update 11 object detection modules. (#555)

* update 11 object detection modules.

hub_module/modules/image/object_detection/faster_rcnn/module.py

-# coding=utf-8
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
-from collections import OrderedDict
-
-import paddle.fluid as fluid
-import paddlehub as hub
-from paddlehub.module.module import moduleinfo
-from paddlehub.common.paddle_helper import add_vars_prefix
-
-from faster_rcnn.data_feed import test_reader, padding_minibatch
-from faster_rcnn.processor import load_label_info, postprocess
-from faster_rcnn.bbox_head import MultiClassNMS, BBoxHead, SmoothL1Loss, TwoFCHead
-from faster_rcnn.rpn_head import AnchorGenerator, RPNTargetAssign, GenerateProposals, RPNHead, FPNRPNHead
-from faster_rcnn.bbox_assigner import BBoxAssigner
-from faster_rcnn.roi_extractor import RoIAlign, FPNRoIAlign
-
-
-@moduleinfo(
-    name="faster_rcnn",
-    version="1.0.0",
-    type="cv/object_detection",
-    summary="Baidu's Faster R-CNN model for object detection.",
-    author="paddlepaddle",
-    author_email="paddle-dev@baidu.com")
-class FasterRCNNBase(hub.Module):
-    def _initialize(self):
-        # data_feed
-        self.test_reader = test_reader
-        self.padding_minibatch = padding_minibatch
-        # processor
-        self.load_label_info = load_label_info
-        self.postprocess = postprocess
-        # bbox_head
-        self.MultiClassNMS = MultiClassNMS
-        self.TwoFCHead = TwoFCHead
-        self.BBoxHead = BBoxHead
-        self.SmoothL1Loss = SmoothL1Loss
-        # rpn_head
-        self.AnchorGenerator = AnchorGenerator
-        self.RPNTargetAssign = RPNTargetAssign
-        self.GenerateProposals = GenerateProposals
-        self.RPNHead = RPNHead
-        self.FPNRPNHead = FPNRPNHead
-        # bbox_assigner
-        self.BBoxAssigner = BBoxAssigner
-        # roi_extractor
-        self.RoIAlign = RoIAlign
-        self.FPNRoIAlign = FPNRoIAlign
-
-    def context(self, body_feats, fpn, rpn_head, roi_extractor, bbox_head,
-                bbox_assigner, image, trainable, var_prefix, phase):
-        """Distill the Head Features, so as to perform transfer learning.
-
-        :param body_feats: feature map of image classification to distill feature map.
-        :type body_feats: list
-        :param fpn: Feature Pyramid Network.
-        :type fpn: <class 'FPN' object>
-        :param rpn_head: Head of Region Proposal Network.
-        :type rpn_head: <class 'RPNHead' object> or  <class 'FPNRPNHead' object>
-        :param roi_extractor:
-        :type roi_extractor:
-        :param bbox_head: Head of Bounding Box.
-        :type bbox_head: <class 'BBoxHead' object>
-        :param bbox_assigner: Parameters of fluid.layers.generate_proposal_labels.
-        :type bbox_assigner: <class 'BBoxAssigner' object>
-        :param image: image tensor.
-        :type image: <class 'paddle.fluid.framework.Variable'>
-        :param trainable: whether to set parameters trainable.
-        :type trainable: bool
-        :param var_prefix: the prefix of variables in faster_rcnn
-        :type var_prefix: str
-        :param phase: Optional Choice: 'predict', 'train'
-        :type phase: str
-        """
-        context_prog = image.block.program
-        with fluid.program_guard(context_prog):
-            im_info = fluid.layers.data(
-                name='im_info', shape=[3], dtype='float32', lod_level=0)
-            im_shape = fluid.layers.data(
-                name='im_shape', shape=[3], dtype='float32', lod_level=0)
-            #body_feats = backbone(image)
-            body_feat_names = list(body_feats.keys())
-            # fpn
-            if fpn is not None:
-                body_feats, spatial_scale = fpn.get_output(body_feats)
-            # rpn_head: RPNHead
-            rois = rpn_head.get_proposals(body_feats, im_info, mode=phase)
-            # train
-            if phase == 'train':
-                gt_bbox = fluid.layers.data(
-                    name='gt_bbox', shape=[4], dtype='float32', lod_level=1)
-                is_crowd = fluid.layers.data(
-                    name='is_crowd', shape=[1], dtype='int32', lod_level=1)
-                gt_class = fluid.layers.data(
-                    name='gt_class', shape=[1], dtype='int32', lod_level=1)
-                rpn_loss = rpn_head.get_loss(im_info, gt_bbox, is_crowd)
-                # bbox_assigner: BBoxAssigner
-                outs = fluid.layers.generate_proposal_labels(
-                    rpn_rois=rois,
-                    gt_classes=gt_class,
-                    is_crowd=is_crowd,
-                    gt_boxes=gt_bbox,
-                    im_info=im_info,
-                    batch_size_per_im=bbox_assigner.batch_size_per_im,
-                    fg_fraction=bbox_assigner.fg_fraction,
-                    fg_thresh=bbox_assigner.fg_thresh,
-                    bg_thresh_hi=bbox_assigner.bg_thresh_hi,
-                    bg_thresh_lo=bbox_assigner.bg_thresh_lo,
-                    bbox_reg_weights=bbox_assigner.bbox_reg_weights,
-                    class_nums=bbox_assigner.class_nums,
-                    use_random=bbox_assigner.use_random)
-                rois = outs[0]
-            if fpn is None:
-                body_feat = body_feats[body_feat_names[-1]]
-                # roi_extractor: RoIAlign
-                roi_feat = fluid.layers.roi_align(
-                    input=body_feat,
-                    rois=rois,
-                    pooled_height=roi_extractor.pooled_height,
-                    pooled_width=roi_extractor.pooled_width,
-                    spatial_scale=roi_extractor.spatial_scale,
-                    sampling_ratio=roi_extractor.sampling_ratio)
-            else:
-                # roi_extractor: FPNRoIAlign
-                roi_feat = roi_extractor(
-                    head_inputs=body_feats,
-                    rois=rois,
-                    spatial_scale=spatial_scale)
-            # head_feat
-            head_feat = bbox_head.head(roi_feat)
-            if isinstance(head_feat, OrderedDict):
-                head_feat = list(head_feat.values())[0]
-            if phase == 'train':
-                inputs = {
-                    'image': var_prefix + image.name,
-                    'im_info': var_prefix + im_info.name,
-                    'im_shape': var_prefix + im_shape.name,
-                    'gt_class': var_prefix + gt_class.name,
-                    'gt_bbox': var_prefix + gt_bbox.name,
-                    'is_crowd': var_prefix + is_crowd.name
-                }
-                outputs = {
-                    'head_feat':
-                    var_prefix + head_feat.name,
-                    'rpn_cls_loss':
-                    var_prefix + rpn_loss['rpn_cls_loss'].name,
-                    'rpn_reg_loss':
-                    var_prefix + rpn_loss['rpn_reg_loss'].name,
-                    'generate_proposal_labels':
-                    [var_prefix + var.name for var in outs]
-                }
-            elif phase == 'predict':
-                pred = bbox_head.get_prediction(roi_feat, rois, im_info,
-                                                im_shape)
-                inputs = {
-                    'image': var_prefix + image.name,
-                    'im_info': var_prefix + im_info.name,
-                    'im_shape': var_prefix + im_shape.name
-                }
-                outputs = {
-                    'head_feat': var_prefix + head_feat.name,
-                    'rois': var_prefix + rois.name,
-                    'bbox_out': var_prefix + pred.name
-                }
-            add_vars_prefix(context_prog, var_prefix)
-            add_vars_prefix(fluid.default_startup_program(), var_prefix)
-
-            global_vars = context_prog.global_block().vars
-            inputs = {key: global_vars[value] for key, value in inputs.items()}
-            outputs = {
-                key: global_vars[value] if not isinstance(value, list) else
-                [global_vars[var] for var in value]
-                for key, value in outputs.items()
-            }
-            place = fluid.CPUPlace()
-            exe = fluid.Executor(place)
-            for param in context_prog.global_block().iter_parameters():
-                param.trainable = trainable
-            return inputs, outputs, context_prog

hub_module/modules/image/object_detection/faster_rcnn_resnet50_coco2017/README.md

+```shell
+$ hub install faster_rcnn_resnet50_coco2017==1.1.0
+```
+
+## 命令行预测
+
+```
+hub run faster_rcnn_resnet50_coco2017 --input_path "/PATH/TO/IMAGE"
+```
+
+## API
+
+```
+def context(num_classes=81,
+            trainable=True,
+            pretrained=True,
+            phase='train')
+```
+
+提取头部特征，用于迁移学习。
+
+**参数**
+
+* num\_classes (int): 类别数；
+* trainable(bool): 将参数的trainable 属性设为trainable；
+* pretrained (bool): 是否加载预训练模型；
+* phase (str): 可选值为 'train'/'predict'，'trian' 用于训练，'predict' 用于预测。
+
+**返回**
+
+* inputs (dict): 模型的输入，keys 包括 'image', 'im\_size'，相应的取值为：
+    * image (Variable): 图像变量
+    * im\_size (Variable): 图片的尺寸
+* outputs (dict): 模型的输出。如果 get\_prediction 为 False，输出 'head\_fatures'，否则输出 'bbox\_out'。
+* context\_prog (Program): 用于迁移学习的 Program。
+
+```python
+def object_detection(paths=None,
+                     images=None,
+                     batch_size=1,
+                     use_gpu=False,
+                     output_dir='detection_result',
+                     score_thresh=0.5,
+                     visualization=True)
+```
+
+预测API，检测输入图片中的所有目标的位置。
+
+**参数**
+
+* paths (list\[str\]): 图片的路径；
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，BGR格式；
+* batch\_size (int): batch 的大小；
+* use\_gpu (bool): 是否使用 GPU；
+* score\_thresh (float): 识别置信度的阈值；
+* visualization (bool): 是否将识别结果保存为图片文件；
+* output\_dir (str): 图片的保存路径，默认设为 detection\_result；
+
+**返回**
+
+* res (list\[dict\]): 识别结果的列表，列表中每一个元素为 dict，各字段为：
+    * data (list): 检测结果，list的每一个元素为 dict，各字段为:
+        * confidence (float): 识别的置信度；
+        * label (str): 标签；
+        * left (int): 边界框的左上角x坐标；
+        * top (int): 边界框的左上角y坐标；
+        * right (int): 边界框的右下角x坐标；
+        * bottom (int): 边界框的右下角y坐标；
+    * save\_path (str, optional): 识别结果的保存路径 (仅当visualization=True时存在)。
+
+```python
+def save_inference_model(dirname,
+                         model_filename=None,
+                         params_filename=None,
+                         combined=True)
+```
+
+将模型保存到指定路径。
+
+**参数**
+
+* dirname: 存在模型的目录名称
+* model\_filename: 模型文件名称，默认为\_\_model\_\_
+* params\_filename: 参数文件名称，默认为\_\_params\_\_(仅当`combined`为True时生效)
+* combined: 是否将参数保存到统一的一个文件中
+
+## 代码示例
+
+```python
+import paddlehub as hub
+import cv2
+
+object_detector = hub.Module(name="faster_rcnn_resnet50_coco2017")
+result = object_detector.object_detection(images=[cv2.imread('/PATH/TO/IMAGE')])
+# or
+# result = object_detector.object_detection((paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving 可以部署一个目标检测的在线服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m faster_rcnn_resnet50_coco2017
+```
+
+这样就完成了一个目标检测的服务化API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/faster_rcnn_resnet50_coco2017"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+### 依赖
+
+paddlepaddle >= 1.6.2
+
+paddlehub >= 1.6.0

hub_module/modules/image/object_detection/faster_rcnn_resnet50_coco2017/bbox_assigner.py

+class BBoxAssigner(object):
+    def __init__(self,
+                 batch_size_per_im=512,
+                 fg_fraction=.25,
+                 fg_thresh=.5,
+                 bg_thresh_hi=.5,
+                 bg_thresh_lo=0.,
+                 bbox_reg_weights=[0.1, 0.1, 0.2, 0.2],
+                 class_nums=81,
+                 shuffle_before_sample=True):
+        super(BBoxAssigner, self).__init__()
+        self.batch_size_per_im = batch_size_per_im
+        self.fg_fraction = fg_fraction
+        self.fg_thresh = fg_thresh
+        self.bg_thresh_hi = bg_thresh_hi
+        self.bg_thresh_lo = bg_thresh_lo
+        self.bbox_reg_weights = bbox_reg_weights
+        self.class_nums = class_nums
+        self.use_random = shuffle_before_sample

hub_module/modules/image/object_detection/faster_rcnn_resnet50_coco2017/bbox_head.py

+# coding=utf-8
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from collections import OrderedDict
+
+from paddle import fluid
+from paddle.fluid.param_attr import ParamAttr
+from paddle.fluid.initializer import Normal, Xavier
+from paddle.fluid.regularizer import L2Decay
+from paddle.fluid.initializer import MSRA
+
+
+class MultiClassNMS(object):
+    # __op__ = fluid.layers.multiclass_nms
+    def __init__(self,
+                 score_threshold=.05,
+                 nms_top_k=-1,
+                 keep_top_k=100,
+                 nms_threshold=.5,
+                 normalized=False,
+                 nms_eta=1.0,
+                 background_label=0):
+        super(MultiClassNMS, self).__init__()
+        self.score_threshold = score_threshold
+        self.nms_top_k = nms_top_k
+        self.keep_top_k = keep_top_k
+        self.nms_threshold = nms_threshold
+        self.normalized = normalized
+        self.nms_eta = nms_eta
+        self.background_label = background_label
+
+
+class SmoothL1Loss(object):
+    '''
+    Smooth L1 loss
+    Args:
+        sigma (float): hyper param in smooth l1 loss
+    '''
+
+    def __init__(self, sigma=1.0):
+        super(SmoothL1Loss, self).__init__()
+        self.sigma = sigma
+
+    def __call__(self, x, y, inside_weight=None, outside_weight=None):
+        return fluid.layers.smooth_l1(
+            x,
+            y,
+            inside_weight=inside_weight,
+            outside_weight=outside_weight,
+            sigma=self.sigma)
+
+
+class BoxCoder(object):
+    def __init__(self,
+                 prior_box_var=[0.1, 0.1, 0.2, 0.2],
+                 code_type='decode_center_size',
+                 box_normalized=False,
+                 axis=1):
+        super(BoxCoder, self).__init__()
+        self.prior_box_var = prior_box_var
+        self.code_type = code_type
+        self.box_normalized = box_normalized
+        self.axis = axis
+
+
+class TwoFCHead(object):
+    """
+    RCNN head with two Fully Connected layers
+    Args:
+        mlp_dim (int): num of filters for the fc layers
+    """
+
+    def __init__(self, mlp_dim=1024):
+        super(TwoFCHead, self).__init__()
+        self.mlp_dim = mlp_dim
+
+    def __call__(self, roi_feat):
+        fan = roi_feat.shape[1] * roi_feat.shape[2] * roi_feat.shape[3]
+
+        fc6 = fluid.layers.fc(
+            input=roi_feat,
+            size=self.mlp_dim,
+            act='relu',
+            name='fc6',
+            param_attr=ParamAttr(name='fc6_w', initializer=Xavier(fan_out=fan)),
+            bias_attr=ParamAttr(
+                name='fc6_b', learning_rate=2., regularizer=L2Decay(0.)))
+        head_feat = fluid.layers.fc(
+            input=fc6,
+            size=self.mlp_dim,
+            act='relu',
+            name='fc7',
+            param_attr=ParamAttr(name='fc7_w', initializer=Xavier()),
+            bias_attr=ParamAttr(
+                name='fc7_b', learning_rate=2., regularizer=L2Decay(0.)))
+
+        return head_feat
+
+
+class BBoxHead(object):
+    """
+    RCNN bbox head
+
+    Args:
+        head (object): the head module instance, e.g., `ResNetC5`, `TwoFCHead`
+        box_coder (object): `BoxCoder` instance
+        nms (object): `MultiClassNMS` instance
+        num_classes: number of output classes
+    """
+    __inject__ = ['head', 'box_coder', 'nms', 'bbox_loss']
+    __shared__ = ['num_classes']
+
+    def __init__(self,
+                 head,
+                 box_coder=BoxCoder(),
+                 nms=MultiClassNMS(),
+                 bbox_loss=SmoothL1Loss(),
+                 num_classes=81):
+        super(BBoxHead, self).__init__()
+        self.head = head
+        self.num_classes = num_classes
+        self.box_coder = box_coder
+        self.nms = nms
+        self.bbox_loss = bbox_loss
+        self.head_feat = None
+
+    def get_head_feat(self, input=None):
+        """
+        Get the bbox head feature map.
+        """
+
+        if input is not None:
+            feat = self.head(input)
+            if isinstance(feat, OrderedDict):
+                feat = list(feat.values())[0]
+            self.head_feat = feat
+        return self.head_feat
+
+    def _get_output(self, roi_feat):
+        """
+        Get bbox head output.
+
+        Args:
+            roi_feat (Variable): RoI feature from RoIExtractor.
+
+        Returns:
+            cls_score(Variable): Output of rpn head with shape of
+                [N, num_anchors, H, W].
+            bbox_pred(Variable): Output of rpn head with shape of
+                [N, num_anchors * 4, H, W].
+        """
+        head_feat = self.get_head_feat(roi_feat)
+        # when ResNetC5 output a single feature map
+        if not isinstance(self.head, TwoFCHead):
+            head_feat = fluid.layers.pool2d(
+                head_feat, pool_type='avg', global_pooling=True)
+        cls_score = fluid.layers.fc(
+            input=head_feat,
+            size=self.num_classes,
+            act=None,
+            name='cls_score',
+            param_attr=ParamAttr(
+                name='cls_score_w', initializer=Normal(loc=0.0, scale=0.01)),
+            bias_attr=ParamAttr(
+                name='cls_score_b', learning_rate=2., regularizer=L2Decay(0.)))
+        bbox_pred = fluid.layers.fc(
+            input=head_feat,
+            size=4 * self.num_classes,
+            act=None,
+            name='bbox_pred',
+            param_attr=ParamAttr(
+                name='bbox_pred_w', initializer=Normal(loc=0.0, scale=0.001)),
+            bias_attr=ParamAttr(
+                name='bbox_pred_b', learning_rate=2., regularizer=L2Decay(0.)))
+        return cls_score, bbox_pred
+
+    def get_loss(self, roi_feat, labels_int32, bbox_targets,
+                 bbox_inside_weights, bbox_outside_weights):
+        """
+        Get bbox_head loss.
+
+        Args:
+            roi_feat (Variable): RoI feature from RoIExtractor.
+            labels_int32(Variable): Class label of a RoI with shape [P, 1].
+                P is the number of RoI.
+            bbox_targets(Variable): Box label of a RoI with shape
+                [P, 4 * class_nums].
+            bbox_inside_weights(Variable): Indicates whether a box should
+                contribute to loss. Same shape as bbox_targets.
+            bbox_outside_weights(Variable): Indicates whether a box should
+                contribute to loss. Same shape as bbox_targets.
+
+        Return:
+            Type: Dict
+                loss_cls(Variable): bbox_head loss.
+                loss_bbox(Variable): bbox_head loss.
+        """
+
+        cls_score, bbox_pred = self._get_output(roi_feat)
+
+        labels_int64 = fluid.layers.cast(x=labels_int32, dtype='int64')
+        labels_int64.stop_gradient = True
+        loss_cls = fluid.layers.softmax_with_cross_entropy(
+            logits=cls_score, label=labels_int64, numeric_stable_mode=True)
+        loss_cls = fluid.layers.reduce_mean(loss_cls)
+        loss_bbox = self.bbox_loss(
+            x=bbox_pred,
+            y=bbox_targets,
+            inside_weight=bbox_inside_weights,
+            outside_weight=bbox_outside_weights)
+        loss_bbox = fluid.layers.reduce_mean(loss_bbox)
+        return {'loss_cls': loss_cls, 'loss_bbox': loss_bbox}
+
+    def get_prediction(self,
+                       roi_feat,
+                       rois,
+                       im_info,
+                       im_shape,
+                       return_box_score=False):
+        """
+        Get prediction bounding box in test stage.
+
+        Args:
+            roi_feat (Variable): RoI feature from RoIExtractor.
+            rois (Variable): Output of generate_proposals in rpn head.
+            im_info (Variable): A 2-D LoDTensor with shape [B, 3]. B is the
+                number of input images, each element consists of im_height,
+                im_width, im_scale.
+            im_shape (Variable): Actual shape of original image with shape
+                [B, 3]. B is the number of images, each element consists of
+                original_height, original_width, 1
+
+        Returns:
+            pred_result(Variable): Prediction result with shape [N, 6]. Each
+                row has 6 values: [label, confidence, xmin, ymin, xmax, ymax].
+                N is the total number of prediction.
+        """
+        cls_score, bbox_pred = self._get_output(roi_feat)
+
+        im_scale = fluid.layers.slice(im_info, [1], starts=[2], ends=[3])
+        im_scale = fluid.layers.sequence_expand(im_scale, rois)
+        boxes = rois / im_scale
+        cls_prob = fluid.layers.softmax(cls_score, use_cudnn=False)
+        bbox_pred = fluid.layers.reshape(bbox_pred, (-1, self.num_classes, 4))
+        # self.box_coder
+        decoded_box = fluid.layers.box_coder(
+            prior_box=boxes,
+            target_box=bbox_pred,
+            prior_box_var=self.box_coder.prior_box_var,
+            code_type=self.box_coder.code_type,
+            box_normalized=self.box_coder.box_normalized,
+            axis=self.box_coder.axis)
+        cliped_box = fluid.layers.box_clip(input=decoded_box, im_info=im_shape)
+        if return_box_score:
+            return {'bbox': cliped_box, 'score': cls_prob}
+        # self.nms
+        pred_result = fluid.layers.multiclass_nms(
+            bboxes=cliped_box,
+            scores=cls_prob,
+            score_threshold=self.nms.score_threshold,
+            nms_top_k=self.nms.nms_top_k,
+            keep_top_k=self.nms.keep_top_k,
+            nms_threshold=self.nms.nms_threshold,
+            normalized=self.nms.normalized,
+            nms_eta=self.nms.nms_eta,
+            background_label=self.nms.background_label)
+        return pred_result

hub_module/modules/image/object_detection/faster_rcnn/data_feed.py → hub_module/modules/image/object_detection/faster_rcnn_resnet50_coco2017/data_feed.py

@@ -15,14 +15,19 @@ __all__ = ['test_reader']
 
 
 def test_reader(paths=None, images=None):
-    """data generator
+    """
+    data generator
+
+    Args:
+        paths (list[str]): paths to images.
+        images (list(numpy.ndarray)): data of images, shape of each is [H, W, C]
 
-    :param paths: path to images.
-    :type paths: list, each element is a str
-    :param images: data of images, [N, H, W, C]
-    :type images: numpy.ndarray
+    Yield:
+        res (dict): key contains 'image' and 'im_info', the corresponding values is:
+            image (numpy.ndarray): the image to be fed into network
+            im_info (numpy.ndarray): the info about the preprocessed.
     """
-    img_list = []
+    img_list = list()
     if paths:
         for img_path in paths:
             assert os.path.isfile(
@@ -87,9 +92,9 @@ def padding_minibatch(batch_data, coarsest_stride=0, use_padded_im_info=True):
     else:
         max_shape = max_shape_org.astype('int32')
 
-    padding_image = []
-    padding_info = []
-    padding_shape = []
+    padding_image = list()
+    padding_info = list()
+    padding_shape = list()
 
     for data in batch_data:
         im_c, im_h, im_w = data['image'].shape

hub_module/modules/image/object_detection/faster_rcnn_resnet50_coco2017/module.py

@@ -13,11 +13,18 @@ from math import ceil
 import numpy as np
 import paddle.fluid as fluid
 import paddlehub as hub
-from paddlehub.module.module import moduleinfo, runnable
+from paddlehub.module.module import moduleinfo, runnable, serving
 from paddle.fluid.core import PaddleTensor, AnalysisConfig, create_paddle_predictor
 from paddlehub.io.parser import txt_parser
+from paddlehub.common.paddle_helper import add_vars_prefix
 
+from faster_rcnn_resnet50_coco2017.processor import load_label_info, postprocess, base64_to_cv2
+from faster_rcnn_resnet50_coco2017.data_feed import test_reader, padding_minibatch
 from faster_rcnn_resnet50_coco2017.resnet import ResNet, ResNetC5
+from faster_rcnn_resnet50_coco2017.rpn_head import AnchorGenerator, RPNTargetAssign, GenerateProposals, RPNHead
+from faster_rcnn_resnet50_coco2017.bbox_head import MultiClassNMS, BBoxHead, SmoothL1Loss
+from faster_rcnn_resnet50_coco2017.bbox_assigner import BBoxAssigner
+from faster_rcnn_resnet50_coco2017.roi_extractor import RoIAlign
 
 
 @moduleinfo(
@@ -27,17 +34,14 @@ from faster_rcnn_resnet50_coco2017.resnet import ResNet, ResNetC5
     summary=
     "Baidu's Faster R-CNN model for object detection with backbone ResNet50, trained with dataset COCO2017",
     author="paddlepaddle",
-    author_email="paddle-dev@baidu.com")
+    author_email="")
 class FasterRCNNResNet50(hub.Module):
     def _initialize(self):
-        self.faster_rcnn = hub.Module(name="faster_rcnn")
         # default pretrained model, Faster-RCNN with backbone ResNet50, shape of input tensor is [3, 800, 1333]
         self.default_pretrained_model_path = os.path.join(
             self.directory, "faster_rcnn_resnet50_model")
-        self.label_names = self.faster_rcnn.load_label_info(
+        self.label_names = load_label_info(
             os.path.join(self.directory, "label_file.txt"))
-        self.infer_prog = None
-        self.bbox_out = None
         self._set_config()
 
     def _set_config(self):
@@ -66,20 +70,23 @@ class FasterRCNNResNet50(hub.Module):
                 trainable=True,
                 pretrained=True,
                 phase='train'):
-        """Distill the Head Features, so as to perform transfer learning.
-
-        :param trainable: whether to set parameters trainable.
-        :type trainable: bool
-        :param pretrained: whether to load default pretrained model.
-        :type pretrained: bool
-        :param param_prefix: the prefix of parameters in neural network.
-        :type param_prefix: str
-        :param phase: Optional Choice: 'predict', 'train'
-        :type phase: str
         """
-        wrapped_prog = fluid.Program()
+        Distill the Head Features, so as to perform transfer learning.
+
+        Args:
+            trainable (bool): whether to set parameters trainable.
+            pretrained (bool): whether to load default pretrained model.
+            get_prediction (bool): whether to get prediction.
+            phase (str): optional choices are 'train' and 'predict'.
+
+        Returns:
+             inputs (dict): the input variables.
+             outputs (dict): the output variables.
+             context_prog (Program): the program to execute transfer learning.
+        """
+        context_prog = fluid.Program()
         startup_program = fluid.Program()
-        with fluid.program_guard(wrapped_prog, startup_program):
+        with fluid.program_guard(context_prog, startup_program):
             with fluid.unique_name.guard():
                 image = fluid.layers.data(
                     name='image', shape=[3, 800, 1333], dtype='float32')
@@ -91,18 +98,106 @@ class FasterRCNNResNet50(hub.Module):
                     freeze_at=2)
                 body_feats = backbone(image)
 
-                # Base Class
-                inputs, outputs, context_prog = self.faster_rcnn.context(
-                    body_feats=body_feats,
-                    fpn=None,
-                    rpn_head=self.rpn_head(),
-                    roi_extractor=self.roi_extractor(),
-                    bbox_head=self.bbox_head(num_classes),
-                    bbox_assigner=self.bbox_assigner(num_classes),
-                    image=image,
-                    trainable=trainable,
-                    var_prefix='@HUB_{}@'.format(self.name),
-                    phase=phase)
+                # var_prefix
+                var_prefix = '@HUB_{}@'.format(self.name)
+                im_info = fluid.layers.data(
+                    name='im_info', shape=[3], dtype='float32', lod_level=0)
+                im_shape = fluid.layers.data(
+                    name='im_shape', shape=[3], dtype='float32', lod_level=0)
+                body_feat_names = list(body_feats.keys())
+                # rpn_head: RPNHead
+                rpn_head = self.rpn_head()
+                rois = rpn_head.get_proposals(body_feats, im_info, mode=phase)
+                # train
+                if phase == 'train':
+                    gt_bbox = fluid.layers.data(
+                        name='gt_bbox', shape=[4], dtype='float32', lod_level=1)
+                    is_crowd = fluid.layers.data(
+                        name='is_crowd', shape=[1], dtype='int32', lod_level=1)
+                    gt_class = fluid.layers.data(
+                        name='gt_class', shape=[1], dtype='int32', lod_level=1)
+                    rpn_loss = rpn_head.get_loss(im_info, gt_bbox, is_crowd)
+                    # bbox_assigner: BBoxAssigner
+                    bbox_assigner = self.bbox_assigner(num_classes)
+                    outs = fluid.layers.generate_proposal_labels(
+                        rpn_rois=rois,
+                        gt_classes=gt_class,
+                        is_crowd=is_crowd,
+                        gt_boxes=gt_bbox,
+                        im_info=im_info,
+                        batch_size_per_im=bbox_assigner.batch_size_per_im,
+                        fg_fraction=bbox_assigner.fg_fraction,
+                        fg_thresh=bbox_assigner.fg_thresh,
+                        bg_thresh_hi=bbox_assigner.bg_thresh_hi,
+                        bg_thresh_lo=bbox_assigner.bg_thresh_lo,
+                        bbox_reg_weights=bbox_assigner.bbox_reg_weights,
+                        class_nums=bbox_assigner.class_nums,
+                        use_random=bbox_assigner.use_random)
+                    rois = outs[0]
+
+                body_feat = body_feats[body_feat_names[-1]]
+                # roi_extractor: RoIAlign
+                roi_extractor = self.roi_extractor()
+                roi_feat = fluid.layers.roi_align(
+                    input=body_feat,
+                    rois=rois,
+                    pooled_height=roi_extractor.pooled_height,
+                    pooled_width=roi_extractor.pooled_width,
+                    spatial_scale=roi_extractor.spatial_scale,
+                    sampling_ratio=roi_extractor.sampling_ratio)
+                # head_feat
+                bbox_head = self.bbox_head(num_classes)
+                head_feat = bbox_head.head(roi_feat)
+                if isinstance(head_feat, OrderedDict):
+                    head_feat = list(head_feat.values())[0]
+                if phase == 'train':
+                    inputs = {
+                        'image': var_prefix + image.name,
+                        'im_info': var_prefix + im_info.name,
+                        'im_shape': var_prefix + im_shape.name,
+                        'gt_class': var_prefix + gt_class.name,
+                        'gt_bbox': var_prefix + gt_bbox.name,
+                        'is_crowd': var_prefix + is_crowd.name
+                    }
+                    outputs = {
+                        'head_feat':
+                        var_prefix + head_feat.name,
+                        'rpn_cls_loss':
+                        var_prefix + rpn_loss['rpn_cls_loss'].name,
+                        'rpn_reg_loss':
+                        var_prefix + rpn_loss['rpn_reg_loss'].name,
+                        'generate_proposal_labels':
+                        [var_prefix + var.name for var in outs]
+                    }
+                elif phase == 'predict':
+                    pred = bbox_head.get_prediction(roi_feat, rois, im_info,
+                                                    im_shape)
+                    inputs = {
+                        'image': var_prefix + image.name,
+                        'im_info': var_prefix + im_info.name,
+                        'im_shape': var_prefix + im_shape.name
+                    }
+                    outputs = {
+                        'head_feat': var_prefix + head_feat.name,
+                        'rois': var_prefix + rois.name,
+                        'bbox_out': var_prefix + pred.name
+                    }
+                add_vars_prefix(context_prog, var_prefix)
+                add_vars_prefix(startup_program, var_prefix)
+
+                global_vars = context_prog.global_block().vars
+                inputs = {
+                    key: global_vars[value]
+                    for key, value in inputs.items()
+                }
+                outputs = {
+                    key: global_vars[value] if not isinstance(value, list) else
+                    [global_vars[var] for var in value]
+                    for key, value in outputs.items()
+                }
+
+                for param in context_prog.global_block().iter_parameters():
+                    param.trainable = trainable
 
                 place = fluid.CPUPlace()
                 exe = fluid.Executor(place)
@@ -122,43 +217,42 @@ class FasterRCNNResNet50(hub.Module):
                 return inputs, outputs, context_prog
 
     def rpn_head(self):
-        return self.faster_rcnn.RPNHead(
-            anchor_generator=self.faster_rcnn.AnchorGenerator(
+        return RPNHead(
+            anchor_generator=AnchorGenerator(
                 anchor_sizes=[32, 64, 128, 256, 512],
                 aspect_ratios=[0.5, 1.0, 2.0],
                 stride=[16.0, 16.0],
                 variance=[1.0, 1.0, 1.0, 1.0]),
-            rpn_target_assign=self.faster_rcnn.RPNTargetAssign(
+            rpn_target_assign=RPNTargetAssign(
                 rpn_batch_size_per_im=256,
                 rpn_fg_fraction=0.5,
                 rpn_negative_overlap=0.3,
                 rpn_positive_overlap=0.7,
                 rpn_straddle_thresh=0.0),
-            train_proposal=self.faster_rcnn.GenerateProposals(
+            train_proposal=GenerateProposals(
                 min_size=0.0,
                 nms_thresh=0.7,
                 post_nms_top_n=12000,
                 pre_nms_top_n=2000),
-            test_proposal=self.faster_rcnn.GenerateProposals(
+            test_proposal=GenerateProposals(
                 min_size=0.0,
                 nms_thresh=0.7,
                 post_nms_top_n=6000,
                 pre_nms_top_n=1000))
 
     def roi_extractor(self):
-        return self.faster_rcnn.RoIAlign(
-            resolution=14, sampling_ratio=0, spatial_scale=0.0625)
+        return RoIAlign(resolution=14, sampling_ratio=0, spatial_scale=0.0625)
 
     def bbox_head(self, num_classes):
-        return self.faster_rcnn.BBoxHead(
+        return BBoxHead(
             head=ResNetC5(depth=50, norm_type='affine_channel'),
-            nms=self.faster_rcnn.MultiClassNMS(
+            nms=MultiClassNMS(
                 keep_top_k=100, nms_threshold=0.5, score_threshold=0.05),
-            bbox_loss=self.faster_rcnn.SmoothL1Loss(),
+            bbox_loss=SmoothL1Loss(),
             num_classes=num_classes)
 
     def bbox_assigner(self, num_classes):
-        return self.faster_rcnn.BBoxAssigner(
+        return BBoxAssigner(
             batch_size_per_im=512,
             bbox_reg_weights=[0.1, 0.1, 0.2, 0.2],
             bg_thresh_hi=0.5,
@@ -178,26 +272,32 @@ class FasterRCNNResNet50(hub.Module):
                          visualization=True):
         """API of Object Detection.
 
-        :param paths: the path of images.
-        :type paths: list, each element is correspond to the path of an image.
-        :param images: data of images, [N, H, W, C]
-        :type images: numpy.ndarray
-        :param use_gpu: whether to use gpu or not.
-        :type use_gpu: bool
-        :param batch_size: bathc size.
-        :type batch_size: int
-        :param output_dir: the directory to store the detection result.
-        :type output_dir: str
-        :param score_thresh: the threshold of detection confidence.
-        :type score_thresh: float
-        :param visualization: whether to draw box and save images.
-        :type visualization: bool
+        Args:
+            paths (list[str]): The paths of images.
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]
+            batch_size (int): batch size.
+            use_gpu (bool): Whether to use gpu.
+            output_dir (str): The path to store output images.
+            visualization (bool): Whether to save image or not.
+            score_thresh (float): threshold for object detecion.
+
+        Returns:
+            res (list[dict]): The result of coco2017 detecion. keys include 'data', 'save_path', the corresponding value is:
+                data (dict): the result of object detection, keys include 'left', 'top', 'right', 'bottom', 'label', 'confidence', the corresponding value is:
+                    left (float): The X coordinate of the upper left corner of the bounding box;
+                    top (float): The Y coordinate of the upper left corner of the bounding box;
+                    right (float): The X coordinate of the lower right corner of the bounding box;
+                    bottom (float): The Y coordinate of the lower right corner of the bounding box;
+                    label (str): The label of detection result;
+                    confidence (float): The confidence of detection result.
+                save_path (str, optional): The path to save output images.
         """
+        paths = paths if paths else list()
         if data and 'image' in data:
-            paths = data['image'] if not paths else paths + data['image']
-        all_images = []
-        paths = paths if paths else []
-        for yield_return in self.faster_rcnn.test_reader(paths, images):
+            paths += data['image']
+
+        all_images = list()
+        for yield_return in test_reader(paths, images):
             all_images.append(yield_return)
 
         images_num = len(all_images)
@@ -211,7 +311,8 @@ class FasterRCNNResNet50(hub.Module):
                     batch_data.append(all_images[handle_id + image_id])
                 except:
                     pass
-            padding_image, padding_info, padding_shape = self.faster_rcnn.padding_minibatch(
+
+            padding_image, padding_info, padding_shape = padding_minibatch(
                 batch_data)
             padding_image_tensor = PaddleTensor(padding_image.copy())
             padding_info_tensor = PaddleTensor(padding_info.copy())
@@ -223,7 +324,7 @@ class FasterRCNNResNet50(hub.Module):
                 data_out = self.gpu_predictor.run(feed_list)
             else:
                 data_out = self.cpu_predictor.run(feed_list)
-            output = self.faster_rcnn.postprocess(
+            output = postprocess(
                 paths=paths,
                 images=images,
                 data_out=data_out,
@@ -275,6 +376,15 @@ class FasterRCNNResNet50(hub.Module):
                 input_data = txt_parser.parse(args.input_file, use_strip=True)
         return input_data
 
+    @serving
+    def serving_method(self, images, **kwargs):
+        """
+        Run as a service.
+        """
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.object_detection(images_decode, **kwargs)
+        return results
+
     @runnable
     def run_cmd(self, argvs):
         self.parser = argparse.ArgumentParser(

hub_module/modules/image/object_detection/faster_rcnn/processor.py → hub_module/modules/image/object_detection/faster_rcnn_resnet50_coco2017/processor.py

 # coding=utf-8
+import base64
 import os
 
+import cv2
 import numpy as np
 from PIL import Image, ImageDraw
 
 __all__ = [
-    'get_save_image_name', 'draw_bounding_box_on_image', 'clip_bbox',
-    'load_label_info'
+    'base64_to_cv2',
+    'load_label_info',
+    'postprocess',
 ]
 
 
+def base64_to_cv2(b64str):
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.fromstring(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+
 def get_save_image_name(img, output_dir, image_path):
     """Get save image name from source image path.
     """
@@ -90,24 +100,29 @@ def postprocess(paths,
                 output_dir,
                 handle_id,
                 visualization=True):
-    """postprocess the lod_tensor produced by fluid.Executor.run
-
-    :param paths: the path of images.
-    :type paths: list, each element is a str
-    :param images: data of images, [N, H, W, C]
-    :type images: numpy.ndarray
-    :param data_out: data produced by executor.run
-    :type data_out: lod_tensor
-    :param score_thresh: the low limit of bounding box.
-    :type score_thresh: float
-    :param label_names: label names
-    :type label_names: list
-    :param output_dir: output directory.
-    :type output_dir: str
-    :param handle_id: The number of images that have been handled.
-    :type handle_id: int
-    :param visualization: whether to draw bbox and save images.
-    :param visualization: bool
+    """
+    postprocess the lod_tensor produced by fluid.Executor.run
+
+    Args:
+        paths (list[str]): the path of images.
+        images (list(numpy.ndarray)):  list of images, shape of each is [H, W, C].
+        data_out (lod_tensor): data produced by executor.run.
+        score_thresh (float): the low limit of bounding box.
+        label_names (list[str]): label names.
+        output_dir (str): output directory.
+        handle_id (int): The number of images that have been handled.
+        visualization (bool): whether to save as images.
+
+    Returns:
+        res (list[dict]): The result of vehicles detecion. keys include 'data', 'save_path', the corresponding value is:
+            data (dict): the result of object detection, keys include 'left', 'top', 'right', 'bottom', 'label', 'confidence', the corresponding value is:
+                left (float): The X coordinate of the upper left corner of the bounding box;
+                top (float): The Y coordinate of the upper left corner of the bounding box;
+                right (float): The X coordinate of the lower right corner of the bounding box;
+                bottom (float): The Y coordinate of the lower right corner of the bounding box;
+                label (str): The label of detection result;
+                confidence (float): The confidence of detection result.
+            save_path (str): The path to save output images.
     """
     lod_tensor = data_out[0]
     lod = lod_tensor.lod[0]

hub_module/modules/image/object_detection/faster_rcnn_resnet50_coco2017/roi_extractor.py

+# coding=utf-8
+__all__ = ['RoIAlign']
+
+
+class RoIAlign(object):
+    def __init__(self, resolution=7, spatial_scale=0.0625, sampling_ratio=0):
+        super(RoIAlign, self).__init__()
+        if isinstance(resolution, int):
+            resolution = [resolution, resolution]
+        self.pooled_height = resolution[0]
+        self.pooled_width = resolution[1]
+        self.spatial_scale = spatial_scale
+        self.sampling_ratio = sampling_ratio

hub_module/modules/image/object_detection/faster_rcnn_resnet50_coco2017/rpn_head.py

+# coding=utf-8
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+from paddle import fluid
+from paddle.fluid.param_attr import ParamAttr
+from paddle.fluid.initializer import Normal
+from paddle.fluid.regularizer import L2Decay
+
+__all__ = ['AnchorGenerator', 'RPNTargetAssign', 'GenerateProposals', 'RPNHead']
+
+
+class AnchorGenerator(object):
+    # __op__ = fluid.layers.anchor_generator
+    def __init__(self,
+                 stride=[16.0, 16.0],
+                 anchor_sizes=[32, 64, 128, 256, 512],
+                 aspect_ratios=[0.5, 1., 2.],
+                 variance=[1., 1., 1., 1.]):
+        super(AnchorGenerator, self).__init__()
+        self.anchor_sizes = anchor_sizes
+        self.aspect_ratios = aspect_ratios
+        self.variance = variance
+        self.stride = stride
+
+
+class RPNTargetAssign(object):
+    # __op__ = fluid.layers.rpn_target_assign
+    def __init__(self,
+                 rpn_batch_size_per_im=256,
+                 rpn_straddle_thresh=0.,
+                 rpn_fg_fraction=0.5,
+                 rpn_positive_overlap=0.7,
+                 rpn_negative_overlap=0.3,
+                 use_random=True):
+        super(RPNTargetAssign, self).__init__()
+        self.rpn_batch_size_per_im = rpn_batch_size_per_im
+        self.rpn_straddle_thresh = rpn_straddle_thresh
+        self.rpn_fg_fraction = rpn_fg_fraction
+        self.rpn_positive_overlap = rpn_positive_overlap
+        self.rpn_negative_overlap = rpn_negative_overlap
+        self.use_random = use_random
+
+
+class GenerateProposals(object):
+    # __op__ = fluid.layers.generate_proposals
+    def __init__(self,
+                 pre_nms_top_n=6000,
+                 post_nms_top_n=1000,
+                 nms_thresh=.5,
+                 min_size=.1,
+                 eta=1.):
+        super(GenerateProposals, self).__init__()
+        self.pre_nms_top_n = pre_nms_top_n
+        self.post_nms_top_n = post_nms_top_n
+        self.nms_thresh = nms_thresh
+        self.min_size = min_size
+        self.eta = eta
+
+
+class RPNHead(object):
+    """
+    RPN Head
+
+    Args:
+        anchor_generator (object): `AnchorGenerator` instance
+        rpn_target_assign (object): `RPNTargetAssign` instance
+        train_proposal (object): `GenerateProposals` instance for training
+        test_proposal (object): `GenerateProposals` instance for testing
+        num_classes (int): number of classes in rpn output
+    """
+    __inject__ = [
+        'anchor_generator', 'rpn_target_assign', 'train_proposal',
+        'test_proposal'
+    ]
+
+    def __init__(self,
+                 anchor_generator,
+                 rpn_target_assign,
+                 train_proposal,
+                 test_proposal,
+                 num_classes=1):
+        super(RPNHead, self).__init__()
+        self.anchor_generator = anchor_generator
+        self.rpn_target_assign = rpn_target_assign
+        self.train_proposal = train_proposal
+        self.test_proposal = test_proposal
+        self.num_classes = num_classes
+
+    def _get_output(self, input):
+        """
+        Get anchor and RPN head output.
+
+        Args:
+            input(Variable): feature map from backbone with shape of [N, C, H, W]
+
+        Returns:
+            rpn_cls_score(Variable): Output of rpn head with shape of [N, num_anchors, H, W].
+            rpn_bbox_pred(Variable): Output of rpn head with shape of [N, num_anchors * 4, H, W].
+        """
+        dim_out = input.shape[1]
+        rpn_conv = fluid.layers.conv2d(
+            input=input,
+            num_filters=dim_out,
+            filter_size=3,
+            stride=1,
+            padding=1,
+            act='relu',
+            name='conv_rpn',
+            param_attr=ParamAttr(
+                name="conv_rpn_w", initializer=Normal(loc=0., scale=0.01)),
+            bias_attr=ParamAttr(
+                name="conv_rpn_b", learning_rate=2., regularizer=L2Decay(0.)))
+        # Generate anchors self.anchor_generator
+        self.anchor, self.anchor_var = fluid.layers.anchor_generator(
+            input=rpn_conv,
+            anchor_sizes=self.anchor_generator.anchor_sizes,
+            aspect_ratios=self.anchor_generator.aspect_ratios,
+            variance=self.anchor_generator.variance,
+            stride=self.anchor_generator.stride)
+
+        num_anchor = self.anchor.shape[2]
+        # Proposal classification scores
+        self.rpn_cls_score = fluid.layers.conv2d(
+            rpn_conv,
+            num_filters=num_anchor * self.num_classes,
+            filter_size=1,
+            stride=1,
+            padding=0,
+            act=None,
+            name='rpn_cls_score',
+            param_attr=ParamAttr(
+                name="rpn_cls_logits_w", initializer=Normal(loc=0.,
+                                                            scale=0.01)),
+            bias_attr=ParamAttr(
+                name="rpn_cls_logits_b",
+                learning_rate=2.,
+                regularizer=L2Decay(0.)))
+        # Proposal bbox regression deltas
+        self.rpn_bbox_pred = fluid.layers.conv2d(
+            rpn_conv,
+            num_filters=4 * num_anchor,
+            filter_size=1,
+            stride=1,
+            padding=0,
+            act=None,
+            name='rpn_bbox_pred',
+            param_attr=ParamAttr(
+                name="rpn_bbox_pred_w", initializer=Normal(loc=0., scale=0.01)),
+            bias_attr=ParamAttr(
+                name="rpn_bbox_pred_b",
+                learning_rate=2.,
+                regularizer=L2Decay(0.)))
+        return self.rpn_cls_score, self.rpn_bbox_pred
+
+    def get_proposals(self, body_feats, im_info, mode='train'):
+        """
+        Get proposals according to the output of backbone.
+
+        Args:
+            body_feats (dict): The dictionary of feature maps from backbone.
+            im_info(Variable): The information of image with shape [N, 3] with
+                shape (height, width, scale).
+            body_feat_names(list): A list of names of feature maps from
+                backbone.
+
+        Returns:
+            rpn_rois(Variable): Output proposals with shape of (rois_num, 4).
+        """
+        # In RPN Heads, only the last feature map of backbone is used.
+        # And body_feat_names[-1] represents the last level name of backbone.
+        body_feat = list(body_feats.values())[-1]
+        rpn_cls_score, rpn_bbox_pred = self._get_output(body_feat)
+
+        if self.num_classes == 1:
+            rpn_cls_prob = fluid.layers.sigmoid(
+                rpn_cls_score, name='rpn_cls_prob')
+        else:
+            rpn_cls_score = fluid.layers.transpose(
+                rpn_cls_score, perm=[0, 2, 3, 1])
+            rpn_cls_score = fluid.layers.reshape(
+                rpn_cls_score, shape=(0, 0, 0, -1, self.num_classes))
+            rpn_cls_prob_tmp = fluid.layers.softmax(
+                rpn_cls_score, use_cudnn=False, name='rpn_cls_prob')
+            rpn_cls_prob_slice = fluid.layers.slice(
+                rpn_cls_prob_tmp, axes=[4], starts=[1], ends=[self.num_classes])
+            rpn_cls_prob, _ = fluid.layers.topk(rpn_cls_prob_slice, 1)
+            rpn_cls_prob = fluid.layers.reshape(
+                rpn_cls_prob, shape=(0, 0, 0, -1))
+            rpn_cls_prob = fluid.layers.transpose(
+                rpn_cls_prob, perm=[0, 3, 1, 2])
+        prop_op = self.train_proposal if mode == 'train' else self.test_proposal
+        # prop_op
+        rpn_rois, rpn_roi_probs = fluid.layers.generate_proposals(
+            scores=rpn_cls_prob,
+            bbox_deltas=rpn_bbox_pred,
+            im_info=im_info,
+            anchors=self.anchor,
+            variances=self.anchor_var,
+            pre_nms_top_n=prop_op.pre_nms_top_n,
+            post_nms_top_n=prop_op.post_nms_top_n,
+            nms_thresh=prop_op.nms_thresh,
+            min_size=prop_op.min_size,
+            eta=prop_op.eta)
+        return rpn_rois
+
+    def _transform_input(self, rpn_cls_score, rpn_bbox_pred, anchor,
+                         anchor_var):
+        rpn_cls_score = fluid.layers.transpose(rpn_cls_score, perm=[0, 2, 3, 1])
+        rpn_bbox_pred = fluid.layers.transpose(rpn_bbox_pred, perm=[0, 2, 3, 1])
+        anchor = fluid.layers.reshape(anchor, shape=(-1, 4))
+        anchor_var = fluid.layers.reshape(anchor_var, shape=(-1, 4))
+        rpn_cls_score = fluid.layers.reshape(
+            x=rpn_cls_score, shape=(0, -1, self.num_classes))
+        rpn_bbox_pred = fluid.layers.reshape(x=rpn_bbox_pred, shape=(0, -1, 4))
+        return rpn_cls_score, rpn_bbox_pred, anchor, anchor_var
+
+    def _get_loss_input(self):
+        for attr in ['rpn_cls_score', 'rpn_bbox_pred', 'anchor', 'anchor_var']:
+            if not getattr(self, attr, None):
+                raise ValueError("self.{} should not be None,".format(attr),
+                                 "call RPNHead.get_proposals first")
+        return self._transform_input(self.rpn_cls_score, self.rpn_bbox_pred,
+                                     self.anchor, self.anchor_var)
+
+    def get_loss(self, im_info, gt_box, is_crowd, gt_label=None):
+        """
+        Sample proposals and Calculate rpn loss.
+
+        Args:
+            im_info(Variable): The information of image with shape [N, 3] with
+                shape (height, width, scale).
+            gt_box(Variable): The ground-truth bounding boxes with shape [M, 4].
+                M is the number of groundtruth.
+            is_crowd(Variable): Indicates groud-truth is crowd or not with
+                shape [M, 1]. M is the number of groundtruth.
+
+        Returns:
+            Type: dict
+                rpn_cls_loss(Variable): RPN classification loss.
+                rpn_bbox_loss(Variable): RPN bounding box regression loss.
+
+        """
+        rpn_cls, rpn_bbox, anchor, anchor_var = self._get_loss_input()
+        if self.num_classes == 1:
+            # self.rpn_target_assign
+            score_pred, loc_pred, score_tgt, loc_tgt, bbox_weight = \
+                fluid.layers.rpn_target_assign(
+                    bbox_pred=rpn_bbox,
+                    cls_logits=rpn_cls,
+                    anchor_box=anchor,
+                    anchor_var=anchor_var,
+                    gt_boxes=gt_box,
+                    is_crowd=is_crowd,
+                    im_info=im_info,
+                    rpn_batch_size_per_im=self.rpn_target_assign.rpn_batch_size_per_im,
+                    rpn_straddle_thresh=self.rpn_target_assign.rpn_straddle_thresh,
+                    rpn_fg_fraction=self.rpn_target_assign.rpn_fg_fraction,
+                    rpn_positive_overlap=self.rpn_target_assign.rpn_positive_overlap,
+                    rpn_negative_overlap=self.rpn_target_assign.rpn_negative_overlap,
+                    use_random=self.rpn_target_assign.use_random)
+            score_tgt = fluid.layers.cast(x=score_tgt, dtype='float32')
+            score_tgt.stop_gradient = True
+            rpn_cls_loss = fluid.layers.sigmoid_cross_entropy_with_logits(
+                x=score_pred, label=score_tgt)
+        else:
+            score_pred, loc_pred, score_tgt, loc_tgt, bbox_weight = \
+                self.rpn_target_assign(
+                    bbox_pred=rpn_bbox,
+                    cls_logits=rpn_cls,
+                    anchor_box=anchor,
+                    anchor_var=anchor_var,
+                    gt_boxes=gt_box,
+                    gt_labels=gt_label,
+                    is_crowd=is_crowd,
+                    num_classes=self.num_classes,
+                    im_info=im_info)
+            labels_int64 = fluid.layers.cast(x=score_tgt, dtype='int64')
+            labels_int64.stop_gradient = True
+            rpn_cls_loss = fluid.layers.softmax_with_cross_entropy(
+                logits=score_pred, label=labels_int64, numeric_stable_mode=True)
+
+        rpn_cls_loss = fluid.layers.reduce_mean(
+            rpn_cls_loss, name='loss_rpn_cls')
+
+        loc_tgt = fluid.layers.cast(x=loc_tgt, dtype='float32')
+        loc_tgt.stop_gradient = True
+        rpn_reg_loss = fluid.layers.smooth_l1(
+            x=loc_pred,
+            y=loc_tgt,
+            sigma=3.0,
+            inside_weight=bbox_weight,
+            outside_weight=bbox_weight)
+        rpn_reg_loss = fluid.layers.reduce_sum(
+            rpn_reg_loss, name='loss_rpn_bbox')
+        score_shape = fluid.layers.shape(score_tgt)
+        score_shape = fluid.layers.cast(x=score_shape, dtype='float32')
+        norm = fluid.layers.reduce_prod(score_shape)
+        norm.stop_gradient = True
+        rpn_reg_loss = rpn_reg_loss / norm
+        return {'rpn_cls_loss': rpn_cls_loss, 'rpn_reg_loss': rpn_reg_loss}

hub_module/modules/image/object_detection/faster_rcnn_resnet50_fpn_coco2017/README.md

+```shell
+$ hub install faster_rcnn_resnet50_fpn_coco2017==1.0.0
+```
+
+## 命令行预测
+
+```
+hub run faster_rcnn_resnet50_fpn_coco2017 --input_path "/PATH/TO/IMAGE"
+```
+
+## API
+
+```
+def context(num_classes=81,
+            trainable=True,
+            pretrained=True,
+            phase='train')
+```
+
+提取头部特征，用于迁移学习。
+
+**参数**
+
+* num\_classes (int): 类别数；
+* trainable(bool): 将参数的trainable 属性设为trainable；
+* pretrained (bool): 是否加载预训练模型；
+* phase (str): 可选值为 'train'/'predict'，'trian' 用于训练，'predict' 用于预测。
+
+**返回**
+
+* inputs (dict): 模型的输入，keys 包括 'image', 'im\_size'，相应的取值为：
+    * image (Variable): 图像变量
+    * im\_size (Variable): 图片的尺寸
+* outputs (dict): 模型的输出。如果 get\_prediction 为 False，输出 'head\_fatures'，否则输出 'bbox\_out'。
+* context\_prog (Program): 用于迁移学习的 Program。
+
+```python
+def object_detection(paths=None,
+                     images=None,
+                     batch_size=1,
+                     use_gpu=False,
+                     output_dir='detection_result',
+                     score_thresh=0.5,
+                     visualization=True)
+```
+
+预测API，检测输入图片中的所有目标的位置。
+
+**参数**
+
+* paths (list\[str\]): 图片的路径；
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，BGR格式；
+* batch\_size (int): batch 的大小；
+* use\_gpu (bool): 是否使用 GPU；
+* score\_thresh (float): 识别置信度的阈值；
+* visualization (bool): 是否将识别结果保存为图片文件；
+* output\_dir (str): 图片的保存路径，默认设为 detection\_result；
+
+**返回**
+
+* res (list\[dict\]): 识别结果的列表，列表中每一个元素为 dict，各字段为：
+    * data (list): 检测结果，list的每一个元素为 dict，各字段为:
+        * confidence (float): 识别的置信度；
+        * label (str): 标签；
+        * left (int): 边界框的左上角x坐标；
+        * top (int): 边界框的左上角y坐标；
+        * right (int): 边界框的右下角x坐标；
+        * bottom (int): 边界框的右下角y坐标；
+    * save\_path (str, optional): 识别结果的保存路径 (仅当visualization=True时存在)。
+
+```python
+def save_inference_model(dirname,
+                         model_filename=None,
+                         params_filename=None,
+                         combined=True)
+```
+
+将模型保存到指定路径。
+
+**参数**
+
+* dirname: 存在模型的目录名称
+* model\_filename: 模型文件名称，默认为\_\_model\_\_
+* params\_filename: 参数文件名称，默认为\_\_params\_\_(仅当`combined`为True时生效)
+* combined: 是否将参数保存到统一的一个文件中
+
+## 代码示例
+
+```python
+import paddlehub as hub
+import cv2
+
+object_detector = hub.Module(name="faster_rcnn_resnet50_fpn_coco2017")
+result = object_detector.object_detection(images=[cv2.imread('/PATH/TO/IMAGE')])
+# or
+# result = object_detector.object_detection((paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving 可以部署一个目标检测的在线服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m faster_rcnn_resnet50_fpn_coco2017
+```
+
+这样就完成了一个目标检测的服务化API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/faster_rcnn_resnet50_fpn_coco2017"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+### 依赖
+
+paddlepaddle >= 1.6.2
+
+paddlehub >= 1.6.0

hub_module/modules/image/object_detection/faster_rcnn/bbox_head.py → hub_module/modules/image/object_detection/faster_rcnn_resnet50_fpn_coco2017/bbox_head.py

@@ -53,7 +53,6 @@ class SmoothL1Loss(object):
 
 
 class BoxCoder(object):
-    # __op__ = fluid.layers.box_coder
     def __init__(self,
                  prior_box_var=[0.1, 0.1, 0.2, 0.2],
                  code_type='decode_center_size',

hub_module/modules/image/object_detection/faster_rcnn_resnet50_fpn_coco2017/data_feed.py

+# coding=utf-8
+from __future__ import absolute_import
+from __future__ import print_function
+from __future__ import division
+
+import os
+from collections import OrderedDict
+
+import cv2
+import numpy as np
+from PIL import Image, ImageEnhance
+from paddle import fluid
+
+__all__ = ['test_reader']
+
+
+def test_reader(paths=None, images=None):
+    """
+    data generator
+
+    Args:
+        paths (list[str]): paths to images.
+        images (list(numpy.ndarray)): data of images, shape of each is [H, W, C]
+
+    Yield:
+        res (dict): key contains 'image', 'im_info', 'im_shape', the corresponding values is:
+            image (numpy.ndarray): the image to be fed into network
+            im_info (numpy.ndarray): the info about the preprocessed.
+            im_shape (numpy.ndarray): the shape of image.
+    """
+    img_list = list()
+    if paths:
+        for img_path in paths:
+            assert os.path.isfile(
+                img_path), "The {} isn't a valid file path.".format(img_path)
+            img = cv2.imread(img_path).astype('float32')
+            img_list.append(img)
+    if images is not None:
+        for img in images:
+            img_list.append(img)
+
+    for im in img_list:
+        im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
+        im = im.astype(np.float32, copy=False)
+        mean = [0.485, 0.456, 0.406]
+        std = [0.229, 0.224, 0.225]
+        mean = np.array(mean)[np.newaxis, np.newaxis, :]
+        std = np.array(std)[np.newaxis, np.newaxis, :]
+        im = im / 255.0
+        im -= mean
+        im /= std
+
+        target_size = 800
+        max_size = 1333
+
+        shape = im.shape
+        # im_shape holds the original shape of image.
+        im_shape = np.array([shape[0], shape[1], 1.0]).astype('float32')
+        im_size_min = np.min(shape[0:2])
+        im_size_max = np.max(shape[0:2])
+        im_scale = float(target_size) / float(im_size_min)
+        if np.round(im_scale * im_size_max) > max_size:
+            im_scale = float(max_size) / float(im_size_max)
+
+        resize_w = np.round(im_scale * float(shape[1]))
+        resize_h = np.round(im_scale * float(shape[0]))
+        # im_info holds the resize info of image.
+        im_info = np.array([resize_h, resize_w, im_scale]).astype('float32')
+
+        im = cv2.resize(
+            im,
+            None,
+            None,
+            fx=im_scale,
+            fy=im_scale,
+            interpolation=cv2.INTER_LINEAR)
+
+        # HWC --> CHW
+        im = np.swapaxes(im, 1, 2)
+        im = np.swapaxes(im, 1, 0)
+        yield {'image': im, 'im_info': im_info, 'im_shape': im_shape}
+
+
+def padding_minibatch(batch_data, coarsest_stride=0, use_padded_im_info=True):
+    max_shape_org = np.array(
+        [data['image'].shape for data in batch_data]).max(axis=0)
+    if coarsest_stride > 0:
+        max_shape = np.zeros((3)).astype('int32')
+        max_shape[1] = int(
+            np.ceil(max_shape_org[1] / coarsest_stride) * coarsest_stride)
+        max_shape[2] = int(
+            np.ceil(max_shape_org[2] / coarsest_stride) * coarsest_stride)
+    else:
+        max_shape = max_shape_org.astype('int32')
+
+    padding_image = list()
+    padding_info = list()
+    padding_shape = list()
+
+    for data in batch_data:
+        im_c, im_h, im_w = data['image'].shape
+        # image
+        padding_im = np.zeros((im_c, max_shape[1], max_shape[2]),
+                              dtype=np.float32)
+        padding_im[:, 0:im_h, 0:im_w] = data['image']
+        padding_image.append(padding_im)
+        # im_info
+        data['im_info'][
+            0] = max_shape[1] if use_padded_im_info else max_shape_org[1]
+        data['im_info'][
+            1] = max_shape[2] if use_padded_im_info else max_shape_org[2]
+        padding_info.append(data['im_info'])
+        padding_shape.append(data['im_shape'])
+
+    padding_image = np.array(padding_image).astype('float32')
+    padding_info = np.array(padding_info).astype('float32')
+    padding_shape = np.array(padding_shape).astype('float32')
+    return padding_image, padding_info, padding_shape

hub_module/modules/image/object_detection/faster_rcnn_resnet50_fpn_coco2017/module.py

@@ -13,12 +13,19 @@ from math import ceil
 import numpy as np
 import paddle.fluid as fluid
 import paddlehub as hub
-from paddlehub.module.module import moduleinfo, runnable
+from paddlehub.module.module import moduleinfo, runnable, serving
 from paddle.fluid.core import PaddleTensor, AnalysisConfig, create_paddle_predictor
 from paddlehub.io.parser import txt_parser
+from paddlehub.common.paddle_helper import add_vars_prefix
 
+from faster_rcnn_resnet50_fpn_coco2017.processor import load_label_info, postprocess, base64_to_cv2
+from faster_rcnn_resnet50_fpn_coco2017.data_feed import test_reader, padding_minibatch
 from faster_rcnn_resnet50_fpn_coco2017.fpn import FPN
-from faster_rcnn_resnet50_fpn_coco2017.resnet import ResNet, ResNetC5
+from faster_rcnn_resnet50_fpn_coco2017.resnet import ResNet
+from faster_rcnn_resnet50_fpn_coco2017.rpn_head import AnchorGenerator, RPNTargetAssign, GenerateProposals, FPNRPNHead
+from faster_rcnn_resnet50_fpn_coco2017.bbox_head import MultiClassNMS, BBoxHead, TwoFCHead
+from faster_rcnn_resnet50_fpn_coco2017.bbox_assigner import BBoxAssigner
+from faster_rcnn_resnet50_fpn_coco2017.roi_extractor import FPNRoIAlign
 
 
 @moduleinfo(
@@ -28,18 +35,15 @@ from faster_rcnn_resnet50_fpn_coco2017.resnet import ResNet, ResNetC5
     summary=
     "Baidu's Faster-RCNN model for object detection, whose backbone is ResNet50, processed with Feature Pyramid Networks",
     author="paddlepaddle",
-    author_email="paddle-dev@baidu.com")
+    author_email="")
 class FasterRCNNResNet50RPN(hub.Module):
     def _initialize(self):
-        self.faster_rcnn = hub.Module(name="faster_rcnn")
         # default pretrained model, Faster-RCNN with backbone ResNet50, shape of input tensor is [3, 800, 1333]
         self.default_pretrained_model_path = os.path.join(
             self.directory, "faster_rcnn_resnet50_fpn_model")
-        self.label_names = self.faster_rcnn.load_label_info(
+        self.label_names = load_label_info(
             os.path.join(self.directory, "label_file.txt"))
-        self.infer_prog = None
-        self.bbox_out = None
-        self._set_config()
+        # self._set_config()
 
     def _set_config(self):
         """
@@ -67,18 +71,23 @@ class FasterRCNNResNet50RPN(hub.Module):
                 trainable=True,
                 pretrained=True,
                 phase='train'):
-        """Distill the Head Features, so as to perform transfer learning.
-
-        :param trainable: whether to set parameters trainable.
-        :type trainable: bool
-        :param pretrained: whether to load default pretrained model.
-        :type pretrained: bool
-        :param phase: Optional Choice: 'predict', 'train'
-        :type phase: str
         """
-        wrapped_prog = fluid.Program()
+        Distill the Head Features, so as to perform transfer learning.
+
+        Args:
+            trainable (bool): whether to set parameters trainable.
+            pretrained (bool): whether to load default pretrained model.
+            get_prediction (bool): whether to get prediction.
+            phase (str): optional choices are 'train' and 'predict'.
+
+        Returns:
+             inputs (dict): the input variables.
+             outputs (dict): the output variables.
+             context_prog (Program): the program to execute transfer learning.
+        """
+        context_prog = fluid.Program()
         startup_program = fluid.Program()
-        with fluid.program_guard(wrapped_prog, startup_program):
+        with fluid.program_guard(context_prog, startup_program):
             with fluid.unique_name.guard():
                 image = fluid.layers.data(
                     name='image', shape=[3, 800, 1333], dtype='float32')
@@ -89,25 +98,107 @@ class FasterRCNNResNet50RPN(hub.Module):
                     feature_maps=[2, 3, 4, 5],
                     freeze_at=2)
                 body_feats = backbone(image)
-                # fpn: FPN
+                # fpn
                 fpn = FPN(
                     max_level=6,
                     min_level=2,
                     num_chan=256,
                     spatial_scale=[0.03125, 0.0625, 0.125, 0.25])
+                var_prefix = '@HUB_{}@'.format(self.name)
+                im_info = fluid.layers.data(
+                    name='im_info', shape=[3], dtype='float32', lod_level=0)
+                im_shape = fluid.layers.data(
+                    name='im_shape', shape=[3], dtype='float32', lod_level=0)
+                body_feat_names = list(body_feats.keys())
+                body_feats, spatial_scale = fpn.get_output(body_feats)
+                # rpn_head: RPNHead
+                rpn_head = self.rpn_head()
+                rois = rpn_head.get_proposals(body_feats, im_info, mode=phase)
+                # train
+                if phase == 'train':
+                    gt_bbox = fluid.layers.data(
+                        name='gt_bbox', shape=[4], dtype='float32', lod_level=1)
+                    is_crowd = fluid.layers.data(
+                        name='is_crowd', shape=[1], dtype='int32', lod_level=1)
+                    gt_class = fluid.layers.data(
+                        name='gt_class', shape=[1], dtype='int32', lod_level=1)
+                    rpn_loss = rpn_head.get_loss(im_info, gt_bbox, is_crowd)
+                    # bbox_assigner: BBoxAssigner
+                    bbox_assigner = self.bbox_assigner(num_classes)
+                    outs = fluid.layers.generate_proposal_labels(
+                        rpn_rois=rois,
+                        gt_classes=gt_class,
+                        is_crowd=is_crowd,
+                        gt_boxes=gt_bbox,
+                        im_info=im_info,
+                        batch_size_per_im=bbox_assigner.batch_size_per_im,
+                        fg_fraction=bbox_assigner.fg_fraction,
+                        fg_thresh=bbox_assigner.fg_thresh,
+                        bg_thresh_hi=bbox_assigner.bg_thresh_hi,
+                        bg_thresh_lo=bbox_assigner.bg_thresh_lo,
+                        bbox_reg_weights=bbox_assigner.bbox_reg_weights,
+                        class_nums=bbox_assigner.class_nums,
+                        use_random=bbox_assigner.use_random)
+                    rois = outs[0]
+
+                roi_extractor = self.roi_extractor()
+                roi_feat = roi_extractor(
+                    head_inputs=body_feats,
+                    rois=rois,
+                    spatial_scale=spatial_scale)
+                # head_feat
+                bbox_head = self.bbox_head(num_classes)
+                head_feat = bbox_head.head(roi_feat)
+                if isinstance(head_feat, OrderedDict):
+                    head_feat = list(head_feat.values())[0]
+                if phase == 'train':
+                    inputs = {
+                        'image': var_prefix + image.name,
+                        'im_info': var_prefix + im_info.name,
+                        'im_shape': var_prefix + im_shape.name,
+                        'gt_class': var_prefix + gt_class.name,
+                        'gt_bbox': var_prefix + gt_bbox.name,
+                        'is_crowd': var_prefix + is_crowd.name
+                    }
+                    outputs = {
+                        'head_feat':
+                        var_prefix + head_feat.name,
+                        'rpn_cls_loss':
+                        var_prefix + rpn_loss['rpn_cls_loss'].name,
+                        'rpn_reg_loss':
+                        var_prefix + rpn_loss['rpn_reg_loss'].name,
+                        'generate_proposal_labels':
+                        [var_prefix + var.name for var in outs]
+                    }
+                elif phase == 'predict':
+                    pred = bbox_head.get_prediction(roi_feat, rois, im_info,
+                                                    im_shape)
+                    inputs = {
+                        'image': var_prefix + image.name,
+                        'im_info': var_prefix + im_info.name,
+                        'im_shape': var_prefix + im_shape.name
+                    }
+                    outputs = {
+                        'head_feat': var_prefix + head_feat.name,
+                        'rois': var_prefix + rois.name,
+                        'bbox_out': var_prefix + pred.name
+                    }
+                add_vars_prefix(context_prog, var_prefix)
+                add_vars_prefix(startup_program, var_prefix)
 
-                # Base Class
-                inputs, outputs, context_prog = self.faster_rcnn.context(
-                    body_feats=body_feats,
-                    fpn=fpn,
-                    rpn_head=self.rpn_head(),
-                    roi_extractor=self.roi_extractor(),
-                    bbox_head=self.bbox_head(num_classes),
-                    bbox_assigner=self.bbox_assigner(num_classes),
-                    image=image,
-                    trainable=trainable,
-                    var_prefix='@HUB_{}@'.format(self.name),
-                    phase=phase)
+                global_vars = context_prog.global_block().vars
+                inputs = {
+                    key: global_vars[value]
+                    for key, value in inputs.items()
+                }
+                outputs = {
+                    key: global_vars[value] if not isinstance(value, list) else
+                    [global_vars[var] for var in value]
+                    for key, value in outputs.items()
+                }
+
+                for param in context_prog.global_block().iter_parameters():
+                    param.trainable = trainable
 
                 place = fluid.CPUPlace()
                 exe = fluid.Executor(place)
@@ -127,24 +218,24 @@ class FasterRCNNResNet50RPN(hub.Module):
                 return inputs, outputs, context_prog
 
     def rpn_head(self):
-        return self.faster_rcnn.FPNRPNHead(
-            anchor_generator=self.faster_rcnn.AnchorGenerator(
+        return FPNRPNHead(
+            anchor_generator=AnchorGenerator(
                 anchor_sizes=[32, 64, 128, 256, 512],
                 aspect_ratios=[0.5, 1.0, 2.0],
                 stride=[16.0, 16.0],
                 variance=[1.0, 1.0, 1.0, 1.0]),
-            rpn_target_assign=self.faster_rcnn.RPNTargetAssign(
+            rpn_target_assign=RPNTargetAssign(
                 rpn_batch_size_per_im=256,
                 rpn_fg_fraction=0.5,
                 rpn_negative_overlap=0.3,
                 rpn_positive_overlap=0.7,
                 rpn_straddle_thresh=0.0),
-            train_proposal=self.faster_rcnn.GenerateProposals(
+            train_proposal=GenerateProposals(
                 min_size=0.0,
                 nms_thresh=0.7,
                 post_nms_top_n=2000,
                 pre_nms_top_n=2000),
-            test_proposal=self.faster_rcnn.GenerateProposals(
+            test_proposal=GenerateProposals(
                 min_size=0.0,
                 nms_thresh=0.7,
                 post_nms_top_n=1000,
@@ -155,7 +246,7 @@ class FasterRCNNResNet50RPN(hub.Module):
             max_level=6)
 
     def roi_extractor(self):
-        return self.faster_rcnn.FPNRoIAlign(
+        return FPNRoIAlign(
             canconical_level=4,
             canonical_size=224,
             max_level=5,
@@ -164,14 +255,14 @@ class FasterRCNNResNet50RPN(hub.Module):
             sampling_ratio=2)
 
     def bbox_head(self, num_classes):
-        return self.faster_rcnn.BBoxHead(
-            head=self.faster_rcnn.TwoFCHead(mlp_dim=1024),
-            nms=self.faster_rcnn.MultiClassNMS(
+        return BBoxHead(
+            head=TwoFCHead(mlp_dim=1024),
+            nms=MultiClassNMS(
                 keep_top_k=100, nms_threshold=0.5, score_threshold=0.05),
             num_classes=num_classes)
 
     def bbox_assigner(self, num_classes):
-        return self.faster_rcnn.BBoxAssigner(
+        return BBoxAssigner(
             batch_size_per_im=512,
             bbox_reg_weights=[0.1, 0.1, 0.2, 0.2],
             bg_thresh_hi=0.5,
@@ -183,6 +274,7 @@ class FasterRCNNResNet50RPN(hub.Module):
     def object_detection(self,
                          paths=None,
                          images=None,
+                         data=None,
                          use_gpu=False,
                          batch_size=1,
                          output_dir='detection_result',
@@ -190,37 +282,49 @@ class FasterRCNNResNet50RPN(hub.Module):
                          visualization=True):
         """API of Object Detection.
 
-        :param paths: the path of images.
-        :type paths: list, each element is correspond to the path of an image.
-        :param images: data of images, [N, H, W, C]
-        :type images: numpy.ndarray
-        :param use_gpu: whether to use gpu or not.
-        :type use_gpu: bool
-        :param batch_size: bathc size.
-        :type batch_size: int
-        :param output_dir: the directory to store the detection result.
-        :type output_dir: str
-        :param score_thresh: the threshold of detection confidence.
-        :type score_thresh: float
-        :param visualization: whether to draw box and save images.
-        :type visualization: bool
+        Args:
+            paths (list[str]): The paths of images.
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]
+            batch_size (int): batch size.
+            use_gpu (bool): Whether to use gpu.
+            output_dir (str): The path to store output images.
+            visualization (bool): Whether to save image or not.
+            score_thresh (float): threshold for object detecion.
+
+        Returns:
+            res (list[dict]): The result of coco2017 detecion. keys include 'data', 'save_path', the corresponding value is:
+                data (dict): the result of object detection, keys include 'left', 'top', 'right', 'bottom', 'label', 'confidence', the corresponding value is:
+                    left (float): The X coordinate of the upper left corner of the bounding box;
+                    top (float): The Y coordinate of the upper left corner of the bounding box;
+                    right (float): The X coordinate of the lower right corner of the bounding box;
+                    bottom (float): The Y coordinate of the lower right corner of the bounding box;
+                    label (str): The label of detection result;
+                    confidence (float): The confidence of detection result.
+                save_path (str, optional): The path to save output images.
         """
-        all_images = []
-        paths = paths if paths else []
-        for yield_data in self.faster_rcnn.test_reader(paths, images):
+        paths = paths if paths else list()
+        if data and 'image' in data:
+            paths += data['image']
+
+        all_images = list()
+        for yield_data in test_reader(paths, images):
             all_images.append(yield_data)
+
         images_num = len(all_images)
         loop_num = ceil(images_num / batch_size)
         res = []
+
         for iter_id in range(loop_num):
             batch_data = []
             handle_id = iter_id * batch_size
+
             for image_id in range(batch_size):
                 try:
                     batch_data.append(all_images[handle_id + image_id])
                 except:
                     pass
-            padding_image, padding_info, padding_shape = self.faster_rcnn.padding_minibatch(
+
+            padding_image, padding_info, padding_shape = padding_minibatch(
                 batch_data, coarsest_stride=32, use_padded_im_info=True)
             padding_image_tensor = PaddleTensor(padding_image.copy())
             padding_info_tensor = PaddleTensor(padding_info.copy())
@@ -228,12 +332,13 @@ class FasterRCNNResNet50RPN(hub.Module):
             feed_list = [
                 padding_image_tensor, padding_info_tensor, padding_shape_tensor
             ]
+
             if use_gpu:
                 data_out = self.gpu_predictor.run(feed_list)
             else:
                 data_out = self.cpu_predictor.run(feed_list)
 
-            output = self.faster_rcnn.postprocess(
+            output = postprocess(
                 paths=paths,
                 images=images,
                 data_out=data_out,
@@ -243,6 +348,7 @@ class FasterRCNNResNet50RPN(hub.Module):
                 handle_id=handle_id,
                 visualization=visualization)
             res += output
+
         return res
 
     def add_module_config_arg(self):
@@ -269,7 +375,7 @@ class FasterRCNNResNet50RPN(hub.Module):
             '--input_path', type=str, default=None, help="input data")
 
         self.arg_input_group.add_argument(
-            '--input_path',
+            '--input_file',
             type=str,
             default=None,
             help="file contain input data")
@@ -285,6 +391,15 @@ class FasterRCNNResNet50RPN(hub.Module):
                 input_data = txt_parser.parse(args.input_file, use_strip=True)
         return input_data
 
+    @serving
+    def serving_method(self, images, **kwargs):
+        """
+        Run as a service.
+        """
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.object_detection(images_decode, **kwargs)
+        return results
+
     @runnable
     def run_cmd(self, argvs):
         self.parser = argparse.ArgumentParser(

hub_module/modules/image/object_detection/ssd/processor.py → hub_module/modules/image/object_detection/faster_rcnn_resnet50_fpn_coco2017/processor.py

 # coding=utf-8
+import base64
 import os
 
+import cv2
 import numpy as np
 from PIL import Image, ImageDraw
 
 __all__ = [
-    'get_save_image_name', 'draw_bounding_box_on_image', 'clip_bbox',
-    'load_label_info'
+    'base64_to_cv2',
+    'load_label_info',
+    'postprocess',
 ]
 
 
+def base64_to_cv2(b64str):
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.fromstring(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+
 def get_save_image_name(img, output_dir, image_path):
     """Get save image name from source image path.
     """
@@ -62,7 +72,6 @@ def draw_bounding_box_on_image(image_path, data_list, save_dir):
         os.remove(save_name)
 
     image.save(save_name)
-
     return save_name
 
 
@@ -91,28 +100,34 @@ def postprocess(paths,
                 output_dir,
                 handle_id,
                 visualization=True):
-    """postprocess the lod_tensor produced by fluid.Executor.run
-
-    :param paths: the path of images.
-    :type paths: list, each element is a str
-    :param images: data of images, [N, H, W, C]
-    :type images: numpy.ndarray
-    :param data_out: data produced by executor.run
-    :type data_out: lod_tensor
-    :param score_thresh: the low limit of bounding box.
-    :type score_thresh: float
-    :param label_names: label names
-    :type label_names: list
-    :param output_dir: output directory.
-    :type output_dir: str
-    :param handle_id: The number of images that have been handled.
-    :type handle_id: int
-    :param visualization: whether to draw bbox.
-    :param visualization: bool
+    """
+    postprocess the lod_tensor produced by fluid.Executor.run
+
+    Args:
+        paths (list[str]): the path of images.
+        images (list(numpy.ndarray)):  list of images, shape of each is [H, W, C].
+        data_out (lod_tensor): data produced by executor.run.
+        score_thresh (float): the low limit of bounding box.
+        label_names (list[str]): label names.
+        output_dir (str): output directory.
+        handle_id (int): The number of images that have been handled.
+        visualization (bool): whether to save as images.
+
+    Returns:
+        res (list[dict]): The result of vehicles detecion. keys include 'data', 'save_path', the corresponding value is:
+            data (dict): the result of object detection, keys include 'left', 'top', 'right', 'bottom', 'label', 'confidence', the corresponding value is:
+                left (float): The X coordinate of the upper left corner of the bounding box;
+                top (float): The Y coordinate of the upper left corner of the bounding box;
+                right (float): The X coordinate of the lower right corner of the bounding box;
+                bottom (float): The Y coordinate of the lower right corner of the bounding box;
+                label (str): The label of detection result;
+                confidence (float): The confidence of detection result.
+            save_path (str): The path to save output images.
     """
     lod_tensor = data_out[0]
     lod = lod_tensor.lod[0]
     results = lod_tensor.as_ndarray()
+
     if handle_id < len(paths):
         unhandled_paths = paths[handle_id:]
         unhandled_paths_num = len(unhandled_paths)
@@ -146,10 +161,6 @@ def postprocess(paths,
             category_id = int(row[0])
             confidence = row[1]
             bbox = row[2:]
-            bbox[0] = bbox[0] * org_img_width
-            bbox[1] = bbox[1] * org_img_height
-            bbox[2] = bbox[2] * org_img_width
-            bbox[3] = bbox[3] * org_img_height
             dt = {}
             dt['label'] = label_names[category_id]
             dt['confidence'] = confidence

hub_module/modules/image/object_detection/faster_rcnn/roi_extractor.py → hub_module/modules/image/object_detection/faster_rcnn_resnet50_fpn_coco2017/roi_extractor.py

 # coding=utf-8
 import paddle.fluid as fluid
 
-__all__ = ['RoIAlign', 'FPNRoIAlign']
-
-
-class RoIAlign(object):
-    # __op__ = fluid.layers.roi_align
-    def __init__(self, resolution=7, spatial_scale=0.0625, sampling_ratio=0):
-        super(RoIAlign, self).__init__()
-        if isinstance(resolution, int):
-            resolution = [resolution, resolution]
-        self.pooled_height = resolution[0]
-        self.pooled_width = resolution[1]
-        self.spatial_scale = spatial_scale
-        self.sampling_ratio = sampling_ratio
+__all__ = ['FPNRoIAlign']
 
 
 class FPNRoIAlign(object):

hub_module/modules/image/object_detection/retinanet_resnet50_fpn_coco2017/README.md

+```shell
+$ hub install retinanet_resnet50_fpn_coco2017==1.0.0
+```
+
+## 命令行预测
+
+```
+hub run retinanet_resnet50_fpn_coco2017 --input_path "/PATH/TO/IMAGE"
+```
+
+## API
+
+```
+def context(trainable=True,
+            pretrained=True,
+            get_prediction=False)
+```
+
+特征提取，用于迁移学习。
+
+**参数**
+
+* trainable(bool): 将参数的trainable属性设为trainable；
+* pretrained (bool): 是否加载预训练模型；
+* get\_prediction (bool): 是否执行预测。
+
+**返回**
+
+* inputs (dict): 模型的输入，keys 包括 'image', 'im\_size'，相应的取值为：
+    * image (Variable): 图像变量
+    * im\_size (Variable): 图片的尺寸
+* outputs (dict): 模型的输出。如果 get\_prediction 为 False，输出 'head\_fatures'，否则输出 'bbox\_out'。
+* context\_prog (Program): 用于迁移学习的 Program.
+
+```python
+def object_detection(paths=None,
+                     images=None,
+                     batch_size=1,
+                     use_gpu=False,
+                     output_dir='detection_result',
+                     score_thresh=0.5,
+                     visualization=True)
+```
+
+预测API，检测输入图片中的所有目标的位置。
+
+**参数**
+
+* paths (list\[str\]): 图片的路径；
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，BGR格式；
+* batch\_size (int): batch 的大小；
+* use\_gpu (bool): 是否使用 GPU；
+* score\_thresh (float): 识别置信度的阈值；
+* visualization (bool): 是否将识别结果保存为图片文件；
+* output\_dir (str): 图片的保存路径，默认设为 detection\_result；
+
+**返回**
+
+* res (list\[dict\]): 识别结果的列表，列表中每一个元素为 dict，各字段为：
+    * data (list): 检测结果，list的每一个元素为 dict，各字段为:
+        * confidence (float): 识别的置信度；
+        * label (str): 标签；
+        * left (int): 边界框的左上角x坐标；
+        * top (int): 边界框的左上角y坐标；
+        * right (int): 边界框的右下角x坐标；
+        * bottom (int): 边界框的右下角y坐标；
+    * save\_path (str, optional): 识别结果的保存路径 (仅当visualization=True时存在)。
+
+```python
+def save_inference_model(dirname,
+                         model_filename=None,
+                         params_filename=None,
+                         combined=True)
+```
+
+将模型保存到指定路径。
+
+**参数**
+
+* dirname: 存在模型的目录名称
+* model\_filename: 模型文件名称，默认为\_\_model\_\_
+* params\_filename: 参数文件名称，默认为\_\_params\_\_(仅当`combined`为True时生效)
+* combined: 是否将参数保存到统一的一个文件中
+
+## 代码示例
+
+```python
+import paddlehub as hub
+import cv2
+
+object_detector = hub.Module(name="retinanet_resnet50_fpn_coco2017")
+result = object_detector.object_detection(images=[cv2.imread('/PATH/TO/IMAGE')])
+# or
+# result = object_detector.object_detection((paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving可以部署一个目标检测的在线服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m retinanet_resnet50_fpn_coco2017
+```
+
+这样就完成了一个目标检测的服务化API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/retinanet_resnet50_fpn_coco2017"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+### 依赖
+
+paddlepaddle >= 1.6.2
+
+paddlehub >= 1.6.0

hub_module/modules/image/object_detection/retinanet_resnet50_fpn_coco2017/data_feed.py

@@ -15,13 +15,19 @@ __all__ = ['test_reader', 'padding_minibatch']
 
 
 def test_reader(paths=None, images=None):
-    """data generator
-    :param paths: path to images.
-    :type paths: list, each element is a str
-    :param images: data of images, [N, H, W, C]
-    :type images: numpy.ndarray
     """
-    img_list = []
+    data generator
+
+    Args:
+        paths (list[str]): paths to images.
+        images (list(numpy.ndarray)): data of images, shape of each is [H, W, C]
+
+    Yield:
+        res (dict): key contains 'image' and 'im_info', the corresponding values is:
+            image (numpy.ndarray): the image to be fed into network
+            im_info (numpy.ndarray): the info about the preprocessed.
+    """
+    img_list = list()
     if paths:
         for img_path in paths:
             assert os.path.isfile(
@@ -83,9 +89,9 @@ def padding_minibatch(batch_data, coarsest_stride=0, use_padded_im_info=True):
     else:
         max_shape = max_shape_org.astype('int32')
 
-    padding_image = []
-    padding_info = []
-    padding_shape = []
+    padding_image = list()
+    padding_info = list()
+    padding_shape = list()
 
     for data in batch_data:
         im_c, im_h, im_w = data['image'].shape

hub_module/modules/image/object_detection/retinanet_resnet50_fpn_coco2017/module.py

@@ -11,13 +11,13 @@ from functools import partial
 import numpy as np
 import paddle.fluid as fluid
 import paddlehub as hub
-from paddlehub.module.module import moduleinfo, runnable
+from paddlehub.module.module import moduleinfo, runnable, serving
 from paddle.fluid.core import PaddleTensor, AnalysisConfig, create_paddle_predictor
 from paddlehub.io.parser import txt_parser
 
 from retinanet_resnet50_fpn_coco2017.fpn import FPN
 from retinanet_resnet50_fpn_coco2017.retina_head import AnchorGenerator, RetinaTargetAssign, RetinaOutputDecoder, RetinaHead
-from retinanet_resnet50_fpn_coco2017.processor import load_label_info, postprocess
+from retinanet_resnet50_fpn_coco2017.processor import load_label_info, postprocess, base64_to_cv2
 from retinanet_resnet50_fpn_coco2017.data_feed import test_reader, padding_minibatch
 from retinanet_resnet50_fpn_coco2017.resnet import ResNet
 
@@ -29,7 +29,7 @@ from retinanet_resnet50_fpn_coco2017.resnet import ResNet
     summary=
     "Baidu's RetinaNet model for object detection, with backbone ResNet50 and FPN.",
     author="paddlepaddle",
-    author_email="paddle-dev@baidu.com")
+    author_email="")
 class RetinaNetResNet50FPN(hub.Module):
     def _initialize(self):
         # default pretrained model of Retinanet_ResNet50_FPN, the shape of input image tensor is (3, 608, 608)
@@ -69,16 +69,19 @@ class RetinaNetResNet50FPN(hub.Module):
                 trainable=True,
                 pretrained=True,
                 get_prediction=False):
-        """Distill the Head Features, so as to perform transfer learning.
+        """
+        Distill the Head Features, so as to perform transfer learning.
+
+        Args:
+            num_classes (int): number of classes.
+            trainable (bool): whether to set parameters trainable.
+            pretrained (bool): whether to load default pretrained model.
+            get_prediction (bool): whether to get prediction.
 
-        :param trainable: whether to set parameters trainable.
-        :type trainable: bool
-        :param pretrained: whether to load default pretrained model.
-        :type pretrained: bool
-        :param get_prediction: whether to get prediction,
-            if True, outputs is {'bbox_out': bbox_out},
-            if False, outputs is {'head_features': head_features}.
-        :type get_prediction: bool
+        Returns:
+             inputs(dict): the input variables.
+             outputs(dict): the output variables.
+             context_prog (Program): the program to execute transfer learning.
         """
         context_prog = fluid.Program()
         startup_program = fluid.Program()
@@ -166,31 +169,38 @@ class RetinaNetResNet50FPN(hub.Module):
                          score_thresh=0.5,
                          visualization=True):
         """API of Object Detection.
-        :param paths: the path of images.
-        :type paths: list, each element is correspond to the path of an image.
-        :param images: data of images, [N, H, W, C]
-        :type images: numpy.ndarray
-        :param use_gpu: whether to use gpu or not.
-        :type use_gpu: bool
-        :param batch_size: bathc size.
-        :type batch_size: int
-        :param output_dir: the directory to store the detection result.
-        :type output_dir: str
-        :param score_thresh: the threshold of detection confidence.
-        :type score_thresh: float
-        :param visualization: whether to draw bounding box and save images.
-        :type visualization: bool
+
+        Args:
+            paths (list[str]): The paths of images.
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]
+            batch_size (int): batch size.
+            use_gpu (bool): Whether to use gpu.
+            output_dir (str): The path to store output images.
+            visualization (bool): Whether to save image or not.
+            score_thresh (float): threshold for object detecion.
+            visualization (bool): whether to save result as images.
+
+        Returns:
+            res (list[dict]): The result of coco2017 detecion. keys include 'data', 'save_path', the corresponding value is:
+                data (dict): the result of object detection, keys include 'left', 'top', 'right', 'bottom', 'label', 'confidence', the corresponding value is:
+                    left (float): The X coordinate of the upper left corner of the bounding box;
+                    top (float): The Y coordinate of the upper left corner of the bounding box;
+                    right (float): The X coordinate of the lower right corner of the bounding box;
+                    bottom (float): The Y coordinate of the lower right corner of the bounding box;
+                    label (str): The label of detection result;
+                    confidence (float): The confidence of detection result.
+                save_path (str, optional): The path to save output images.
         """
-        all_images = []
-        paths = paths if paths else []
+        all_images = list()
+        paths = paths if paths else list()
         for yield_data in test_reader(paths, images):
             all_images.append(yield_data)
 
         images_num = len(all_images)
         loop_num = int(np.ceil(images_num / batch_size))
-        res = []
+        res = list()
         for iter_id in range(loop_num):
-            batch_data = []
+            batch_data = list()
             handle_id = iter_id * batch_size
             for image_id in range(batch_size):
                 try:
@@ -248,7 +258,7 @@ class RetinaNetResNet50FPN(hub.Module):
             help="file contain input data")
 
     def check_input_data(self, args):
-        input_data = []
+        input_data = list()
         if args.input_path:
             input_data = [args.input_path]
         elif args.input_file:
@@ -258,6 +268,15 @@ class RetinaNetResNet50FPN(hub.Module):
                 input_data = txt_parser.parse(args.input_file, use_strip=True)
         return input_data
 
+    @serving
+    def serving_method(self, images, **kwargs):
+        """
+        Run as a service.
+        """
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.object_detection(images_decode, **kwargs)
+        return results
+
     @runnable
     def run_cmd(self, argvs):
         self.parser = argparse.ArgumentParser(

hub_module/modules/image/object_detection/retinanet_resnet50_fpn_coco2017/processor.py

 # coding=utf-8
+import base64
 import os
 
+import cv2
 import numpy as np
 from PIL import Image, ImageDraw
 
 __all__ = [
-    'get_save_image_name', 'draw_bounding_box_on_image', 'clip_bbox',
-    'load_label_info'
+    'base64_to_cv2',
+    'load_label_info',
+    'postprocess',
 ]
 
 
+def base64_to_cv2(b64str):
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.fromstring(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+
 def get_save_image_name(img, output_dir, image_path):
     """Get save image name from source image path.
     """
@@ -80,24 +90,29 @@ def load_label_info(file_path):
 
 def postprocess(paths, images, data_out, score_thresh, label_names, output_dir,
                 handle_id, visualization):
-    """postprocess the lod_tensor produced by fluid.Executor.run
-
-    :param paths: the path of images.
-    :type paths: list, each element is a str
-    :param images: data of images, [N, H, W, C]
-    :type images: numpy.ndarray
-    :param data_out: data produced by executor.run
-    :type data_out: lod_tensor
-    :param score_thresh: the low limit of bounding box.
-    :type score_thresh: float
-    :param label_names: label names
-    :type label_names: list
-    :param output_dir: output directory.
-    :type output_dir: str
-    :param handle_id: The number of images that have been handled.
-    :type handle_id: int
-    :param visualization: whether to draw bbox.
-    :param visualization: bool
+    """
+    postprocess the lod_tensor produced by fluid.Executor.run
+
+    Args:
+        paths (list[str]): the path of images.
+        images (list(numpy.ndarray)):  list of images, shape of each is [H, W, C].
+        data_out (lod_tensor): data produced by executor.run.
+        score_thresh (float): the low limit of bounding box.
+        label_names (list[str]): label names.
+        output_dir (str): output directory.
+        handle_id (int): The number of images that have been handled.
+        visualization (bool): whether to save as images.
+
+    Returns:
+        res (list[dict]): The result of vehicles detecion. keys include 'data', 'save_path', the corresponding value is:
+            data (dict): the result of object detection, keys include 'left', 'top', 'right', 'bottom', 'label', 'confidence', the corresponding value is:
+                left (float): The X coordinate of the upper left corner of the bounding box;
+                top (float): The Y coordinate of the upper left corner of the bounding box;
+                right (float): The X coordinate of the lower right corner of the bounding box;
+                bottom (float): The Y coordinate of the lower right corner of the bounding box;
+                label (str): The label of detection result;
+                confidence (float): The confidence of detection result.
+            save_path (str): The path to save output images.
     """
     lod_tensor = data_out[0]
     lod = lod_tensor.lod[0]

hub_module/modules/image/object_detection/ssd/module.py

-# coding=utf-8
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
-from collections import OrderedDict
-
-import paddle.fluid as fluid
-import paddlehub as hub
-from paddlehub.module.module import moduleinfo
-from paddlehub.common.paddle_helper import add_vars_prefix
-
-from ssd.data_feed import reader, DecodeImage, ResizeImage, NormalizeImage, Permute
-from ssd.processor import load_label_info, postprocess
-from ssd.multi_box_head import MultiBoxHead
-from ssd.output_decoder import SSDOutputDecoder
-
-
-@moduleinfo(
-    name="ssd",
-    version="1.0.0",
-    type="cv/object_detection",
-    summary=
-    "SSD (Single Shot MultiBox Detector) is a object detection model, which trained with PASCAL VOC dataset.",
-    author="paddlepaddle",
-    author_email="paddle-dev@baidu.com")
-class SSD(hub.Module):
-    def _initialize(self):
-        self.reader = reader
-        self.load_label_info = load_label_info
-        self.postprocess = postprocess
-        self.MultiBoxHead = MultiBoxHead
-        self.SSDOutputDecoder = SSDOutputDecoder
-        self.DecodeImage = DecodeImage
-        self.ResizeImage = ResizeImage
-        self.NormalizeImage = NormalizeImage
-        self.Permute = Permute
-
-    def context(self,
-                body_feats,
-                multi_box_head,
-                ssd_output_decoder,
-                image,
-                trainable=True,
-                var_prefix='',
-                get_prediction=False):
-        """Distill the Head Features, so as to perform transfer learning.
-
-        :param body_feats: feature mps of backbone outputs
-        :type body_feats: list
-        :param multi_box_head: SSD head of MultiBoxHead.
-        :type multi_box_head: <class 'MultiBoxHead' object>
-        :param ssd_output_decoder: SSD output decoder
-        :type ssd_output_decoder: <class 'SSDOutputDecoder' object>
-        :param image: image tensor.
-        :type image: <class 'paddle.fluid.framework.Variable'>
-        :param trainable: whether to set parameters trainable.
-        :type trainable: bool
-        :param var_prefix: the prefix of variables in ssd
-        :type var_prefix: str
-        :param get_prediction: whether to get prediction,
-            if True, outputs is bbox_out,
-            if False, outputs is body_features.
-        :type get_prediction: bool
-        """
-        context_prog = image.block.program
-        with fluid.program_guard(context_prog):
-            im_size = fluid.layers.data(
-                name='im_size', shape=[2], dtype='int32')
-            inputs = {
-                'image': var_prefix + image.name,
-                'im_size': var_prefix + im_size.name
-            }
-            if not get_prediction:
-                outputs = {
-                    'body_features':
-                    [var_prefix + var.name for var in body_feats]
-                }
-            else:
-                locs, confs, box, box_var = fluid.layers.multi_box_head(
-                    inputs=body_feats,
-                    image=image,
-                    base_size=multi_box_head.base_size,
-                    num_classes=multi_box_head.num_classes,
-                    aspect_ratios=multi_box_head.aspect_ratios,
-                    min_ratio=multi_box_head.min_ratio,
-                    max_ratio=multi_box_head.max_ratio,
-                    min_sizes=multi_box_head.min_sizes,
-                    max_sizes=multi_box_head.max_sizes,
-                    steps=multi_box_head.steps,
-                    offset=multi_box_head.offset,
-                    flip=multi_box_head.flip,
-                    kernel_size=multi_box_head.kernel_size,
-                    pad=multi_box_head.pad,
-                    min_max_aspect_ratios_order=multi_box_head.
-                    min_max_aspect_ratios_order)
-                pred = fluid.layers.detection_output(
-                    loc=locs,
-                    scores=confs,
-                    prior_box=box,
-                    prior_box_var=box_var,
-                    nms_threshold=ssd_output_decoder.nms_threshold,
-                    nms_top_k=ssd_output_decoder.nms_top_k,
-                    keep_top_k=ssd_output_decoder.keep_top_k,
-                    score_threshold=ssd_output_decoder.score_threshold,
-                    nms_eta=ssd_output_decoder.nms_eta,
-                    background_label=ssd_output_decoder.background_label)
-                outputs = {'bbox_out': var_prefix + pred.name}
-
-            add_vars_prefix(context_prog, var_prefix)
-            add_vars_prefix(fluid.default_startup_program(), var_prefix)
-            inputs = {
-                key: context_prog.global_block().vars[value]
-                for key, value in inputs.items()
-            }
-            outputs = {
-                key: [
-                    context_prog.global_block().vars[varname]
-                    for varname in value
-                ]
-                for key, value in outputs.items()
-            }
-
-            for param in context_prog.global_block().iter_parameters():
-                param.trainable = trainable
-
-            return inputs, outputs, context_prog

hub_module/modules/image/object_detection/ssd/multi_box_head.py

-# coding=utf-8
-class MultiBoxHead(object):
-    # __op__ = fluid.layers.multi_box_head
-    def __init__(self,
-                 base_size,
-                 num_classes,
-                 aspect_ratios,
-                 min_ratio=None,
-                 max_ratio=None,
-                 min_sizes=None,
-                 max_sizes=None,
-                 steps=None,
-                 offset=0.5,
-                 flip=True,
-                 kernel_size=1,
-                 pad=0,
-                 min_max_aspect_ratios_order=False):
-        self.base_size = base_size
-        self.num_classes = num_classes
-        self.aspect_ratios = aspect_ratios
-        self.min_ratio = min_ratio
-        self.max_ratio = max_ratio
-        self.min_sizes = min_sizes
-        self.max_sizes = max_sizes
-        self.steps = steps
-        self.offset = offset
-        self.flip = flip
-        self.kernel_size = kernel_size
-        self.pad = pad
-        self.min_max_aspect_ratios_order = min_max_aspect_ratios_order

hub_module/modules/image/object_detection/ssd/output_decoder.py

-class SSDOutputDecoder(object):
-    # __op__ = fluid.layers.detection_output
-    def __init__(self,
-                 nms_threshold=0.3,
-                 nms_top_k=400,
-                 keep_top_k=200,
-                 score_threshold=0.01,
-                 nms_eta=1.0,
-                 background_label=0):
-        self.nms_threshold = nms_threshold
-        self.background_label = background_label
-        self.nms_top_k = nms_top_k
-        self.keep_top_k = keep_top_k
-        self.score_threshold = score_threshold
-        self.nms_eta = nms_eta

hub_module/modules/image/object_detection/ssd_mobilenet_v1_pascal/README.md

+```shell
+$ hub install ssd_mobilenet_v1_pascal==1.1.0
+```
+
+## 命令行预测
+
+```
+hub run ssd_mobilenet_v1_pascal --input_path "/PATH/TO/IMAGE"
+```
+
+## API
+
+```
+def context(trainable=True,
+            pretrained=True,
+            get_prediction=False)
+```
+
+特征提取，用于迁移学习。
+
+**参数**
+
+* trainable(bool): 设置参数的 trainable 属性；
+* pretrained (bool): 是否加载预训练模型；
+* get\_prediction (bool): 是否执行预测。
+
+**返回**
+
+* inputs (dict): 模型的输入，keys 包括 'image', 'im\_size'，相应的取值为：
+    * image (Variable): 图像变量
+    * im\_size (Variable): 图片的尺寸
+* outputs (dict): 模型的输出。如果 get\_prediction 为 False，输出 'head\_fatures'，否则输出 'bbox\_out'。
+* context\_prog (Program): 用于迁移学习的 Program.
+
+```python
+def object_detection(paths=None,
+                     images=None,
+                     batch_size=1,
+                     use_gpu=False,
+                     output_dir='detection_result',
+                     score_thresh=0.5,
+                     visualization=True)
+```
+
+预测API，检测输入图片中的所有目标的位置。
+
+**参数**
+
+* paths (list\[str\]): 图片的路径；
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，BGR格式；
+* batch\_size (int): batch 的大小；
+* use\_gpu (bool): 是否使用 GPU；
+* score\_thresh (float): 识别置信度的阈值；
+* visualization (bool): 是否将识别结果保存为图片文件；
+* output\_dir (str): 图片的保存路径，默认设为 detection\_result；
+
+**返回**
+
+* res (list\[dict\]): 识别结果的列表，列表中每一个元素为 dict，各字段为：
+    * data (list): 检测结果，list的每一个元素为 dict，各字段为:
+        * confidence (float): 识别的置信度；
+        * label (str): 标签；
+        * left (int): 边界框的左上角x坐标；
+        * top (int): 边界框的左上角y坐标；
+        * right (int): 边界框的右下角x坐标；
+        * bottom (int): 边界框的右下角y坐标；
+    * save\_path (str, optional): 识别结果的保存路径 (仅当visualization=True时存在)。
+
+```python
+def save_inference_model(dirname,
+                         model_filename=None,
+                         params_filename=None,
+                         combined=True)
+```
+
+将模型保存到指定路径。
+
+**参数**
+
+* dirname: 存在模型的目录名称
+* model\_filename: 模型文件名称，默认为\_\_model\_\_
+* params\_filename: 参数文件名称，默认为\_\_params\_\_(仅当`combined`为True时生效)
+* combined: 是否将参数保存到统一的一个文件中
+
+## 代码示例
+
+```python
+import paddlehub as hub
+import cv2
+
+object_detector = hub.Module(name="ssd_mobilenet_v1_pascal")
+result = object_detector.object_detection(images=[cv2.imread('/PATH/TO/IMAGE')])
+# or
+# result = object_detector.object_detection((paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving可以部署一个目标检测的在线服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m ssd_mobilenet_v1_pascal
+```
+
+这样就完成了一个目标检测的服务化API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/ssd_mobilenet_v1_pascal"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+### 依赖
+
+paddlepaddle >= 1.6.2
+
+paddlehub >= 1.6.0

hub_module/modules/image/object_detection/ssd_mobilenet_v1_pascal/config.yml

+MobileNet:
+  norm_decay: 0.
+  conv_group_scale: 1
+  conv_learning_rate: 0.1
+  extra_block_filters: [[256, 512], [128, 256], [128, 256], [64, 128]]
+  with_extra_blocks: True
+
 SSDOutputDecoder:
   background_label: 0
   keep_top_k: 200
@@ -9,7 +16,7 @@ SSDOutputDecoder:
 MultiBoxHead:
   aspect_ratios: [[2.], [2., 3.], [2., 3.], [2., 3.], [2., 3.], [2., 3.]]
   base_size: 300
-  flip: true
+  flip: True
   max_ratio: 90
   max_sizes: [[], 150.0, 195.0, 240.0, 285.0, 300.0]
   min_ratio: 20

hub_module/modules/image/object_detection/ssd_mobilenet_v1_pascal/data_feed.py

+# coding=utf-8
+from __future__ import absolute_import
+from __future__ import print_function
+from __future__ import division
+
+import os
+import random
+from collections import OrderedDict
+
+import cv2
+import numpy as np
+from PIL import Image
+from paddle import fluid
+
+__all__ = ['reader']
+
+
+class DecodeImage(object):
+    def __init__(self, to_rgb=True, with_mixup=False):
+        """ Transform the image data to numpy format.
+
+        Args:
+            to_rgb (bool): whether to convert BGR to RGB
+            with_mixup (bool): whether or not to mixup image and gt_bbbox/gt_score
+        """
+        self.to_rgb = to_rgb
+        self.with_mixup = with_mixup
+
+    def __call__(self, im):
+        if self.to_rgb:
+            im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
+
+        return im
+
+
+class ResizeImage(object):
+    def __init__(self,
+                 target_size=0,
+                 max_size=0,
+                 interp=cv2.INTER_LINEAR,
+                 use_cv2=True):
+        """
+        Rescale image to the specified target size, and capped at max_size
+        if max_size != 0.
+        If target_size is list, selected a scale randomly as the specified
+        target size.
+
+        Args:
+            target_size (int|list): the target size of image's short side,
+                multi-scale training is adopted when type is list.
+            max_size (int): the max size of image
+            interp (int): the interpolation method
+            use_cv2 (bool): use the cv2 interpolation method or use PIL
+                interpolation method
+        """
+        self.max_size = int(max_size)
+        self.interp = int(interp)
+        self.use_cv2 = use_cv2
+        self.target_size = target_size
+
+    def __call__(self, im):
+        if not isinstance(im, np.ndarray):
+            raise TypeError("{}: image type is not numpy.".format(self))
+        if len(im.shape) != 3:
+            raise ValueError('{}: image is not 3-dimensional.'.format(self))
+        im_shape = im.shape
+        im_size_min = np.min(im_shape[0:2])
+        im_size_max = np.max(im_shape[0:2])
+        if isinstance(self.target_size, list):
+            # Case for multi-scale training
+            selected_size = random.choice(self.target_size)
+        else:
+            selected_size = self.target_size
+        if float(im_size_min) == 0:
+            raise ZeroDivisionError('{}: min size of image is 0'.format(self))
+        if self.max_size != 0:
+            im_scale = float(selected_size) / float(im_size_min)
+            # Prevent the biggest axis from being more than max_size
+            if np.round(im_scale * im_size_max) > self.max_size:
+                im_scale = float(self.max_size) / float(im_size_max)
+            im_scale_x = im_scale
+            im_scale_y = im_scale
+
+            resize_w = im_scale_x * float(im_shape[1])
+            resize_h = im_scale_y * float(im_shape[0])
+            im_info = [resize_h, resize_w, im_scale]
+        else:
+            im_scale_x = float(selected_size) / float(im_shape[1])
+            im_scale_y = float(selected_size) / float(im_shape[0])
+
+            resize_w = selected_size
+            resize_h = selected_size
+
+        if self.use_cv2:
+            im = cv2.resize(
+                im,
+                None,
+                None,
+                fx=im_scale_x,
+                fy=im_scale_y,
+                interpolation=self.interp)
+        else:
+            if self.max_size != 0:
+                raise TypeError(
+                    'If you set max_size to cap the maximum size of image,'
+                    'please set use_cv2 to True to resize the image.')
+            im = im.astype('uint8')
+            im = Image.fromarray(im)
+            im = im.resize((int(resize_w), int(resize_h)), self.interp)
+            im = np.array(im)
+
+        return im
+
+
+class NormalizeImage(object):
+    def __init__(self,
+                 mean=[0.485, 0.456, 0.406],
+                 std=[1, 1, 1],
+                 is_scale=True,
+                 is_channel_first=True):
+        """
+        Args:
+            mean (list): the pixel mean
+            std (list): the pixel variance
+        """
+        self.mean = mean
+        self.std = std
+        self.is_scale = is_scale
+        self.is_channel_first = is_channel_first
+
+    def __call__(self, im):
+        """Normalize the image.
+
+        Operators:
+            1.(optional) Scale the image to [0,1]
+            2. Each pixel minus mean and is divided by std
+        """
+        im = im.astype(np.float32, copy=False)
+        if self.is_channel_first:
+            mean = np.array(self.mean)[:, np.newaxis, np.newaxis]
+            std = np.array(self.std)[:, np.newaxis, np.newaxis]
+        else:
+            mean = np.array(self.mean)[np.newaxis, np.newaxis, :]
+            std = np.array(self.std)[np.newaxis, np.newaxis, :]
+        if self.is_scale:
+            im = im / 255.0
+        im -= mean
+        im /= std
+        return im
+
+
+class Permute(object):
+    def __init__(self, to_bgr=True, channel_first=True):
+        """
+        Change the channel.
+
+        Args:
+            to_bgr (bool): confirm whether to convert RGB to BGR
+            channel_first (bool): confirm whether to change channel
+        """
+        self.to_bgr = to_bgr
+        self.channel_first = channel_first
+
+    def __call__(self, im):
+        if self.channel_first:
+            im = np.swapaxes(im, 1, 2)
+            im = np.swapaxes(im, 1, 0)
+        if self.to_bgr:
+            im = im[[2, 1, 0], :, :]
+        return im
+
+
+def reader(paths=[],
+           images=None,
+           decode_image=DecodeImage(to_rgb=True, with_mixup=False),
+           resize_image=ResizeImage(
+               target_size=512, interp=1, max_size=0, use_cv2=False),
+           permute_image=Permute(to_bgr=False),
+           normalize_image=NormalizeImage(
+               mean=[104, 117, 123], std=[1, 1, 1], is_scale=False)):
+    """
+    data generator
+
+    Args:
+        paths (list[str]): paths to images.
+        images (list(numpy.ndarray)): data of images, shape of each is [H, W, C]
+        decode_image (class object): instance of <class 'DecodeImage' object>
+        resize_image (class object): instance of <class 'ResizeImage' object>
+        permute_image (class object): instance of <class 'Permute' object>
+        normalize_image (class object): instance of <class 'NormalizeImage' object>
+    """
+    img_list = []
+    if paths is not None:
+        assert type(paths) is list, "type(paths) is not list."
+        for img_path in paths:
+            assert os.path.isfile(
+                img_path), "The {} isn't a valid file path.".format(img_path)
+            img = cv2.imread(img_path).astype('float32')
+            img_list.append(img)
+    if images is not None:
+        for img in images:
+            img_list.append(img)
+
+    decode_image = DecodeImage(to_rgb=True, with_mixup=False)
+    resize_image = ResizeImage(
+        target_size=300, interp=1, max_size=0, use_cv2=False)
+    permute_image = Permute()
+    normalize_image = NormalizeImage(
+        mean=[127.5, 127.5, 127.5],
+        std=[127.502231, 127.502231, 127.502231],
+        is_scale=False)
+
+    for img in img_list:
+        preprocessed_img = decode_image(img)
+        preprocessed_img = resize_image(preprocessed_img)
+        preprocessed_img = permute_image(preprocessed_img)
+        preprocessed_img = normalize_image(preprocessed_img)
+        yield [preprocessed_img]

hub_module/modules/image/object_detection/ssd_mobilenet_v1_pascal/module.py

 # coding=utf-8
 from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
 
-import os
 import ast
 import argparse
+import os
 from functools import partial
 
+import yaml
 import numpy as np
 import paddle.fluid as fluid
 import paddlehub as hub
-from paddlehub.module.module import moduleinfo, runnable
 from paddle.fluid.core import PaddleTensor, AnalysisConfig, create_paddle_predictor
-from paddlehub.io.parser import txt_parser
-import yaml
+from paddlehub.module.module import moduleinfo, runnable, serving
+from paddlehub.common.paddle_helper import add_vars_prefix
 
 from ssd_mobilenet_v1_pascal.mobilenet_v1 import MobileNet
+from ssd_mobilenet_v1_pascal.processor import load_label_info, postprocess, base64_to_cv2
+from ssd_mobilenet_v1_pascal.data_feed import reader
 
 
 @moduleinfo(
@@ -25,25 +25,18 @@ from ssd_mobilenet_v1_pascal.mobilenet_v1 import MobileNet
     type="cv/object_detection",
     summary="SSD with backbone MobileNet_V1, trained with dataset Pasecal VOC.",
     author="paddlepaddle",
-    author_email="paddle-dev@baidu.com")
+    author_email="")
 class SSDMobileNetv1(hub.Module):
     def _initialize(self):
-        self.ssd = hub.Module(name="ssd")
-        # default pretrained model of SSD_MobileNet_V1_VOC, the shape of image tensor is (3, 300, 300)
         self.default_pretrained_model_path = os.path.join(
             self.directory, "ssd_mobilenet_v1_model")
-        self.label_names = self.ssd.load_label_info(
+        self.label_names = load_label_info(
             os.path.join(self.directory, "label_file.txt"))
-        self.infer_prog = None
-        self.image = None
-        self.bbox_out = None
+        self.model_config = None
         self._set_config()
-        self._config = None
 
     def _set_config(self):
-        """
-        predictor config setting
-        """
+        # predictor config setting.
         cpu_config = AnalysisConfig(self.default_pretrained_model_path)
         cpu_config.disable_glog_info()
         cpu_config.disable_gpu()
@@ -62,51 +55,92 @@ class SSDMobileNetv1(hub.Module):
             gpu_config.enable_use_gpu(memory_pool_init_size_mb=500, device_id=0)
             self.gpu_predictor = create_paddle_predictor(gpu_config)
 
-    def context(self,
-                num_classes=21,
-                trainable=True,
-                pretrained=True,
-                get_prediction=False):
-        """Distill the Head Features, so as to perform transfer learning.
+        # model config setting.
+        if not self.model_config:
+            with open(os.path.join(self.directory, 'config.yml')) as fp:
+                self.model_config = yaml.load(fp.read(), Loader=yaml.FullLoader)
+
+        self.multi_box_head_config = self.model_config['MultiBoxHead']
+        self.output_decoder_config = self.model_config['SSDOutputDecoder']
+        self.mobilenet_config = self.model_config['MobileNet']
+
+    def context(self, trainable=True, pretrained=True, get_prediction=False):
+        """
+        Distill the Head Features, so as to perform transfer learning.
+
+        Args:
+            trainable (bool): whether to set parameters trainable.
+            pretrained (bool): whether to load default pretrained model.
+            get_prediction (bool): whether to get prediction.
 
-        :param trainable: whether to set parameters trainable.
-        :type trainable: bool
-        :param pretrained: whether to load default pretrained model.
-        :type pretrained: bool
-        :param get_prediction: whether to get prediction,
-            if True, outputs is {'bbox_out': bbox_out},
-            if False, outputs is {'body_features': body_features}.
-        :type get_prediction: bool
+        Returns:
+             inputs(dict): the input variables.
+             outputs(dict): the output variables.
+             context_prog (Program): the program to execute transfer learning.
         """
-        wrapped_prog = fluid.Program()
+        context_prog = fluid.Program()
         startup_program = fluid.Program()
-        with fluid.program_guard(wrapped_prog, startup_program):
+        with fluid.program_guard(context_prog, startup_program):
             with fluid.unique_name.guard():
                 # image
                 image = fluid.layers.data(
                     name='image', shape=[3, 300, 300], dtype='float32')
-                backbone = MobileNet(
-                    norm_decay=0.,
-                    conv_group_scale=1,
-                    conv_learning_rate=0.1,
-                    extra_block_filters=[[256, 512], [128, 256], [128, 256],
-                                         [64, 128]],
-                    with_extra_blocks=True)
+                # backbone
+                backbone = MobileNet(**self.mobilenet_config)
+                # body_feats
                 body_feats = backbone(image)
-                # call ssd.context
-                inputs, outputs, context_prog = self.ssd.context(
-                    body_feats=body_feats,
-                    multi_box_head=self.ssd.MultiBoxHead(
-                        num_classes=num_classes, **self.multi_box_head_config),
-                    ssd_output_decoder=self.ssd.SSDOutputDecoder(
-                        **self.output_decoder_config),
-                    image=image,
-                    trainable=trainable,
-                    var_prefix='@HUB_{}@'.format(self.name),
-                    get_prediction=get_prediction)
+                # im_size
+                im_size = fluid.layers.data(
+                    name='im_size', shape=[2], dtype='int32')
+                # var_prefix
+                var_prefix = '@HUB_{}@'.format(self.name)
+                # names of inputs
+                inputs = {
+                    'image': var_prefix + image.name,
+                    'im_size': var_prefix + im_size.name
+                }
+                # names of outputs
+                if get_prediction:
+                    locs, confs, box, box_var = fluid.layers.multi_box_head(
+                        inputs=body_feats,
+                        image=image,
+                        num_classes=21,
+                        **self.multi_box_head_config)
+                    pred = fluid.layers.detection_output(
+                        loc=locs,
+                        scores=confs,
+                        prior_box=box,
+                        prior_box_var=box_var,
+                        **self.output_decoder_config)
+                    outputs = {'bbox_out': [var_prefix + pred.name]}
+                else:
+                    outputs = {
+                        'body_features':
+                        [var_prefix + var.name for var in body_feats]
+                    }
+
+                # add_vars_prefix
+                add_vars_prefix(context_prog, var_prefix)
+                add_vars_prefix(fluid.default_startup_program(), var_prefix)
+                # inputs
+                inputs = {
+                    key: context_prog.global_block().vars[value]
+                    for key, value in inputs.items()
+                }
+                outputs = {
+                    out_key: [
+                        context_prog.global_block().vars[varname]
+                        for varname in out_value
+                    ]
+                    for out_key, out_value in outputs.items()
+                }
+                # trainable
+                for param in context_prog.global_block().iter_parameters():
+                    param.trainable = trainable
 
                 place = fluid.CPUPlace()
                 exe = fluid.Executor(place)
+                # pretrained
                 if pretrained:
 
                     def _if_exist(var):
@@ -120,82 +154,56 @@ class SSDMobileNetv1(hub.Module):
                         predicate=_if_exist)
                 else:
                     exe.run(startup_program)
-                return inputs, outputs, context_prog
-
-    @property
-    def config(self):
-        if not self._config:
-            with open(os.path.join(self.directory, 'config.yml')) as file:
-                self._config = yaml.load(file.read(), Loader=yaml.FullLoader)
-        return self._config
 
-    @property
-    def multi_box_head_config(self):
-        return self.config['MultiBoxHead']
-
-    @property
-    def output_decoder_config(self):
-        return self.config['SSDOutputDecoder']
+                return inputs, outputs, context_prog
 
     def object_detection(self,
                          paths=None,
                          images=None,
                          data=None,
-                         use_gpu=False,
                          batch_size=1,
+                         use_gpu=False,
                          output_dir='detection_result',
                          score_thresh=0.5,
                          visualization=True):
         """API of Object Detection.
 
-        :param paths: the path of images.
-        :type paths: list, each element is correspond to the path of an image.
-        :param images: data of images, [N, H, W, C]
-        :type images: numpy.ndarray
-        :param use_gpu: whether to use gpu or not.
-        :type use_gpu: bool
-        :param batch_size: bathc size.
-        :type batch_size: int
-        :param output_dir: the directory to store the detection result.
-        :type output_dir: str
-        :param score_thresh: the threshold of detection confidence.
-        :type score_thresh: float
-        :param visualization: whether to draw bounding box and save images.
-        :type visualization: bool
+        Args:
+            paths (list[str]): The paths of images.
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]
+            batch_size (int): batch size.
+            use_gpu (bool): Whether to use gpu.
+            output_dir (str): The path to store output images.
+            visualization (bool): Whether to save image or not.
+            score_thresh (float): threshold for object detecion.
+
+        Returns:
+            res (list[dict]): The result of coco2017 detecion. keys include 'data', 'save_path', the corresponding value is:
+                data (dict): the result of object detection, keys include 'left', 'top', 'right', 'bottom', 'label', 'confidence', the corresponding value is:
+                    left (float): The X coordinate of the upper left corner of the bounding box;
+                    top (float): The Y coordinate of the upper left corner of the bounding box;
+                    right (float): The X coordinate of the lower right corner of the bounding box;
+                    bottom (float): The Y coordinate of the lower right corner of the bounding box;
+                    label (str): The label of detection result;
+                    confidence (float): The confidence of detection result.
+                save_path (str, optional): The path to save output images.
         """
+        paths = paths if paths else list()
         if data and 'image' in data:
-            paths = data['image'] if not paths else paths + data['image']
-        decode_image = self.ssd.DecodeImage(to_rgb=True, with_mixup=False)
-        resize_image = self.ssd.ResizeImage(
-            target_size=300, interp=1, max_size=0, use_cv2=False)
-        permute_image = self.ssd.Permute()
-        normalize_image = self.ssd.NormalizeImage(
-            mean=[127.5, 127.5, 127.5],
-            std=[127.502231, 127.502231, 127.502231],
-            is_scale=False)
-        data_reader = partial(
-            self.ssd.reader,
-            paths,
-            images,
-            decode_image=decode_image,
-            resize_image=resize_image,
-            permute_image=permute_image,
-            normalize_image=normalize_image)
+            paths += data['image']
+
+        data_reader = partial(reader, paths, images)
         batch_reader = fluid.io.batch(data_reader, batch_size=batch_size)
-        paths = paths if paths else []
         res = []
         for iter_id, feed_data in enumerate(batch_reader()):
-            np_data = np.array(feed_data).astype('float32')
-            if np_data.shape == 1:
-                np_data = np_data[0]
-            else:
-                np_data = np.squeeze(np_data, axis=1)
-            data_tensor = PaddleTensor(np_data.copy())
+            feed_data = np.array(feed_data)
+            image_tensor = PaddleTensor(np.array(list(feed_data[:, 0])).copy())
             if use_gpu:
-                data_out = self.gpu_predictor.run([data_tensor])
+                data_out = self.gpu_predictor.run([image_tensor])
             else:
-                data_out = self.cpu_predictor.run([data_tensor])
-            output = self.ssd.postprocess(
+                data_out = self.cpu_predictor.run([image_tensor])
+
+            output = postprocess(
                 paths=paths,
                 images=images,
                 data_out=data_out,
@@ -204,55 +212,49 @@ class SSDMobileNetv1(hub.Module):
                 output_dir=output_dir,
                 handle_id=iter_id * batch_size,
                 visualization=visualization)
-            res += output
-
+            res.extend(output)
         return res
 
-    def add_module_config_arg(self):
-        """
-        Add the command config options
-        """
-        self.arg_config_group.add_argument(
-            '--use_gpu',
-            type=ast.literal_eval,
-            default=False,
-            help="whether use GPU or not")
+    def save_inference_model(self,
+                             dirname,
+                             model_filename=None,
+                             params_filename=None,
+                             combined=True):
+        if combined:
+            model_filename = "__model__" if not model_filename else model_filename
+            params_filename = "__params__" if not params_filename else params_filename
+        place = fluid.CPUPlace()
+        exe = fluid.Executor(place)
 
-        self.arg_config_group.add_argument(
-            '--batch_size',
-            type=int,
-            default=1,
-            help="batch size for prediction")
+        program, feeded_var_names, target_vars = fluid.io.load_inference_model(
+            dirname=self.default_pretrained_model_path, executor=exe)
 
-    def add_module_input_arg(self):
+        fluid.io.save_inference_model(
+            dirname=dirname,
+            main_program=program,
+            executor=exe,
+            feeded_var_names=feeded_var_names,
+            target_vars=target_vars,
+            model_filename=model_filename,
+            params_filename=params_filename)
+
+    @serving
+    def serving_method(self, images, **kwargs):
         """
-        Add the command input options
+        Run as a service.
         """
-        self.arg_input_group.add_argument(
-            '--input_path', type=str, default=None, help="input data")
-
-        self.arg_input_group.add_argument(
-            '--input_file',
-            type=str,
-            default=None,
-            help="file contain input data")
-
-    def check_input_data(self, args):
-        input_data = []
-        if args.input_path:
-            input_data = [args.input_path]
-        elif args.input_file:
-            if not os.path.exists(args.input_file):
-                raise RuntimeError("File %s is not exist." % args.input_file)
-            else:
-                input_data = txt_parser.parse(args.input_file, use_strip=True)
-        return input_data
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.object_detection(images_decode, **kwargs)
+        return results
 
     @runnable
     def run_cmd(self, argvs):
+        """
+        Run as a command.
+        """
         self.parser = argparse.ArgumentParser(
-            description="Run the {}".format(self.name),
-            prog="hub run {}".format(self.name),
+            description="Run the {} module.".format(self.name),
+            prog='hub run {}'.format(self.name),
             usage='%(prog)s',
             add_help=True)
         self.arg_input_group = self.parser.add_argument_group(
@@ -262,17 +264,50 @@ class SSDMobileNetv1(hub.Module):
             description=
             "Run configuration for controlling module behavior, not required.")
         self.add_module_config_arg()
-
         self.add_module_input_arg()
         args = self.parser.parse_args(argvs)
-        input_data = self.check_input_data(args)
-        if len(input_data) == 0:
-            self.parser.print_help()
-            exit(1)
-        else:
-            for image_path in input_data:
-                if not os.path.exists(image_path):
-                    raise RuntimeError(
-                        "File %s or %s is not exist." % image_path)
-        return self.object_detection(
-            paths=input_data, use_gpu=args.use_gpu, batch_size=args.batch_size)
+        results = self.face_detection(
+            paths=[args.input_path],
+            batch_size=args.batch_size,
+            use_gpu=args.use_gpu,
+            output_dir=args.output_dir,
+            visualization=args.visualization,
+            score_thresh=args.score_thresh)
+        return results
+
+    def add_module_config_arg(self):
+        """
+        Add the command config options.
+        """
+        self.arg_config_group.add_argument(
+            '--use_gpu',
+            type=ast.literal_eval,
+            default=False,
+            help="whether use GPU or not")
+        self.arg_config_group.add_argument(
+            '--output_dir',
+            type=str,
+            default='detection_result',
+            help="The directory to save output images.")
+        self.arg_config_group.add_argument(
+            '--visualization',
+            type=ast.literal_eval,
+            default=False,
+            help="whether to save output as images.")
+
+    def add_module_input_arg(self):
+        """
+        Add the command input options.
+        """
+        self.arg_input_group.add_argument(
+            '--input_path', type=str, help="path to image.")
+        self.arg_input_group.add_argument(
+            '--batch_size',
+            type=ast.literal_eval,
+            default=1,
+            help="batch size.")
+        self.arg_input_group.add_argument(
+            '--score_thresh',
+            type=ast.literal_eval,
+            default=0.5,
+            help="threshold for object detecion.")

hub_module/modules/image/object_detection/ssd_mobilenet_v1_pascal/processor.py

+# coding=utf-8
+import base64
+import os
+
+import cv2
+import numpy as np
+from PIL import Image, ImageDraw
+
+__all__ = ['base64_to_cv2', 'load_label_info', 'postprocess']
+
+
+def base64_to_cv2(b64str):
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.fromstring(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+
+def get_save_image_name(img, output_dir, image_path):
+    """
+    Get save image name from source image path.
+    """
+    if not os.path.exists(output_dir):
+        os.makedirs(output_dir)
+    image_name = os.path.split(image_path)[-1]
+    name, ext = os.path.splitext(image_name)
+
+    if img.format == 'PNG':
+        ext = '.png'
+    elif img.format == 'JPEG':
+        ext = '.jpg'
+    elif img.format == 'BMP':
+        ext = '.bmp'
+    else:
+        if img.mode == "RGB" or img.mode == "L":
+            ext = ".jpg"
+        elif img.mode == "RGBA" or img.mode == "P":
+            ext = '.png'
+
+    return os.path.join(output_dir, "{}".format(name)) + ext
+
+
+def draw_bounding_box_on_image(image_path, data_list, save_dir):
+    image = Image.open(image_path)
+    draw = ImageDraw.Draw(image)
+    for data in data_list:
+        left, right, top, bottom = data['left'], data['right'], data[
+            'top'], data['bottom']
+
+        # draw bbox
+        draw.line([(left, top), (left, bottom), (right, bottom), (right, top),
+                   (left, top)],
+                  width=2,
+                  fill='red')
+
+        # draw label
+        if image.mode == 'RGB':
+            text = data['label'] + ": %.2f%%" % (100 * data['confidence'])
+            textsize_width, textsize_height = draw.textsize(text=text)
+            draw.rectangle(
+                xy=(left, top - (textsize_height + 5),
+                    left + textsize_width + 10, top),
+                fill=(255, 255, 255))
+            draw.text(xy=(left, top - 15), text=text, fill=(0, 0, 0))
+
+    save_name = get_save_image_name(image, save_dir, image_path)
+    if os.path.exists(save_name):
+        os.remove(save_name)
+
+    image.save(save_name)
+
+    return save_name
+
+
+def clip_bbox(bbox, img_width, img_height):
+    xmin = max(min(bbox[0], img_width), 0.)
+    ymin = max(min(bbox[1], img_height), 0.)
+    xmax = max(min(bbox[2], img_width), 0.)
+    ymax = max(min(bbox[3], img_height), 0.)
+    return xmin, ymin, xmax, ymax
+
+
+def load_label_info(file_path):
+    with open(file_path, 'r') as fr:
+        text = fr.readlines()
+        label_names = []
+        for info in text:
+            label_names.append(info.strip())
+        return label_names
+
+
+def postprocess(paths,
+                images,
+                data_out,
+                score_thresh,
+                label_names,
+                output_dir,
+                handle_id,
+                visualization=True):
+    """
+    postprocess the lod_tensor produced by fluid.Executor.run
+
+    Args:
+        paths (list[str]): the path of images.
+        images (list(numpy.ndarray)):  list of images, shape of each is [H, W, C].
+        data_out (lod_tensor): data produced by executor.run.
+        score_thresh (float): the low limit of bounding box.
+        label_names (list[str]): label names.
+        output_dir (str): output directory.
+        handle_id (int): The number of images that have been handled.
+        visualization (bool): whether to save as images.
+
+    Returns:
+        res (list[dict]): The result of vehicles detecion. keys include 'data', 'save_path', the corresponding value is:
+            data (dict): the result of object detection, keys include 'left', 'top', 'right', 'bottom', 'label', 'confidence', the corresponding value is:
+                left (float): The X coordinate of the upper left corner of the bounding box;
+                top (float): The Y coordinate of the upper left corner of the bounding box;
+                right (float): The X coordinate of the lower right corner of the bounding box;
+                bottom (float): The Y coordinate of the lower right corner of the bounding box;
+                label (str): The label of detection result;
+                confidence (float): The confidence of detection result.
+            save_path (str): The path to save output images.
+    """
+    lod_tensor = data_out[0]
+    lod = lod_tensor.lod[0]
+    results = lod_tensor.as_ndarray()
+    if handle_id < len(paths):
+        unhandled_paths = paths[handle_id:]
+        unhandled_paths_num = len(unhandled_paths)
+    else:
+        unhandled_paths_num = 0
+
+    output = []
+    for index in range(len(lod) - 1):
+        output_i = {'data': []}
+        if index < unhandled_paths_num:
+            org_img_path = unhandled_paths[index]
+            org_img = Image.open(org_img_path)
+            output_i['path'] = org_img_path
+        else:
+            org_img = images[index - unhandled_paths_num]
+            org_img = org_img.astype(np.uint8)
+            org_img = Image.fromarray(org_img[:, :, ::-1])
+            if visualization:
+                org_img_path = get_save_image_name(
+                    org_img, output_dir, 'image_numpy_{}'.format(
+                        (handle_id + index)))
+                org_img.save(org_img_path)
+        org_img_height = org_img.height
+        org_img_width = org_img.width
+        result_i = results[lod[index]:lod[index + 1]]
+        for row in result_i:
+            if len(row) != 6:
+                continue
+            if row[1] < score_thresh:
+                continue
+            category_id = int(row[0])
+            confidence = row[1]
+            bbox = row[2:]
+            bbox[0] = bbox[0] * org_img_width
+            bbox[1] = bbox[1] * org_img_height
+            bbox[2] = bbox[2] * org_img_width
+            bbox[3] = bbox[3] * org_img_height
+            dt = {}
+            dt['label'] = label_names[category_id]
+            dt['confidence'] = confidence
+            dt['left'], dt['top'], dt['right'], dt['bottom'] = clip_bbox(
+                bbox, org_img_width, org_img_height)
+            output_i['data'].append(dt)
+
+        output.append(output_i)
+        if visualization:
+            output_i['save_path'] = draw_bounding_box_on_image(
+                org_img_path, output_i['data'], output_dir)
+
+    return output

hub_module/modules/image/object_detection/ssd_vgg16_300_coco2017/README.md

+```shell
+$ hub install ssd_vgg16_300_coco2017==1.0.0
+```
+
+## 命令行预测
+
+```
+hub run ssd_vgg16_300_coco2017 --input_path "/PATH/TO/IMAGE"
+```
+
+## API
+
+```
+def context(trainable=True,
+            pretrained=True,
+            get_prediction=False)
+```
+
+特征提取，用于迁移学习。
+
+**参数**
+
+* trainable(bool): 设置参数的 trainable 属性；
+* pretrained (bool): 是否加载预训练模型；
+* get\_prediction (bool): 是否执行预测。
+
+**返回**
+
+* inputs (dict): 模型的输入，keys 包括 'image', 'im\_size'，相应的取值为：
+    * image (Variable): 图像变量
+    * im\_size (Variable): 图片的尺寸
+* outputs (dict): 模型的输出。如果 get\_prediction 为 False，输出 'head\_fatures'，否则输出 'bbox\_out'。
+* context\_prog (Program): 用于迁移学习的 Program.
+
+```python
+def object_detection(paths=None,
+                     images=None,
+                     batch_size=1,
+                     use_gpu=False,
+                     output_dir='detection_result',
+                     score_thresh=0.5,
+                     visualization=True)
+```
+
+预测API，检测输入图片中的所有目标的位置。
+
+**参数**
+
+* paths (list\[str\]): 图片的路径；
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，BGR格式；
+* batch\_size (int): batch 的大小；
+* use\_gpu (bool): 是否使用 GPU；
+* score\_thresh (float): 识别置信度的阈值；
+* visualization (bool): 是否将识别结果保存为图片文件；
+* output\_dir (str): 图片的保存路径，默认设为 detection\_result；
+
+**返回**
+
+* res (list\[dict\]): 识别结果的列表，列表中每一个元素为 dict，各字段为：
+    * data (list): 检测结果，list的每一个元素为 dict，各字段为:
+        * confidence (float): 识别的置信度；
+        * label (str): 标签；
+        * left (int): 边界框的左上角x坐标；
+        * top (int): 边界框的左上角y坐标；
+        * right (int): 边界框的右下角x坐标；
+        * bottom (int): 边界框的右下角y坐标；
+    * save\_path (str, optional): 识别结果的保存路径 (仅当visualization=True时存在)。
+
+```python
+def save_inference_model(dirname,
+                         model_filename=None,
+                         params_filename=None,
+                         combined=True)
+```
+
+将模型保存到指定路径。
+
+**参数**
+
+* dirname: 存在模型的目录名称
+* model\_filename: 模型文件名称，默认为\_\_model\_\_
+* params\_filename: 参数文件名称，默认为\_\_params\_\_(仅当`combined`为True时生效)
+* combined: 是否将参数保存到统一的一个文件中
+
+## 代码示例
+
+```python
+import paddlehub as hub
+import cv2
+
+object_detector = hub.Module(name="ssd_vgg16_300_coco2017")
+result = object_detector.object_detection(images=[cv2.imread('/PATH/TO/IMAGE')])
+# or
+# result = object_detector.object_detection((paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving可以部署一个目标检测的在线服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m ssd_vgg16_300_coco2017
+```
+
+这样就完成了一个目标检测的服务化API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/ssd_vgg16_300_coco2017"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+### 依赖
+
+paddlepaddle >= 1.6.2
+
+paddlehub >= 1.6.0

hub_module/modules/image/object_detection/ssd_vgg16_300_coco2017/data_feed.py

+# coding=utf-8
+from __future__ import absolute_import
+from __future__ import print_function
+from __future__ import division
+
+import os
+import random
+from collections import OrderedDict
+
+import cv2
+import numpy as np
+from PIL import Image
+from paddle import fluid
+
+__all__ = ['reader']
+
+
+class DecodeImage(object):
+    def __init__(self, to_rgb=True, with_mixup=False):
+        """ Transform the image data to numpy format.
+
+        Args:
+            to_rgb (bool): whether to convert BGR to RGB
+            with_mixup (bool): whether or not to mixup image and gt_bbbox/gt_score
+        """
+        self.to_rgb = to_rgb
+        self.with_mixup = with_mixup
+
+    def __call__(self, im):
+        if self.to_rgb:
+            im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
+
+        return im
+
+
+class ResizeImage(object):
+    def __init__(self,
+                 target_size=0,
+                 max_size=0,
+                 interp=cv2.INTER_LINEAR,
+                 use_cv2=True):
+        """
+        Rescale image to the specified target size, and capped at max_size
+        if max_size != 0.
+        If target_size is list, selected a scale randomly as the specified
+        target size.
+
+        Args:
+            target_size (int|list): the target size of image's short side,
+                multi-scale training is adopted when type is list.
+            max_size (int): the max size of image
+            interp (int): the interpolation method
+            use_cv2 (bool): use the cv2 interpolation method or use PIL
+                interpolation method
+        """
+        self.max_size = int(max_size)
+        self.interp = int(interp)
+        self.use_cv2 = use_cv2
+        self.target_size = target_size
+
+    def __call__(self, im):
+        if not isinstance(im, np.ndarray):
+            raise TypeError("{}: image type is not numpy.".format(self))
+        if len(im.shape) != 3:
+            raise ValueError('{}: image is not 3-dimensional.'.format(self))
+        im_shape = im.shape
+        im_size_min = np.min(im_shape[0:2])
+        im_size_max = np.max(im_shape[0:2])
+        if isinstance(self.target_size, list):
+            # Case for multi-scale training
+            selected_size = random.choice(self.target_size)
+        else:
+            selected_size = self.target_size
+        if float(im_size_min) == 0:
+            raise ZeroDivisionError('{}: min size of image is 0'.format(self))
+        if self.max_size != 0:
+            im_scale = float(selected_size) / float(im_size_min)
+            # Prevent the biggest axis from being more than max_size
+            if np.round(im_scale * im_size_max) > self.max_size:
+                im_scale = float(self.max_size) / float(im_size_max)
+            im_scale_x = im_scale
+            im_scale_y = im_scale
+
+            resize_w = im_scale_x * float(im_shape[1])
+            resize_h = im_scale_y * float(im_shape[0])
+            im_info = [resize_h, resize_w, im_scale]
+        else:
+            im_scale_x = float(selected_size) / float(im_shape[1])
+            im_scale_y = float(selected_size) / float(im_shape[0])
+
+            resize_w = selected_size
+            resize_h = selected_size
+
+        if self.use_cv2:
+            im = cv2.resize(
+                im,
+                None,
+                None,
+                fx=im_scale_x,
+                fy=im_scale_y,
+                interpolation=self.interp)
+        else:
+            if self.max_size != 0:
+                raise TypeError(
+                    'If you set max_size to cap the maximum size of image,'
+                    'please set use_cv2 to True to resize the image.')
+            im = im.astype('uint8')
+            im = Image.fromarray(im)
+            im = im.resize((int(resize_w), int(resize_h)), self.interp)
+            im = np.array(im)
+
+        return im
+
+
+class NormalizeImage(object):
+    def __init__(self,
+                 mean=[0.485, 0.456, 0.406],
+                 std=[1, 1, 1],
+                 is_scale=True,
+                 is_channel_first=True):
+        """
+        Args:
+            mean (list): the pixel mean
+            std (list): the pixel variance
+        """
+        self.mean = mean
+        self.std = std
+        self.is_scale = is_scale
+        self.is_channel_first = is_channel_first
+
+    def __call__(self, im):
+        """Normalize the image.
+
+        Operators:
+            1.(optional) Scale the image to [0,1]
+            2. Each pixel minus mean and is divided by std
+        """
+        im = im.astype(np.float32, copy=False)
+        if self.is_channel_first:
+            mean = np.array(self.mean)[:, np.newaxis, np.newaxis]
+            std = np.array(self.std)[:, np.newaxis, np.newaxis]
+        else:
+            mean = np.array(self.mean)[np.newaxis, np.newaxis, :]
+            std = np.array(self.std)[np.newaxis, np.newaxis, :]
+        if self.is_scale:
+            im = im / 255.0
+        im -= mean
+        im /= std
+        return im
+
+
+class Permute(object):
+    def __init__(self, to_bgr=True, channel_first=True):
+        """
+        Change the channel.
+
+        Args:
+            to_bgr (bool): confirm whether to convert RGB to BGR
+            channel_first (bool): confirm whether to change channel
+        """
+        self.to_bgr = to_bgr
+        self.channel_first = channel_first
+
+    def __call__(self, im):
+        if self.channel_first:
+            im = np.swapaxes(im, 1, 2)
+            im = np.swapaxes(im, 1, 0)
+        if self.to_bgr:
+            im = im[[2, 1, 0], :, :]
+        return im
+
+
+def reader(paths=[],
+           images=None,
+           decode_image=DecodeImage(to_rgb=True, with_mixup=False),
+           resize_image=ResizeImage(
+               target_size=512, interp=1, max_size=0, use_cv2=False),
+           permute_image=Permute(to_bgr=False),
+           normalize_image=NormalizeImage(
+               mean=[104, 117, 123], std=[1, 1, 1], is_scale=False)):
+    """
+    data generator
+
+    Args:
+        paths (list[str]): paths to images.
+        images (list(numpy.ndarray)): data of images, shape of each is [H, W, C]
+        decode_image (class object): instance of <class 'DecodeImage' object>
+        resize_image (class object): instance of <class 'ResizeImage' object>
+        permute_image (class object): instance of <class 'Permute' object>
+        normalize_image (class object): instance of <class 'NormalizeImage' object>
+    """
+    img_list = []
+    if paths is not None:
+        assert type(paths) is list, "type(paths) is not list."
+        for img_path in paths:
+            assert os.path.isfile(
+                img_path), "The {} isn't a valid file path.".format(img_path)
+            img = cv2.imread(img_path).astype('float32')
+            img_list.append(img)
+    if images is not None:
+        for img in images:
+            img_list.append(img)
+
+    resize_image = ResizeImage(
+        target_size=300, interp=1, max_size=0, use_cv2=False)
+
+    for img in img_list:
+        preprocessed_img = decode_image(img)
+        preprocessed_img = resize_image(preprocessed_img)
+        preprocessed_img = permute_image(preprocessed_img)
+        preprocessed_img = normalize_image(preprocessed_img)
+        yield [preprocessed_img]

hub_module/modules/image/object_detection/ssd_vgg16_300_coco2017/module.py

 # coding=utf-8
 from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
 
-import os
 import ast
 import argparse
+import os
 from functools import partial
 
+import yaml
 import numpy as np
 import paddle.fluid as fluid
 import paddlehub as hub
-from paddlehub.module.module import moduleinfo, runnable
 from paddle.fluid.core import PaddleTensor, AnalysisConfig, create_paddle_predictor
-from paddlehub.io.parser import txt_parser
-import yaml
+from paddlehub.module.module import moduleinfo, runnable, serving
+from paddlehub.common.paddle_helper import add_vars_prefix
 
 from ssd_vgg16_300_coco2017.vgg import VGG
+from ssd_vgg16_300_coco2017.processor import load_label_info, postprocess, base64_to_cv2
+from ssd_vgg16_300_coco2017.data_feed import reader
 
 
 @moduleinfo(
@@ -25,28 +25,22 @@ from ssd_vgg16_300_coco2017.vgg import VGG
     type="cv/object_detection",
     summary="SSD with backbone VGG16, trained with dataset COCO.",
     author="paddlepaddle",
-    author_email="paddle-dev@baidu.com")
+    author_email="")
 class SSDVGG16(hub.Module):
     def _initialize(self):
-        self.ssd = hub.Module(name="ssd")
-        # default pretrained model of SSD_VGG16, the shape of image tensor is (3, 300, 300)
         self.default_pretrained_model_path = os.path.join(
             self.directory, "ssd_vgg16_300_model")
-        self.label_names = self.ssd.load_label_info(
+        self.label_names = load_label_info(
             os.path.join(self.directory, "label_file.txt"))
-        self.infer_prog = None
-        self.image = None
-        self.bbox_out = None
+        self.model_config = None
         self._set_config()
-        self._config = None
 
     def _set_config(self):
-        """
-        predictor config setting
-        """
+        # predictor config setting.
         cpu_config = AnalysisConfig(self.default_pretrained_model_path)
         cpu_config.disable_glog_info()
         cpu_config.disable_gpu()
+        cpu_config.switch_ir_optim(False)
         self.cpu_predictor = create_paddle_predictor(cpu_config)
 
         try:
@@ -61,25 +55,31 @@ class SSDVGG16(hub.Module):
             gpu_config.enable_use_gpu(memory_pool_init_size_mb=500, device_id=0)
             self.gpu_predictor = create_paddle_predictor(gpu_config)
 
-    def context(self,
-                num_classes=81,
-                trainable=True,
-                pretrained=True,
-                get_prediction=False):
-        """Distill the Head Features, so as to perform transfer learning.
+        # model config setting.
+        if not self.model_config:
+            with open(os.path.join(self.directory, 'config.yml')) as fp:
+                self.model_config = yaml.load(fp.read(), Loader=yaml.FullLoader)
+
+        self.multi_box_head_config = self.model_config['MultiBoxHead']
+        self.output_decoder_config = self.model_config['SSDOutputDecoder']
 
-        :param trainable: whether to set parameters trainable.
-        :type trainable: bool
-        :param pretrained: whether to load default pretrained model.
-        :type pretrained: bool
-        :param get_prediction: whether to get prediction,
-            if True, outputs is {'bbox_out': bbox_out},
-            if False, outputs is {'head_features': head_features}.
-        :type get_prediction: bool
+    def context(self, trainable=True, pretrained=True, get_prediction=False):
         """
-        wrapped_prog = fluid.Program()
+        Distill the Head Features, so as to perform transfer learning.
+
+        Args:
+            trainable (bool): whether to set parameters trainable.
+            pretrained (bool): whether to load default pretrained model.
+            get_prediction (bool): whether to get prediction.
+
+        Returns:
+             inputs(dict): the input variables.
+             outputs(dict): the output variables.
+             context_prog (Program): the program to execute transfer learning.
+        """
+        context_prog = fluid.Program()
         startup_program = fluid.Program()
-        with fluid.program_guard(wrapped_prog, startup_program):
+        with fluid.program_guard(context_prog, startup_program):
             with fluid.unique_name.guard():
                 # image
                 image = fluid.layers.data(
@@ -89,21 +89,60 @@ class SSDVGG16(hub.Module):
                     depth=16,
                     with_extra_blocks=True,
                     normalizations=[20., -1, -1, -1, -1, -1])
+                # body_feats
                 body_feats = backbone(image)
-                # call ssd.context
-                inputs, outputs, context_prog = self.ssd.context(
-                    body_feats=body_feats,
-                    multi_box_head=self.ssd.MultiBoxHead(
-                        num_classes=num_classes, **self.multi_box_head_config),
-                    ssd_output_decoder=self.ssd.SSDOutputDecoder(
-                        **self.output_decoder_config),
-                    image=image,
-                    trainable=trainable,
-                    var_prefix='@HUB_{}@'.format(self.name),
-                    get_prediction=get_prediction)
+                # im_size
+                im_size = fluid.layers.data(
+                    name='im_size', shape=[2], dtype='int32')
+                # var_prefix
+                var_prefix = '@HUB_{}@'.format(self.name)
+                # names of inputs
+                inputs = {
+                    'image': var_prefix + image.name,
+                    'im_size': var_prefix + im_size.name
+                }
+                # names of outputs
+                if get_prediction:
+                    locs, confs, box, box_var = fluid.layers.multi_box_head(
+                        inputs=body_feats,
+                        image=image,
+                        num_classes=81,
+                        **self.multi_box_head_config)
+                    pred = fluid.layers.detection_output(
+                        loc=locs,
+                        scores=confs,
+                        prior_box=box,
+                        prior_box_var=box_var,
+                        **self.output_decoder_config)
+                    outputs = {'bbox_out': [var_prefix + pred.name]}
+                else:
+                    outputs = {
+                        'body_features':
+                        [var_prefix + var.name for var in body_feats]
+                    }
+
+                # add_vars_prefix
+                add_vars_prefix(context_prog, var_prefix)
+                add_vars_prefix(fluid.default_startup_program(), var_prefix)
+                # inputs
+                inputs = {
+                    key: context_prog.global_block().vars[value]
+                    for key, value in inputs.items()
+                }
+                outputs = {
+                    out_key: [
+                        context_prog.global_block().vars[varname]
+                        for varname in out_value
+                    ]
+                    for out_key, out_value in outputs.items()
+                }
+                # trainable
+                for param in context_prog.global_block().iter_parameters():
+                    param.trainable = trainable
 
                 place = fluid.CPUPlace()
                 exe = fluid.Executor(place)
+                # pretrained
                 if pretrained:
 
                     def _if_exist(var):
@@ -117,67 +156,52 @@ class SSDVGG16(hub.Module):
                         predicate=_if_exist)
                 else:
                     exe.run(startup_program)
-                return inputs, outputs, context_prog
 
-    @property
-    def config(self):
-        if not self._config:
-            with open(os.path.join(self.directory, 'config.yml')) as file:
-                self._config = yaml.load(file.read(), Loader=yaml.FullLoader)
-        return self._config
-
-    @property
-    def multi_box_head_config(self):
-        return self.config['MultiBoxHead']
-
-    @property
-    def output_decoder_config(self):
-        return self.config['SSDOutputDecoder']
+                return inputs, outputs, context_prog
 
     def object_detection(self,
                          paths=None,
                          images=None,
-                         use_gpu=False,
                          batch_size=1,
+                         use_gpu=False,
                          output_dir='detection_result',
                          score_thresh=0.5,
                          visualization=True):
         """API of Object Detection.
 
-        :param paths: the path of images.
-        :type paths: list, each element is correspond to the path of an image.
-        :param images: data of images, [N, H, W, C]
-        :type images: numpy.ndarray
-        :param use_gpu: whether to use gpu or not.
-        :type use_gpu: bool
-        :param batch_size: bathc size.
-        :type batch_size: int
-        :param output_dir: the directory to store the detection result.
-        :type output_dir: str
-        :param score_thresh: the threshold of detection confidence.
-        :type score_thresh: float
-        :param visualization: whether to draw bounding box and save images.
-        :type visualization: bool
+        Args:
+            paths (list[str]): The paths of images.
+            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]
+            batch_size (int): batch size.
+            use_gpu (bool): Whether to use gpu.
+            output_dir (str): The path to store output images.
+            visualization (bool): Whether to save image or not.
+            score_thresh (float): threshold for object detecion.
+
+        Returns:
+            res (list[dict]): The result of coco2017 detecion. keys include 'data', 'save_path', the corresponding value is:
+                data (dict): the result of object detection, keys include 'left', 'top', 'right', 'bottom', 'label', 'confidence', the corresponding value is:
+                    left (float): The X coordinate of the upper left corner of the bounding box;
+                    top (float): The Y coordinate of the upper left corner of the bounding box;
+                    right (float): The X coordinate of the lower right corner of the bounding box;
+                    bottom (float): The Y coordinate of the lower right corner of the bounding box;
+                    label (str): The label of detection result;
+                    confidence (float): The confidence of detection result.
+                save_path (str, optional): The path to save output images.
         """
-        resize_image = self.ssd.ResizeImage(
-            target_size=300, interp=1, max_size=0, use_cv2=False)
-        data_reader = partial(
-            self.ssd.reader, paths, images, resize_image=resize_image)
+        paths = paths if paths else list()
+        data_reader = partial(reader, paths, images)
         batch_reader = fluid.io.batch(data_reader, batch_size=batch_size)
-        paths = paths if paths else []
         res = []
         for iter_id, feed_data in enumerate(batch_reader()):
-            np_data = np.array(feed_data).astype('float32')
-            if np_data.shape == 1:
-                np_data = np_data[0]
-            else:
-                np_data = np.squeeze(np_data, axis=1)
-            data_tensor = PaddleTensor(np_data.copy())
+            feed_data = np.array(feed_data)
+            image_tensor = PaddleTensor(np.array(list(feed_data[:, 0])).copy())
             if use_gpu:
-                data_out = self.gpu_predictor.run([data_tensor])
+                data_out = self.gpu_predictor.run([image_tensor])
             else:
-                data_out = self.cpu_predictor.run([data_tensor])
-            output = self.ssd.postprocess(
+                data_out = self.cpu_predictor.run([image_tensor])
+
+            output = postprocess(
                 paths=paths,
                 images=images,
                 data_out=data_out,
@@ -186,53 +210,49 @@ class SSDVGG16(hub.Module):
                 output_dir=output_dir,
                 handle_id=iter_id * batch_size,
                 visualization=visualization)
-            res += output
+            res.extend(output)
         return res
 
-    def add_module_config_arg(self):
-        """
-        Add the command config options
-        """
-        self.arg_config_group.add_argument(
-            '--use_gpu',
-            type=ast.literal_eval,
-            default=False,
-            help="whether use GPU or not")
+    def save_inference_model(self,
+                             dirname,
+                             model_filename=None,
+                             params_filename=None,
+                             combined=True):
+        if combined:
+            model_filename = "__model__" if not model_filename else model_filename
+            params_filename = "__params__" if not params_filename else params_filename
+        place = fluid.CPUPlace()
+        exe = fluid.Executor(place)
 
-        self.arg_config_group.add_argument(
-            '--batch_size',
-            type=int,
-            default=1,
-            help="batch size for prediction")
+        program, feeded_var_names, target_vars = fluid.io.load_inference_model(
+            dirname=self.default_pretrained_model_path, executor=exe)
 
-    def add_module_input_arg(self):
+        fluid.io.save_inference_model(
+            dirname=dirname,
+            main_program=program,
+            executor=exe,
+            feeded_var_names=feeded_var_names,
+            target_vars=target_vars,
+            model_filename=model_filename,
+            params_filename=params_filename)
+
+    @serving
+    def serving_method(self, images, **kwargs):
         """
-        Add the command input options
+        Run as a service.
         """
-        self.arg_input_group.add_argument(
-            '--input_path', type=str, default=None, help="input data")
-        self.arg_input_group.add_argument(
-            '--input_file',
-            type=str,
-            default=None,
-            help="file contain input data")
-
-    def check_input_data(self, args):
-        input_data = []
-        if args.input_path:
-            input_data = [args.input_path]
-        elif args.input_file:
-            if not os.path.exists(args.input_file):
-                raise RuntimeError("File %s is not exist." % args.input_file)
-            else:
-                input_data = txt_parser.parse(args.input_file, use_strip=True)
-        return input_data
+        images_decode = [base64_to_cv2(image) for image in images]
+        results = self.object_detection(images_decode, **kwargs)
+        return results
 
     @runnable
     def run_cmd(self, argvs):
+        """
+        Run as a command.
+        """
         self.parser = argparse.ArgumentParser(
-            description="Run the {}".format(self.name),
-            prog="hub run {}".format(self.name),
+            description="Run the {} module.".format(self.name),
+            prog='hub run {}'.format(self.name),
             usage='%(prog)s',
             add_help=True)
         self.arg_input_group = self.parser.add_argument_group(
@@ -242,18 +262,50 @@ class SSDVGG16(hub.Module):
             description=
             "Run configuration for controlling module behavior, not required.")
         self.add_module_config_arg()
-
         self.add_module_input_arg()
         args = self.parser.parse_args(argvs)
-        input_path = args.input_path
-        input_data = self.check_input_data(args)
-        if len(input_data) == 0:
-            self.parser.print_help()
-            exit(1)
-        else:
-            for image_path in input_data:
-                if not os.path.exists(image_path):
-                    raise RuntimeError(
-                        "File %s or %s is not exist." % image_path)
-        return self.object_detection(
-            paths=input_data, use_gpu=args.use_gpu, batch_size=args.batch_size)
+        results = self.face_detection(
+            paths=[args.input_path],
+            batch_size=args.batch_size,
+            use_gpu=args.use_gpu,
+            output_dir=args.output_dir,
+            visualization=args.visualization,
+            score_thresh=args.score_thresh)
+        return results
+
+    def add_module_config_arg(self):
+        """
+        Add the command config options.
+        """
+        self.arg_config_group.add_argument(
+            '--use_gpu',
+            type=ast.literal_eval,
+            default=False,
+            help="whether use GPU or not")
+        self.arg_config_group.add_argument(
+            '--output_dir',
+            type=str,
+            default='detection_result',
+            help="The directory to save output images.")
+        self.arg_config_group.add_argument(
+            '--visualization',
+            type=ast.literal_eval,
+            default=False,
+            help="whether to save output as images.")
+
+    def add_module_input_arg(self):
+        """
+        Add the command input options.
+        """
+        self.arg_input_group.add_argument(
+            '--input_path', type=str, help="path to image.")
+        self.arg_input_group.add_argument(
+            '--batch_size',
+            type=ast.literal_eval,
+            default=1,
+            help="batch size.")
+        self.arg_input_group.add_argument(
+            '--score_thresh',
+            type=ast.literal_eval,
+            default=0.5,
+            help="threshold for object detecion.")

hub_module/modules/image/object_detection/ssd_vgg16_300_coco2017/processor.py

+# coding=utf-8
+import base64
+import os
+
+import cv2
+import numpy as np
+from PIL import Image, ImageDraw
+
+__all__ = ['base64_to_cv2', 'load_label_info', 'postprocess']
+
+
+def base64_to_cv2(b64str):
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.fromstring(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+
+def get_save_image_name(img, output_dir, image_path):
+    """
+    Get save image name from source image path.
+    """
+    if not os.path.exists(output_dir):
+        os.makedirs(output_dir)
+    image_name = os.path.split(image_path)[-1]
+    name, ext = os.path.splitext(image_name)
+
+    if img.format == 'PNG':
+        ext = '.png'
+    elif img.format == 'JPEG':
+        ext = '.jpg'
+    elif img.format == 'BMP':
+        ext = '.bmp'
+    else:
+        if img.mode == "RGB" or img.mode == "L":
+            ext = ".jpg"
+        elif img.mode == "RGBA" or img.mode == "P":
+            ext = '.png'
+
+    return os.path.join(output_dir, "{}".format(name)) + ext
+
+
+def draw_bounding_box_on_image(image_path, data_list, save_dir):
+    image = Image.open(image_path)
+    draw = ImageDraw.Draw(image)
+    for data in data_list:
+        left, right, top, bottom = data['left'], data['right'], data[
+            'top'], data['bottom']
+
+        # draw bbox
+        draw.line([(left, top), (left, bottom), (right, bottom), (right, top),
+                   (left, top)],
+                  width=2,
+                  fill='red')
+
+        # draw label
+        if image.mode == 'RGB':
+            text = data['label'] + ": %.2f%%" % (100 * data['confidence'])
+            textsize_width, textsize_height = draw.textsize(text=text)
+            draw.rectangle(
+                xy=(left, top - (textsize_height + 5),
+                    left + textsize_width + 10, top),
+                fill=(255, 255, 255))
+            draw.text(xy=(left, top - 15), text=text, fill=(0, 0, 0))
+
+    save_name = get_save_image_name(image, save_dir, image_path)
+    if os.path.exists(save_name):
+        os.remove(save_name)
+
+    image.save(save_name)
+
+    return save_name
+
+
+def clip_bbox(bbox, img_width, img_height):
+    xmin = max(min(bbox[0], img_width), 0.)
+    ymin = max(min(bbox[1], img_height), 0.)
+    xmax = max(min(bbox[2], img_width), 0.)
+    ymax = max(min(bbox[3], img_height), 0.)
+    return xmin, ymin, xmax, ymax
+
+
+def load_label_info(file_path):
+    with open(file_path, 'r') as fr:
+        text = fr.readlines()
+        label_names = []
+        for info in text:
+            label_names.append(info.strip())
+        return label_names
+
+
+def postprocess(paths,
+                images,
+                data_out,
+                score_thresh,
+                label_names,
+                output_dir,
+                handle_id,
+                visualization=True):
+    """
+    postprocess the lod_tensor produced by fluid.Executor.run
+
+    Args:
+        paths (list[str]): the path of images.
+        images (list(numpy.ndarray)):  list of images, shape of each is [H, W, C].
+        data_out (lod_tensor): data produced by executor.run.
+        score_thresh (float): the low limit of bounding box.
+        label_names (list[str]): label names.
+        output_dir (str): output directory.
+        handle_id (int): The number of images that have been handled.
+        visualization (bool): whether to save as images.
+
+    Returns:
+        res (list[dict]): The result of vehicles detecion. keys include 'data', 'save_path', the corresponding value is:
+            data (dict): the result of object detection, keys include 'left', 'top', 'right', 'bottom', 'label', 'confidence', the corresponding value is:
+                left (float): The X coordinate of the upper left corner of the bounding box;
+                top (float): The Y coordinate of the upper left corner of the bounding box;
+                right (float): The X coordinate of the lower right corner of the bounding box;
+                bottom (float): The Y coordinate of the lower right corner of the bounding box;
+                label (str): The label of detection result;
+                confidence (float): The confidence of detection result.
+            save_path (str): The path to save output images.
+    """
+    lod_tensor = data_out[0]
+    lod = lod_tensor.lod[0]
+    results = lod_tensor.as_ndarray()
+    if handle_id < len(paths):
+        unhandled_paths = paths[handle_id:]
+        unhandled_paths_num = len(unhandled_paths)
+    else:
+        unhandled_paths_num = 0
+
+    output = []
+    for index in range(len(lod) - 1):
+        output_i = {'data': []}
+        if index < unhandled_paths_num:
+            org_img_path = unhandled_paths[index]
+            org_img = Image.open(org_img_path)
+            output_i['path'] = org_img_path
+        else:
+            org_img = images[index - unhandled_paths_num]
+            org_img = org_img.astype(np.uint8)
+            org_img = Image.fromarray(org_img[:, :, ::-1])
+            if visualization:
+                org_img_path = get_save_image_name(
+                    org_img, output_dir, 'image_numpy_{}'.format(
+                        (handle_id + index)))
+                org_img.save(org_img_path)
+        org_img_height = org_img.height
+        org_img_width = org_img.width
+        result_i = results[lod[index]:lod[index + 1]]
+        for row in result_i:
+            if len(row) != 6:
+                continue
+            if row[1] < score_thresh:
+                continue
+            category_id = int(row[0])
+            confidence = row[1]
+            bbox = row[2:]
+            bbox[0] = bbox[0] * org_img_width
+            bbox[1] = bbox[1] * org_img_height
+            bbox[2] = bbox[2] * org_img_width
+            bbox[3] = bbox[3] * org_img_height
+            dt = {}
+            dt['label'] = label_names[category_id]
+            dt['confidence'] = confidence
+            dt['left'], dt['top'], dt['right'], dt['bottom'] = clip_bbox(
+                bbox, org_img_width, org_img_height)
+            output_i['data'].append(dt)
+
+        output.append(output_i)
+        if visualization:
+            output_i['save_path'] = draw_bounding_box_on_image(
+                org_img_path, output_i['data'], output_dir)
+
+    return output

hub_module/modules/image/object_detection/ssd_vgg16_512_coco2017/README.md

+```shell
+$ hub install ssd_vgg16_512_coco2017==1.0.0
+```
+
+## 命令行预测
+
+```
+hub run ssd_vgg16_512_coco2017 --input_path "/PATH/TO/IMAGE"
+```
+
+## API
+
+```
+def context(trainable=True,
+            pretrained=True,
+            get_prediction=False)
+```
+
+特征提取，用于迁移学习。
+
+**参数**
+
+* trainable(bool): 设置参数的 trainable 属性；
+* pretrained (bool): 是否加载预训练模型；
+* get\_prediction (bool): 是否执行预测。
+
+**返回**
+
+* inputs (dict): 模型的输入，keys 包括 'image', 'im\_size'，相应的取值为：
+    * image (Variable): 图像变量
+    * im\_size (Variable): 图片的尺寸
+* outputs (dict): 模型的输出。如果 get\_prediction 为 False，输出 'head\_fatures'，否则输出 'bbox\_out'。
+* context\_prog (Program): 用于迁移学习的 Program.
+
+```python
+def object_detection(paths=None,
+                     images=None,
+                     batch_size=1,
+                     use_gpu=False,
+                     output_dir='detection_result',
+                     score_thresh=0.5,
+                     visualization=True)
+```
+
+预测API，检测输入图片中的所有目标的位置。
+
+**参数**
+
+* paths (list\[str\]): 图片的路径；
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，BGR格式；
+* batch\_size (int): batch 的大小；
+* use\_gpu (bool): 是否使用 GPU；
+* score\_thresh (float): 识别置信度的阈值；
+* visualization (bool): 是否将识别结果保存为图片文件；
+* output\_dir (str): 图片的保存路径，默认设为 detection\_result；
+
+**返回**
+
+* res (list\[dict\]): 识别结果的列表，列表中每一个元素为 dict，各字段为：
+    * data (list): 检测结果，list的每一个元素为 dict，各字段为:
+        * confidence (float): 识别的置信度；
+        * label (str): 标签；
+        * left (int): 边界框的左上角x坐标；
+        * top (int): 边界框的左上角y坐标；
+        * right (int): 边界框的右下角x坐标；
+        * bottom (int): 边界框的右下角y坐标；
+    * save\_path (str, optional): 识别结果的保存路径 (仅当visualization=True时存在)。
+
+```python
+def save_inference_model(dirname,
+                         model_filename=None,
+                         params_filename=None,
+                         combined=True)
+```
+
+将模型保存到指定路径。
+
+**参数**
+
+* dirname: 存在模型的目录名称
+* model\_filename: 模型文件名称，默认为\_\_model\_\_
+* params\_filename: 参数文件名称，默认为\_\_params\_\_(仅当`combined`为True时生效)
+* combined: 是否将参数保存到统一的一个文件中
+
+## 代码示例
+
+```python
+import paddlehub as hub
+import cv2
+
+object_detector = hub.Module(name="ssd_vgg16_512_coco2017")
+result = object_detector.object_detection(images=[cv2.imread('/PATH/TO/IMAGE')])
+# or
+# result = object_detector.object_detection((paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving可以部署一个目标检测的在线服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m ssd_vgg16_512_coco2017
+```
+
+这样就完成了一个目标检测的服务化API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU 预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/ssd_vgg16_512_coco2017"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+### 依赖
+
+paddlepaddle >= 1.6.2
+
+paddlehub >= 1.6.0

hub_module/modules/image/object_detection/ssd/data_feed.py → hub_module/modules/image/object_detection/ssd_vgg16_512_coco2017/data_feed.py

@@ -9,10 +9,10 @@ from collections import OrderedDict
 
 import cv2
 import numpy as np
-from PIL import Image, ImageEnhance
+from PIL import Image
 from paddle import fluid
 
-__all__ = ['reader', 'DecodeImage', 'ResizeImage', 'NormalizeImage', 'Permute']
+__all__ = ['reader']
 
 
 class DecodeImage(object):
@@ -59,8 +59,6 @@ class ResizeImage(object):
         self.target_size = target_size
 
     def __call__(self, im):
-        """ Resize the image numpy.
-        """
         if not isinstance(im, np.ndarray):
             raise TypeError("{}: image type is not numpy.".format(self))
         if len(im.shape) != 3:
@@ -132,6 +130,7 @@ class NormalizeImage(object):
 
     def __call__(self, im):
         """Normalize the image.
+
         Operators:
             1.(optional) Scale the image to [0,1]
             2. Each pixel minus mean and is divided by std
@@ -154,6 +153,7 @@ class Permute(object):
     def __init__(self, to_bgr=True, channel_first=True):
         """
         Change the channel.
+
         Args:
             to_bgr (bool): confirm whether to convert RGB to BGR
             channel_first (bool): confirm whether to change channel
@@ -178,16 +178,16 @@ def reader(paths=[],
            permute_image=Permute(to_bgr=False),
            normalize_image=NormalizeImage(
                mean=[104, 117, 123], std=[1, 1, 1], is_scale=False)):
-    """data generator
-
-    :param paths: path to images.
-    :type paths: list, each element is a str
-    :param images: data of images, [N, H, W, C]
-    :type images: numpy.ndarray
-    :param decode_image: instance of <class 'DecodeImage' object>
-    :param resize_image: instance of <class 'ResizeImage' object>
-    :param permute_image: instance of <class 'Permute' object>
-    :param normalize_image: instance of <class 'NormalizeImage' object>
+    """
+    data generator
+
+    Args:
+        paths (list[str]): paths to images.
+        images (list(numpy.ndarray)): data of images, shape of each is [H, W, C]
+        decode_image (class object): instance of <class 'DecodeImage' object>
+        resize_image (class object): instance of <class 'ResizeImage' object>
+        permute_image (class object): instance of <class 'Permute' object>
+        normalize_image (class object): instance of <class 'NormalizeImage' object>
     """
     img_list = []
     if paths is not None:

hub_module/modules/image/object_detection/yolov3/module.py

-# coding=utf-8
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
-from collections import OrderedDict
-
-import paddle.fluid as fluid
-import paddlehub as hub
-from paddlehub.module.module import moduleinfo
-from paddlehub.common.paddle_helper import add_vars_prefix
-
-from yolov3.data_feed import reader
-from yolov3.processor import load_label_info, postprocess
-from yolov3.yolo_head import MultiClassNMS, YOLOv3Head
-
-
-@moduleinfo(
-    name="yolov3",
-    version="1.0.0",
-    type="cv/object_detection",
-    summary="Baidu's YOLOv3 model for object detection.",
-    author="paddlepaddle",
-    author_email="paddle-dev@baidu.com")
-class YOLOv3(hub.Module):
-    def _initialize(self):
-        self.reader = reader
-        self.load_label_info = load_label_info
-        self.postprocess = postprocess
-        self.MultiClassNMS = MultiClassNMS
-        self.YOLOv3Head = YOLOv3Head
-
-    def context(self,
-                body_feats,
-                yolo_head,
-                image,
-                trainable=True,
-                var_prefix='',
-                get_prediction=False):
-        """
-        Distill the Head Features, so as to perform transfer learning.
-
-        Args:
-            body_feats (feature maps of backbone): feature maps of backbone.
-            yolo_head (<class 'YOLOv3Head' object>): yolo_head of YOLOv3
-            image (Variable): image tensor.
-            trainable (bool): whether to set parameters trainable.
-            var_prefix (str): the prefix of variables in yolo_head and backbone.
-            get_prediction (bool): whether to get prediction or not.
-
-        Returns:
-             inputs(dict): the input variables.
-             outputs(dict): the output variables.
-             context_prog (Program): the program to execute transfer learning.
-        """
-        context_prog = image.block.program
-        with fluid.program_guard(context_prog):
-            im_size = fluid.layers.data(
-                name='im_size', shape=[2], dtype='int32')
-            head_features = yolo_head._get_outputs(
-                body_feats, is_train=trainable)
-            inputs = {
-                'image': var_prefix + image.name,
-                'im_size': var_prefix + im_size.name
-            }
-            if get_prediction:
-                bbox_out = yolo_head.get_prediction(head_features, im_size)
-                outputs = {'bbox_out': [var_prefix + bbox_out.name]}
-            else:
-                outputs = {
-                    'head_features':
-                    [var_prefix + var.name for var in head_features]
-                }
-
-            place = fluid.CPUPlace()
-            exe = fluid.Executor(place)
-            exe.run(fluid.default_startup_program())
-
-            add_vars_prefix(context_prog, var_prefix)
-            add_vars_prefix(fluid.default_startup_program(), var_prefix)
-            inputs = {
-                key: context_prog.global_block().vars[value]
-                for key, value in inputs.items()
-            }
-            outputs = {
-                key: [
-                    context_prog.global_block().vars[varname]
-                    for varname in value
-                ]
-                for key, value in outputs.items()
-            }
-
-            for param in context_prog.global_block().iter_parameters():
-                param.trainable = trainable
-            return inputs, outputs, context_prog

hub_module/modules/image/object_detection/yolov3_darknet53_coco2017/darknet.py

@@ -15,6 +15,7 @@ __all__ = ['DarkNet']
 
 class DarkNet(object):
     """DarkNet, see https://pjreddie.com/darknet/yolo/
+
     Args:
         depth (int): network depth, currently only darknet 53 is supported
         norm_type (str): normalization type, 'bn' and 'sync_bn' are supported
@@ -120,11 +121,8 @@ class DarkNet(object):
         return out
 
     def __call__(self, input):
-        """Get the backbone of DarkNet, that is output for the 5 stages.
-
-        :param input: Variable of input image
-        :type input: Variable
-        :Returns: The last variables of each stage.
+        """
+        Get the backbone of DarkNet, that is output for the 5 stages.
         """
         stages, block_func = self.depth_cfg[self.depth]
         stages = stages[0:5]

hub_module/modules/image/object_detection/yolov3/data_feed.py → hub_module/modules/image/object_detection/yolov3_darknet53_coco2017/data_feed.py

@@ -12,12 +12,15 @@ __all__ = ['reader']
 
 
 def reader(paths=[], images=None):
-    """data generator
+    """
+    data generator
+
+    Args:
+        paths (list[str]): paths to images.
+        images (list(numpy.ndarray)): data of images, shape of each is [H, W, C]
 
-    :param paths: path to images.
-    :type paths: list, each element is a str
-    :param images: data of images, [N, H, W, C]
-    :type images: numpy.ndarray
+    Yield:
+        res (list): preprocessed image and the size of original image.
     """
     img_list = []
     if paths:

hub_module/modules/image/object_detection/yolov3/processor.py → hub_module/modules/image/object_detection/yolov3_darknet53_coco2017/processor.py

 # coding=utf-8
+import base64
 import os
 
+import cv2
 import numpy as np
 from PIL import Image, ImageDraw
 
-__all__ = ['load_label_info', 'postprocess']
+__all__ = ['base64_to_cv2', 'load_label_info', 'postprocess']
+
+
+def base64_to_cv2(b64str):
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.fromstring(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
 
 
 def check_dir(dir_path):

hub_module/modules/image/object_detection/yolov3_darknet53_pedestrian/serving.py

-import base64
-import cv2
-import numpy as np
-
-
-def base64_to_cv2(b64str):
-    data = base64.b64decode(b64str.encode('utf8'))
-    data = np.fromstring(data, np.uint8)
-    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
-    return data