * num_queries, num_classes]
    pred_scores = pred_scores.detach().view(-1, nc)
    pred_scores = F.sigmoid(pred_scores) if self.use_fl else F.softmax(pred_scores, dim=-1)
    # [batch_size * num_queries, 4]
    pred_bboxes = pred_bboxes.detach().view(-1, 4)

    # Compute the classification cost
    pred_scores = pred_scores[:, gt_cls]
    if self.use_fl:
        neg_cost_class = (1 - self.alpha) * (pred_scores**self.gamma) * (-(1 - pred_scores + 1e-8).log())
        pos_cost_class = self.alpha * ((1 - pred_scores) ** self.gamma) * (-(pred_scores + 1e-8).log())
        cost_class = pos_cost_class - neg_cost_class
    else:
        cost_class = -pred_scores

    # Compute the L1 cost between boxes
    cost_bbox = (pred_bboxes.unsqueeze(1) - gt_bboxes.unsqueeze(0)).abs().sum(-1)  # (bs*num_queries, num_gt)

    # Compute the GIoU cost between boxes, (bs*num_queries, num_gt)
    cost_giou = 1.0 - bbox_iou(pred_bboxes.unsqueeze(1), gt_bboxes.unsqueeze(0), xywh=True, GIoU=True).squeeze(-1)

    # Final cost matrix
    C = (
        self.cost_gain["class"] * cost_class
        + self.cost_gain["bbox"] * cost_bbox
        + self.cost_gain["giou"] * cost_giou
    )
    # Compute the mask cost and dice cost
    if self.with_mask:
        C += self._cost_mask(bs, gt_groups, masks, gt_mask)

    # Set invalid values (NaNs and infinities) to 0 (fixes ValueError: matrix contains invalid numeric entries)
    C[C.isnan() | C.isinf()] = 0.0

    C = C.view(bs, nq, -1).cpu()
    indices = [linear_sum_assignment(c[i]) for i, c in enumerate(C.split(gt_groups, -1))]
    gt_groups = torch.as_tensor([0, *gt_groups[:-1]]).cumsum_(0)  # (idx for queries, idx for gt)
    return [
        (torch.tensor(i, dtype=torch.long), torch.tensor(j, dtype=torch.long) + gt_groups[k])
        for k, (i, j) in enumerate(indices)
    ]



ultralytics.models.utils.ops.get_cdn_group(batch, num_classes, num_queries, class_embed, num_dn=100, cls_noise_ratio=0.5, box_noise_scale=1.0, training=False)

コントラスト除去トレーニンググループを取得する。この関数は、グランドトゥルース(gt)から正と負のサンプルを用いて を作成します.この関数は,クラスラベルとバウンディングボックスの座標にノイズを適用します. そして,変更後のラベル,バウンディングボックス,アテンションマスク,メタ情報を返します.

パラメーター

名称 タイプ 説明 デフォルト
batch dict

gt_cls' (torch.Tensor 形状 [num_gts, ]), 'gt_bboxes' ( . 形状 [num_gts, 4]), 'gt_groups' (List(int)) を含むdict。 (torch.Tensor with shape [num_gts, 4]), 'gt_groups' (List(int)) が含まれます。 各画像のgtsの数を示す。

必須
num_classes int

クラスの数

必須
num_queries int

クエリーの数

必須
class_embed Tensor

クラスラベルを埋め込み空間にマッピングするための埋め込み重み。

必須
num_dn int

ノイズ除去の回数。デフォルトは100。

100
cls_noise_ratio float

クラス・ラベルのノイズ比率。デフォルトは0.5。

0.5
box_noise_scale float

バウンディングボックス座標のノイズスケール。デフォルトは1.0。

1.0
training bool

トレーニングモードの場合。デフォルトはFalse。

False

リターンズ

タイプ 説明
Tuple[Optional[Tensor], Optional[Tensor], Optional[Tensor], Optional[Dict]]

修正クラス埋め込み、 バウンディングボックス,アテンションマスク,ノイズ除去のためのメタ情報.トレーニングモードでない場合,または 'num_dn' が0以下の場合,この関数はタプル内のすべての要素に対してNoneを返す.

ソースコード ultralytics/models/utils/ops.py
def get_cdn_group(
    batch, num_classes, num_queries, class_embed, num_dn=100, cls_noise_ratio=0.5, box_noise_scale=1.0, training=False
):
    """
    Get contrastive denoising training group. This function creates a contrastive denoising training group with positive
    and negative samples from the ground truths (gt). It applies noise to the class labels and bounding box coordinates,
    and returns the modified labels, bounding boxes, attention mask and meta information.

    Args:
        batch (dict): A dict that includes 'gt_cls' (torch.Tensor with shape [num_gts, ]), 'gt_bboxes'
            (torch.Tensor with shape [num_gts, 4]), 'gt_groups' (List(int)) which is a list of batch size length
            indicating the number of gts of each image.
        num_classes (int): Number of classes.
        num_queries (int): Number of queries.
        class_embed (torch.Tensor): Embedding weights to map class labels to embedding space.
        num_dn (int, optional): Number of denoising. Defaults to 100.
        cls_noise_ratio (float, optional): Noise ratio for class labels. Defaults to 0.5.
        box_noise_scale (float, optional): Noise scale for bounding box coordinates. Defaults to 1.0.
        training (bool, optional): If it's in training mode. Defaults to False.

    Returns:
        (Tuple[Optional[Tensor], Optional[Tensor], Optional[Tensor], Optional[Dict]]): The modified class embeddings,
            bounding boxes, attention mask and meta information for denoising. If not in training mode or 'num_dn'
            is less than or equal to 0, the function returns None for all elements in the tuple.
    """

    if (not training) or num_dn <= 0:
        return None, None, None, None
    gt_groups = batch["gt_groups"]
    total_num = sum(gt_groups)
    max_nums = max(gt_groups)
    if max_nums == 0:
        return None, None, None, None

    num_group = num_dn // max_nums
    num_group = 1 if num_group == 0 else num_group
    # Pad gt to max_num of a batch
    bs = len(gt_groups)
    gt_cls = batch["cls"]  # (bs*num, )
    gt_bbox = batch["bboxes"]  # bs*num, 4
    b_idx = batch["batch_idx"]

    # Each group has positive and negative queries.
    dn_cls = gt_cls.repeat(2 * num_group)  # (2*num_group*bs*num, )
    dn_bbox = gt_bbox.repeat(2 * num_group, 1)  # 2*num_group*bs*num, 4
    dn_b_idx = b_idx.repeat(2 * num_group).view(-1)  # (2*num_group*bs*num, )

    # Positive and negative mask
    # (bs*num*num_group, ), the second total_num*num_group part as negative samples
    neg_idx = torch.arange(total_num * num_group, dtype=torch.long, device=gt_bbox.device) + num_group * total_num

    if cls_noise_ratio > 0:
        # Half of bbox prob
        mask = torch.rand(dn_cls.shape) < (cls_noise_ratio * 0.5)
        idx = torch.nonzero(mask).squeeze(-1)
        # Randomly put a new one here
        new_label = torch.randint_like(idx, 0, num_classes, dtype=dn_cls.dtype, device=dn_cls.device)
        dn_cls[idx] = new_label

    if box_noise_scale > 0:
        known_bbox = xywh2xyxy(dn_bbox)

        diff = (dn_bbox[..., 2:] * 0.5).repeat(1, 2) * box_noise_scale  # 2*num_group*bs*num, 4

        rand_sign = torch.randint_like(dn_bbox, 0, 2) * 2.0 - 1.0
        rand_part = torch.rand_like(dn_bbox)
        rand_part[neg_idx] += 1.0
        rand_part *= rand_sign
        known_bbox += rand_part * diff
        known_bbox.clip_(min=0.0, max=1.0)
        dn_bbox = xyxy2xywh(known_bbox)
        dn_bbox = torch.logit(dn_bbox, eps=1e-6)  # inverse sigmoid

    num_dn = int(max_nums * 2 * num_group)  # total denoising queries
    # class_embed = torch.cat([class_embed, torch.zeros([1, class_embed.shape[-1]], device=class_embed.device)])
    dn_cls_embed = class_embed[dn_cls]  # bs*num * 2 * num_group, 256
    padding_cls = torch.zeros(bs, num_dn, dn_cls_embed.shape[-1], device=gt_cls.device)
    padding_bbox = torch.zeros(bs, num_dn, 4, device=gt_bbox.device)

    map_indices = torch.cat([torch.tensor(range(num), dtype=torch.long) for num in gt_groups])
    pos_idx = torch.stack([map_indices + max_nums * i for i in range(num_group)], dim=0)

    map_indices = torch.cat([map_indices + max_nums * i for i in range(2 * num_group)])
    padding_cls[(dn_b_idx, map_indices)] = dn_cls_embed
    padding_bbox[(dn_b_idx, map_indices)] = dn_bbox

    tgt_size = num_dn + num_queries
    attn_mask = torch.zeros([tgt_size, tgt_size], dtype=torch.bool)
    # Match query cannot see the reconstruct
    attn_mask[num_dn:, :num_dn] = True
    # Reconstruct cannot see each other
    for i in range(num_group):
        if i == 0:
            attn_mask[max_nums * 2 * i : max_nums * 2 * (i + 1), max_nums * 2 * (i + 1) : num_dn] = True
        if i == num_group - 1:
            attn_mask[max_nums * 2 * i : max_nums * 2 * (i + 1), : max_nums * i * 2] = True
        else:
            attn_mask[max_nums * 2 * i : max_nums * 2 * (i + 1), max_nums * 2 * (i + 1) : num_dn] = True
            attn_mask[max_nums * 2 * i : max_nums * 2 * (i + 1), : max_nums * 2 * i] = True
    dn_meta = {
        "dn_pos_idx": [p.reshape(-1) for p in pos_idx.cpu().split(list(gt_groups), dim=1)],
        "dn_num_group": num_group,
        "dn_num_split": [num_dn, num_queries],
    }

    return (
        padding_cls.to(class_embed.device),
        padding_bbox.to(class_embed.device),
        attn_mask.to(class_embed.device),
        dn_meta,
    )





作成日:2023-11-12 更新日:2023-11-25
作成者:glenn-jocher(3),Laughing-q(1)