不是很懂ProposalTargetCreator里面的loc_normalize_std作用

[wzr0108]

class ProposalTargetCreator(object):
    def __init__(self, n_sample=128, pos_ratio=0.5, pos_iou_thresh=0.5, neg_iou_thresh_high=0.5, neg_iou_thresh_low=0):
        self.n_sample = n_sample
        self.pos_ratio = pos_ratio
        self.pos_roi_per_image = np.round(self.n_sample * self.pos_ratio)
        self.pos_iou_thresh = pos_iou_thresh
        self.neg_iou_thresh_high = neg_iou_thresh_high
        self.neg_iou_thresh_low = neg_iou_thresh_low

    def __call__(self, roi, bbox, label, loc_normalize_std=(0.1, 0.1, 0.2, 0.2)):
        roi = np.concatenate((roi.detach().cpu().numpy(), bbox), axis=0)
        # ----------------------------------------------------- #
        #   计算建议框和真实框的重合程度
        # ----------------------------------------------------- #
        iou = bbox_iou(roi, bbox)

        if len(bbox) == 0:
            gt_assignment = np.zeros(len(roi), np.int32)
            max_iou = np.zeros(len(roi))
            gt_roi_label = np.zeros(len(roi))
        else:
            # ---------------------------------------------------------#
            #   获得每一个建议框最对应的真实框  [num_roi, ]
            # ---------------------------------------------------------#
            gt_assignment = iou.argmax(axis=1)
            # ---------------------------------------------------------#
            #   获得每一个建议框最对应的真实框的iou  [num_roi, ]
            # ---------------------------------------------------------#
            max_iou = iou.max(axis=1)
            # ---------------------------------------------------------#
            #   真实框的标签要+1因为有背景的存在
            # ---------------------------------------------------------#
            gt_roi_label = label[gt_assignment] + 1

        # ----------------------------------------------------------------#
        #   满足建议框和真实框重合程度大于neg_iou_thresh_high的作为负样本
        #   将正样本的数量限制在self.pos_roi_per_image以内
        # ----------------------------------------------------------------#
        pos_index = np.where(max_iou >= self.pos_iou_thresh)[0]
        pos_roi_per_this_image = int(min(self.pos_roi_per_image, pos_index.size))
        if pos_index.size > 0:
            pos_index = np.random.choice(pos_index, size=pos_roi_per_this_image, replace=False)

        # -----------------------------------------------------------------------------------------------------#
        #   满足建议框和真实框重合程度小于neg_iou_thresh_high大于neg_iou_thresh_low作为负样本
        #   将正样本的数量和负样本的数量的总和固定成self.n_sample
        # -----------------------------------------------------------------------------------------------------#
        neg_index = np.where((max_iou < self.neg_iou_thresh_high) & (max_iou >= self.neg_iou_thresh_low))[0]
        neg_roi_per_this_image = self.n_sample - pos_roi_per_this_image
        neg_roi_per_this_image = int(min(neg_roi_per_this_image, neg_index.size))
        if neg_index.size > 0:
            neg_index = np.random.choice(neg_index, size=neg_roi_per_this_image, replace=False)

        # ---------------------------------------------------------#
        #   sample_roi      [n_sample, ]
        #   gt_roi_loc      [n_sample, 4]
        #   gt_roi_label    [n_sample, ]
        # ---------------------------------------------------------#
        keep_index = np.append(pos_index, neg_index)

        sample_roi = roi[keep_index]
        if len(bbox) == 0:
            return sample_roi, np.zeros_like(sample_roi), gt_roi_label[keep_index]

        gt_roi_loc = bbox2loc(sample_roi, bbox[gt_assignment[keep_index]])
        gt_roi_loc = (gt_roi_loc / np.array(loc_normalize_std, np.float32))

        gt_roi_label = gt_roi_label[keep_index]
        gt_roi_label[pos_roi_per_this_image:] = 0
        return sample_roi, gt_roi_loc, gt_roi_label

[wzr0108]

roi = np.concatenate((roi.detach().cpu().numpy(), bbox), axis=0) 为什么要把roi和bbox拼接起来呢

[bubbliiiing]

1、为了改变数量级 2、为了保证每次至少有一点正样本训练classifier

[wzr0108]

太感谢了