模型简介

SSD，全称Single Shot MultiBox Detector，是Wei Liu在ECCV 2016上提出的一种目标检测算法。使用Nvidia Titan X在VOC 2007测试集上，SSD对于输入尺寸300x300的网络，达到74.3%mAP(mean Average Precision)以及59FPS；对于512x512的网络，达到了76.9%mAP ，超越当时最强的Faster RCNN(73.2%mAP)。具体可参考论文[1]。 SSD目标检测主流算法分成可以两个类型：

1. two-stage方法：RCNN系列

   通过算法产生候选框，然后再对这些候选框进行分类和回归。

2. one-stage方法：YOLO和SSD

   直接通过主干网络给出类别位置信息，不需要区域生成。

SSD是单阶段的目标检测算法，通过卷积神经网络进行特征提取，取不同的特征层进行检测输出，所以SSD是一种多尺度的检测方法。在需要检测的特征层，直接使用一个3 ×× 3卷积，进行通道的变换。SSD采用了anchor的策略，预设不同长宽比例的anchor，每一个输出特征层基于anchor预测多个检测框（4或者6）。采用了多尺度检测方法，浅层用于检测小目标，深层用于检测大目标。

SSD的主要特点包括：

1. 单次检测：与其他需要先生成候选区域再进行分类的目标检测方法（如Fast R-CNN, Faster R-CNN）不同，SSD在一次前向传播中直接预测类别和位置，因此速度更快。

2. 多尺度特征图：SSD在网络中使用了不同尺度的特征图来进行检测，这样可以有效地检测到不同大小的目标。

3. 默认框（Default Boxes）：在每个特征图位置上，SSD使用一系列默认框，这些框相对于特征图的位置和大小是固定的。网络对这些默认框内的目标进行分类和位置回归。

4. 损失函数：SSD的损失函数是定位损失（localization loss）和置信度损失（confidence loss）的总和。定位损失用于衡量预测框与真实框之间的差距，置信度损失用于衡量类别预测的准确性。

数据采样

为了使模型对于各种输入对象大小和形状更加鲁棒，SSD算法每个训练图像通过以下选项之一随机采样：

• 使用整个原始输入图像

• 采样一个区域，使采样区域和原始图片最小的交并比重叠为0.1,0.3,0.5,0.7或0.9

• 随机采样一个区域

每个采样区域的大小为原始图像大小的[0.3,1]，长宽比在1/2和2之间。如果真实标签框中心在采样区域内，则保留两者重叠部分作为新图片的真实标注框。在上述采样步骤之后，将每个采样区域大小调整为固定大小，并以0.5的概率水平翻转。

import cv2
import numpy as np

def _rand(a=0., b=1.):
    return np.random.rand() * (b - a) + a

def intersect(box_a, box_b):
    """Compute the intersect of two sets of boxes."""
    max_yx = np.minimum(box_a[:, 2:4], box_b[2:4])
    min_yx = np.maximum(box_a[:, :2], box_b[:2])
    inter = np.clip((max_yx - min_yx), a_min=0, a_max=np.inf)
    return inter[:, 0] * inter[:, 1]

def jaccard_numpy(box_a, box_b):
    """Compute the jaccard overlap of two sets of boxes."""
    inter = intersect(box_a, box_b)
    area_a = ((box_a[:, 2] - box_a[:, 0]) *
              (box_a[:, 3] - box_a[:, 1]))
    area_b = ((box_b[2] - box_b[0]) *
              (box_b[3] - box_b[1]))
    union = area_a + area_b - inter
    return inter / union

def random_sample_crop(image, boxes):
    """Crop images and boxes randomly."""
    height, width, _ = image.shape
    min_iou = np.random.choice([None, 0.1, 0.3, 0.5, 0.7, 0.9])

    if min_iou is None:
        return image, boxes

    for _ in range(50):
        image_t = image
        w = _rand(0.3, 1.0) * width
        h = _rand(0.3, 1.0) * height
        # aspect ratio constraint b/t .5 & 2
        if h / w < 0.5 or h / w > 2:
            continue

        left = _rand() * (width - w)
        top = _rand() * (height - h)
        rect = np.array([int(top), int(left), int(top + h), int(left + w)])
        overlap = jaccard_numpy(boxes, rect)

        # dropout some boxes
        drop_mask = overlap > 0
        if not drop_mask.any():
            continue

        if overlap[drop_mask].min() < min_iou and overlap[drop_mask].max() > (min_iou + 0.2):
            continue

        image_t = image_t[rect[0]:rect[2], rect[1]:rect[3], :]
        centers = (boxes[:, :2] + boxes[:, 2:4]) / 2.0
        m1 = (rect[0] < centers[:, 0]) * (rect[1] < centers[:, 1])
        m2 = (rect[2] > centers[:, 0]) * (rect[3] > centers[:, 1])

        # mask in that both m1 and m2 are true
        mask = m1 * m2 * drop_mask

        # have any valid boxes? try again if not
        if not mask.any():
            continue

        # take only matching gt boxes
        boxes_t = boxes[mask, :].copy()
        boxes_t[:, :2] = np.maximum(boxes_t[:, :2], rect[:2])
        boxes_t[:, :2] -= rect[:2]
        boxes_t[:, 2:4] = np.minimum(boxes_t[:, 2:4], rect[2:4])
        boxes_t[:, 2:4] -= rect[:2]

        return image_t, boxes_t
    return image, boxes

def ssd_bboxes_encode(boxes):
    """Labels anchors with ground truth inputs."""

    def jaccard_with_anchors(bbox):
        """Compute jaccard score a box and the anchors."""
        # Intersection bbox and volume.
        ymin = np.maximum(y1, bbox[0])
        xmin = np.maximum(x1, bbox[1])
        ymax = np.minimum(y2, bbox[2])
        xmax = np.minimum(x2, bbox[3])
        w = np.maximum(xmax - xmin, 0.)
        h = np.maximum(ymax - ymin, 0.)

        # Volumes.
        inter_vol = h * w
        union_vol = vol_anchors + (bbox[2] - bbox[0]) * (bbox[3] - bbox[1]) - inter_vol
        jaccard = inter_vol / union_vol
        return np.squeeze(jaccard)

    pre_scores = np.zeros((8732), dtype=np.float32)
    t_boxes = np.zeros((8732, 4), dtype=np.float32)
    t_label = np.zeros((8732), dtype=np.int64)
    for bbox in boxes:
        label = int(bbox[4])
        scores = jaccard_with_anchors(bbox)
        idx = np.argmax(scores)
        scores[idx] = 2.0
        mask = (scores > matching_threshold)
        mask = mask & (scores > pre_scores)
        pre_scores = np.maximum(pre_scores, scores * mask)
        t_label = mask * label + (1 - mask) * t_label
        for i in range(4):
            t_boxes[:, i] = mask * bbox[i] + (1 - mask) * t_boxes[:, i]

    index = np.nonzero(t_label)

    # Transform to tlbr.
    bboxes = np.zeros((8732, 4), dtype=np.float32)
    bboxes[:, [0, 1]] = (t_boxes[:, [0, 1]] + t_boxes[:, [2, 3]]) / 2
    bboxes[:, [2, 3]] = t_boxes[:, [2, 3]] - t_boxes[:, [0, 1]]

    # Encode features.
    bboxes_t = bboxes[index]
    default_boxes_t = default_boxes[index]
    bboxes_t[:, :2] = (bboxes_t[:, :2] - default_boxes_t[:, :2]) / (default_boxes_t[:, 2:] * 0.1)
    tmp = np.maximum(bboxes_t[:, 2:4] / default_boxes_t[:, 2:4], 0.000001)
    bboxes_t[:, 2:4] = np.log(tmp) / 0.2
    bboxes[index] = bboxes_t

    num_match = np.array([len(np.nonzero(t_label)[0])], dtype=np.int32)
    return bboxes, t_label.astype(np.int32), num_match

def preprocess_fn(img_id, image, box, is_training):
    """Preprocess function for dataset."""
    cv2.setNumThreads(2)

    def _infer_data(image, input_shape):
        img_h, img_w, _ = image.shape
        input_h, input_w = input_shape

        image = cv2.resize(image, (input_w, input_h))

        # When the channels of image is 1
        if len(image.shape) == 2:
            image = np.expand_dims(image, axis=-1)
            image = np.concatenate([image, image, image], axis=-1)

        return img_id, image, np.array((img_h, img_w), np.float32)

    def _data_aug(image, box, is_training, image_size=(300, 300)):
        ih, iw, _ = image.shape
        h, w = image_size
        if not is_training:
            return _infer_data(image, image_size)
        # Random crop
        box = box.astype(np.float32)
        image, box = random_sample_crop(image, box)
        ih, iw, _ = image.shape
        # Resize image
        image = cv2.resize(image, (w, h))
        # Flip image or not
        flip = _rand() < .5
        if flip:
            image = cv2.flip(image, 1, dst=None)
        # When the channels of image is 1
        if len(image.shape) == 2:
            image = np.expand_dims(image, axis=-1)
            image = np.concatenate([image, image, image], axis=-1)
        box[:, [0, 2]] = box[:, [0, 2]] / ih
        box[:, [1, 3]] = box[:, [1, 3]] / iw
        if flip:
            box[:, [1, 3]] = 1 - box[:, [3, 1]]
        box, label, num_match = ssd_bboxes_encode(box)
        return image, box, label, num_match

    return _data_aug(image, box, is_training, image_size=[300, 300])

数据集创建

from mindspore import Tensor
from mindspore.dataset import MindDataset
from mindspore.dataset.vision import Decode, HWC2CHW, Normalize, RandomColorAdjust


def create_ssd_dataset(mindrecord_file, batch_size=32, device_num=1, rank=0,
                       is_training=True, num_parallel_workers=1, use_multiprocessing=True):
    """Create SSD dataset with MindDataset."""
    dataset = MindDataset(mindrecord_file, columns_list=["img_id", "image", "annotation"], num_shards=device_num,
                          shard_id=rank, num_parallel_workers=num_parallel_workers, shuffle=is_training)

    decode = Decode()
    dataset = dataset.map(operations=decode, input_columns=["image"])

    change_swap_op = HWC2CHW()
    # Computed from random subset of ImageNet training images
    normalize_op = Normalize(mean=[0.485 * 255, 0.456 * 255, 0.406 * 255],
                             std=[0.229 * 255, 0.224 * 255, 0.225 * 255])
    color_adjust_op = RandomColorAdjust(brightness=0.4, contrast=0.4, saturation=0.4)
    compose_map_func = (lambda img_id, image, annotation: preprocess_fn(img_id, image, annotation, is_training))

    if is_training:
        output_columns = ["image", "box", "label", "num_match"]
        trans = [color_adjust_op, normalize_op, change_swap_op]
    else:
        output_columns = ["img_id", "image", "image_shape"]
        trans = [normalize_op, change_swap_op]

    dataset = dataset.map(operations=compose_map_func, input_columns=["img_id", "image", "annotation"],
                          output_columns=output_columns, python_multiprocessing=use_multiprocessing,
                          num_parallel_workers=num_parallel_workers)

    dataset = dataset.map(operations=trans, input_columns=["image"], python_multiprocessing=use_multiprocessing,
                          num_parallel_workers=num_parallel_workers)

    dataset = dataset.batch(batch_size, drop_remainder=True)
    return dataset

模型构建

from mindspore import nn

def _make_layer(channels):
    in_channels = channels[0]
    layers = []
    for out_channels in channels[1:]:
        layers.append(nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=3))
        layers.append(nn.ReLU())
        in_channels = out_channels
    return nn.SequentialCell(layers)

class Vgg16(nn.Cell):
    """VGG16 module."""

    def __init__(self):
        super(Vgg16, self).__init__()
        self.b1 = _make_layer([3, 64, 64])
        self.b2 = _make_layer([64, 128, 128])
        self.b3 = _make_layer([128, 256, 256, 256])
        self.b4 = _make_layer([256, 512, 512, 512])
        self.b5 = _make_layer([512, 512, 512, 512])

        self.m1 = nn.MaxPool2d(kernel_size=2, stride=2, pad_mode='SAME')
        self.m2 = nn.MaxPool2d(kernel_size=2, stride=2, pad_mode='SAME')
        self.m3 = nn.MaxPool2d(kernel_size=2, stride=2, pad_mode='SAME')
        self.m4 = nn.MaxPool2d(kernel_size=2, stride=2, pad_mode='SAME')
        self.m5 = nn.MaxPool2d(kernel_size=3, stride=1, pad_mode='SAME')

    def construct(self, x):
        # block1
        x = self.b1(x)
        x = self.m1(x)

        # block2
        x = self.b2(x)
        x = self.m2(x)

        # block3
        x = self.b3(x)
        x = self.m3(x)

        # block4
        x = self.b4(x)
        block4 = x
        x = self.m4(x)

        # block5
        x = self.b5(x)
        x = self.m5(x)

        return block4, x

import mindspore as ms
import mindspore.nn as nn
import mindspore.ops as ops

def _last_conv2d(in_channel, out_channel, kernel_size=3, stride=1, pad_mod='same', pad=0):
    in_channels = in_channel
    out_channels = in_channel
    depthwise_conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, pad_mode='same',
                               padding=pad, group=in_channels)
    conv = nn.Conv2d(in_channel, out_channel, kernel_size=1, stride=1, padding=0, pad_mode='same', has_bias=True)
    bn = nn.BatchNorm2d(in_channel, eps=1e-3, momentum=0.97,
                        gamma_init=1, beta_init=0, moving_mean_init=0, moving_var_init=1)

    return nn.SequentialCell([depthwise_conv, bn, nn.ReLU6(), conv])

class FlattenConcat(nn.Cell):
    """FlattenConcat module."""

    def __init__(self):
        super(FlattenConcat, self).__init__()
        self.num_ssd_boxes = 8732

    def construct(self, inputs):
        output = ()
        batch_size = ops.shape(inputs[0])[0]
        for x in inputs:
            x = ops.transpose(x, (0, 2, 3, 1))
            output += (ops.reshape(x, (batch_size, -1)),)
        res = ops.concat(output, axis=1)
        return ops.reshape(res, (batch_size, self.num_ssd_boxes, -1))

class MultiBox(nn.Cell):
    """
    Multibox conv layers. Each multibox layer contains class conf scores and localization predictions.
    """

    def __init__(self):
        super(MultiBox, self).__init__()
        num_classes = 81
        out_channels = [512, 1024, 512, 256, 256, 256]
        num_default = [4, 6, 6, 6, 4, 4]

        loc_layers = []
        cls_layers = []
        for k, out_channel in enumerate(out_channels):
            loc_layers += [_last_conv2d(out_channel, 4 * num_default[k],
                                        kernel_size=3, stride=1, pad_mod='same', pad=0)]
            cls_layers += [_last_conv2d(out_channel, num_classes * num_default[k],
                                        kernel_size=3, stride=1, pad_mod='same', pad=0)]

        self.multi_loc_layers = nn.CellList(loc_layers)
        self.multi_cls_layers = nn.CellList(cls_layers)
        self.flatten_concat = FlattenConcat()

    def construct(self, inputs):
        loc_outputs = ()
        cls_outputs = ()
        for i in range(len(self.multi_loc_layers)):
            loc_outputs += (self.multi_loc_layers[i](inputs[i]),)
            cls_outputs += (self.multi_cls_layers[i](inputs[i]),)
        return self.flatten_concat(loc_outputs), self.flatten_concat(cls_outputs)

class SSD300Vgg16(nn.Cell):
    """SSD300Vgg16 module."""

    def __init__(self):
        super(SSD300Vgg16, self).__init__()

        # VGG16 backbone: block1~5
        self.backbone = Vgg16()

        # SSD blocks: block6~7
        self.b6_1 = nn.Conv2d(in_channels=512, out_channels=1024, kernel_size=3, padding=6, dilation=6, pad_mode='pad')
        self.b6_2 = nn.Dropout(p=0.5)

        self.b7_1 = nn.Conv2d(in_channels=1024, out_channels=1024, kernel_size=1)
        self.b7_2 = nn.Dropout(p=0.5)

        # Extra Feature Layers: block8~11
        self.b8_1 = nn.Conv2d(in_channels=1024, out_channels=256, kernel_size=1, padding=1, pad_mode='pad')
        self.b8_2 = nn.Conv2d(in_channels=256, out_channels=512, kernel_size=3, stride=2, pad_mode='valid')

        self.b9_1 = nn.Conv2d(in_channels=512, out_channels=128, kernel_size=1, padding=1, pad_mode='pad')
        self.b9_2 = nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, stride=2, pad_mode='valid')

        self.b10_1 = nn.Conv2d(in_channels=256, out_channels=128, kernel_size=1)
        self.b10_2 = nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, pad_mode='valid')

        self.b11_1 = nn.Conv2d(in_channels=256, out_channels=128, kernel_size=1)
        self.b11_2 = nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, pad_mode='valid')

        # boxes
        self.multi_box = MultiBox()

    def construct(self, x):
        # VGG16 backbone: block1~5
        block4, x = self.backbone(x)

        # SSD blocks: block6~7
        x = self.b6_1(x)  # 1024
        x = self.b6_2(x)

        x = self.b7_1(x)  # 1024
        x = self.b7_2(x)
        block7 = x

        # Extra Feature Layers: block8~11
        x = self.b8_1(x)  # 256
        x = self.b8_2(x)  # 512
        block8 = x

        x = self.b9_1(x)  # 128
        x = self.b9_2(x)  # 256
        block9 = x

        x = self.b10_1(x)  # 128
        x = self.b10_2(x)  # 256
        block10 = x

        x = self.b11_1(x)  # 128
        x = self.b11_2(x)  # 256
        block11 = x

        # boxes
        multi_feature = (block4, block7, block8, block9, block10, block11)
        pred_loc, pred_label = self.multi_box(multi_feature)
        if not self.training:
            pred_label = ops.sigmoid(pred_label)
        pred_loc = pred_loc.astype(ms.float32)
        pred_label = pred_label.astype(ms.float32)
        return pred_loc, pred_label

损失函数

SSD算法的目标函数分为两部分：计算相应的预选框与目标类别的置信度误差（confidence loss, conf）以及相应的位置误差（locatization loss， loc）：

其中：
N 是先验框的正样本数量；
c 为类别置信度预测值;
l 为先验框的所对应边界框的位置预测值;
g 为ground truth的位置参数
α 用以调整confidence loss和location loss之间的比例，默认为1。

def class_loss(logits, label):
    """Calculate category losses."""
    label = ops.one_hot(label, ops.shape(logits)[-1], Tensor(1.0, ms.float32), Tensor(0.0, ms.float32))
    weight = ops.ones_like(logits)
    pos_weight = ops.ones_like(logits)
    sigmiod_cross_entropy = ops.binary_cross_entropy_with_logits(logits, label, weight.astype(ms.float32), pos_weight.astype(ms.float32))
    sigmoid = ops.sigmoid(logits)
    label = label.astype(ms.float32)
    p_t = label * sigmoid + (1 - label) * (1 - sigmoid)
    modulating_factor = ops.pow(1 - p_t, 2.0)
    alpha_weight_factor = label * 0.75 + (1 - label) * (1 - 0.75)
    focal_loss = modulating_factor * alpha_weight_factor * sigmiod_cross_entropy
    return focal_loss

Metrics

在SSD中，训练过程是不需要用到非极大值抑制(NMS)，但当进行检测时，例如输入一张图片要求输出框的时候，需要用到NMS过滤掉那些重叠度较大的预测框。
非极大值抑制的流程如下：

1. 根据置信度得分进行排序

2. 选择置信度最高的比边界框添加到最终输出列表中，将其从边界框列表中删除

3. 计算所有边界框的面积

4. 计算置信度最高的边界框与其它候选框的IoU

5. 删除IoU大于阈值的边界框

6. 重复上述过程，直至边界框列表为空

7. import json
   from pycocotools.coco import COCO
   from pycocotools.cocoeval import COCOeval
   
   
   def apply_eval(eval_param_dict):
       net = eval_param_dict["net"]
       net.set_train(False)
       ds = eval_param_dict["dataset"]
       anno_json = eval_param_dict["anno_json"]
       coco_metrics = COCOMetrics(anno_json=anno_json,
                                  classes=train_cls,
                                  num_classes=81,
                                  max_boxes=100,
                                  nms_threshold=0.6,
                                  min_score=0.1)
       for data in ds.create_dict_iterator(output_numpy=True, num_epochs=1):
           img_id = data['img_id']
           img_np = data['image']
           image_shape = data['image_shape']
   
           output = net(Tensor(img_np))
   
           for batch_idx in range(img_np.shape[0]):
               pred_batch = {
                   "boxes": output[0].asnumpy()[batch_idx],
                   "box_scores": output[1].asnumpy()[batch_idx],
                   "img_id": int(np.squeeze(img_id[batch_idx])),
                   "image_shape": image_shape[batch_idx]
               }
               coco_metrics.update(pred_batch)
       eval_metrics = coco_metrics.get_metrics()
       return eval_metrics
   
   
   def apply_nms(all_boxes, all_scores, thres, max_boxes):
       """Apply NMS to bboxes."""
       y1 = all_boxes[:, 0]
       x1 = all_boxes[:, 1]
       y2 = all_boxes[:, 2]
       x2 = all_boxes[:, 3]
       areas = (x2 - x1 + 1) * (y2 - y1 + 1)
   
       order = all_scores.argsort()[::-1]
       keep = []
   
       while order.size > 0:
           i = order[0]
           keep.append(i)
   
           if len(keep) >= max_boxes:
               break
   
           xx1 = np.maximum(x1[i], x1[order[1:]])
           yy1 = np.maximum(y1[i], y1[order[1:]])
           xx2 = np.minimum(x2[i], x2[order[1:]])
           yy2 = np.minimum(y2[i], y2[order[1:]])
   
           w = np.maximum(0.0, xx2 - xx1 + 1)
           h = np.maximum(0.0, yy2 - yy1 + 1)
           inter = w * h
   
           ovr = inter / (areas[i] + areas[order[1:]] - inter)
   
           inds = np.where(ovr <= thres)[0]
   
           order = order[inds + 1]
       return keep
   
   
   class COCOMetrics:
       """Calculate mAP of predicted bboxes."""
   
       def __init__(self, anno_json, classes, num_classes, min_score, nms_threshold, max_boxes):
           self.num_classes = num_classes
           self.classes = classes
           self.min_score = min_score
           self.nms_threshold = nms_threshold
           self.max_boxes = max_boxes
   
           self.val_cls_dict = {i: cls for i, cls in enumerate(classes)}
           self.coco_gt = COCO(anno_json)
           cat_ids = self.coco_gt.loadCats(self.coco_gt.getCatIds())
           self.class_dict = {cat['name']: cat['id'] for cat in cat_ids}
   
           self.predictions = []
           self.img_ids = []
   
       def update(self, batch):
           pred_boxes = batch['boxes']
           box_scores = batch['box_scores']
           img_id = batch['img_id']
           h, w = batch['image_shape']
   
           final_boxes = []
           final_label = []
           final_score = []
           self.img_ids.append(img_id)
   
           for c in range(1, self.num_classes):
               class_box_scores = box_scores[:, c]
               score_mask = class_box_scores > self.min_score
               class_box_scores = class_box_scores[score_mask]
               class_boxes = pred_boxes[score_mask] * [h, w, h, w]
   
               if score_mask.any():
                   nms_index = apply_nms(class_boxes, class_box_scores, self.nms_threshold, self.max_boxes)
                   class_boxes = class_boxes[nms_index]
                   class_box_scores = class_box_scores[nms_index]
   
                   final_boxes += class_boxes.tolist()
                   final_score += class_box_scores.tolist()
                   final_label += [self.class_dict[self.val_cls_dict[c]]] * len(class_box_scores)
   
           for loc, label, score in zip(final_boxes, final_label, final_score):
               res = {}
               res['image_id'] = img_id
               res['bbox'] = [loc[1], loc[0], loc[3] - loc[1], loc[2] - loc[0]]
               res['score'] = score
               res['category_id'] = label
               self.predictions.append(res)
   
       def get_metrics(self):
           with open('predictions.json', 'w') as f:
               json.dump(self.predictions, f)
   
           coco_dt = self.coco_gt.loadRes('predictions.json')
           E = COCOeval(self.coco_gt, coco_dt, iouType='bbox')
           E.params.imgIds = self.img_ids
           E.evaluate()
           E.accumulate()
           E.summarize()
           return E.stats[0]
   
   
   class SsdInferWithDecoder(nn.Cell):
       """
   SSD Infer wrapper to decode the bbox locations."""
   
       def __init__(self, network, default_boxes, ckpt_path):
           super(SsdInferWithDecoder, self).__init__()
           param_dict = ms.load_checkpoint(ckpt_path)
           ms.load_param_into_net(network, param_dict)
           self.network = network
           self.default_boxes = default_boxes
           self.prior_scaling_xy = 0.1
           self.prior_scaling_wh = 0.2
   
       def construct(self, x):
           pred_loc, pred_label = self.network(x)
   
           default_bbox_xy = self.default_boxes[..., :2]
           default_bbox_wh = self.default_boxes[..., 2:]
           pred_xy = pred_loc[..., :2] * self.prior_scaling_xy * default_bbox_wh + default_bbox_xy
           pred_wh = ops.exp(pred_loc[..., 2:] * self.prior_scaling_wh) * default_bbox_wh
   
           pred_xy_0 = pred_xy - pred_wh / 2.0
           pred_xy_1 = pred_xy + pred_wh / 2.0
           pred_xy = ops.concat((pred_xy_0, pred_xy_1), -1)
           pred_xy = ops.maximum(pred_xy, 0)
           pred_xy = ops.minimum(pred_xy, 1)
           return pred_xy, pred_label