使用Faster-Rcnn进行目标检测(实践篇)

pip install cython
pip install python-opencv
pip install easydict

git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git

cd $FRCN_ROOT/lib
make 

cd $FRCN_ROOT/caffe-fast-rcnn
make -j8 && make pycaffe

<annotation>
    <folder>VOC2007</folder> #数据集文件夹
    <filename>000105.jpg</filename> #图片的name
    <source> #注释信息，无所谓有无
        <database>The VOC2007 Database</database>
        <annotation>PASCAL VOC2007</annotation>
        <image>flickr</image>
        <flickrid>321862192</flickrid>
    </source>
    <owner> #注释信息，无所谓有无
        <flickrid>Eric T. Johnson</flickrid>
        <name>?</name>
    </owner>
    <size> #图片大小
        <width>500</width>
        <height>333</height>
        <depth>3</depth>
    </size>
    <segmented>0</segmented>
    <object> #多少个框就有多少个object标签
        <name>boat</name> #bounding box中的object的class name
        <pose>Frontal</pose>
        <truncated>1</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>22</xmin> #框的坐标
            <ymin>1</ymin>
            <xmax>320</xmax>
            <ymax>314</ymax>
        </bndbox>
    </object>
    <object>
        <name>person</name>
        <pose>Frontal</pose>
        <truncated>1</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>202</xmin>
            <ymin>71</ymin>
            <xmax>295</xmax>
            <ymax>215</ymax>
        </bndbox>
    </object>
    <object>
        <name>person</name>
        <pose>Frontal</pose>
        <truncated>1</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>170</xmin>
            <ymin>107</ymin>
            <xmax>239</xmax>
            <ymax>206</ymax>
        </bndbox>
    </object>
</annotation>

layer {  
  name: 'data'  
  type: 'Python'  
  top: 'data'  
  top: 'rois'  
  top: 'labels'  
  top: 'bbox_targets'  
  top: 'bbox_inside_weights'  
  top: 'bbox_outside_weights'  
  python_param {  
    module: 'roi_data_layer.layer'  
    layer: 'RoIDataLayer'  
    param_str: "'num_classes': 2" #按训练集类别改，该值为类别数+1  
  }  
}  

layer {  
  name: "cls_score"  
  type: "InnerProduct"  
  bottom: "fc7"  
  top: "cls_score"  
  param { 
  lr_mult: 1.0
  }  
  param {
  lr_mult: 2.0 
  }  
  inner_product_param {  
    num_output: 2 #按训练集类别改，该值为类别数+1  
    weight_filler {  
      type: "gaussian"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  

layer {  
  name: "bbox_pred"  
  type: "InnerProduct"  
  bottom: "fc7"  
  top: "bbox_pred"  
  param { 
  lr_mult: 1.0 
  }  
  param { 
  lr_mult: 2.0 
  }  
  inner_product_param {  
    num_output: 8 #按训练集类别改，该值为（类别数+1）*4，四个顶点坐标  
    weight_filler {  
      type: "gaussian"  
      std: 0.001  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  

layer {  
  name: 'input-data'  
  type: 'Python'  
  top: 'data'  
  top: 'im_info'  
  top: 'gt_boxes'  
  python_param {  
    module: 'roi_data_layer.layer'  
    layer: 'RoIDataLayer'  
    param_str: "'num_classes': 2" #按训练集类别改，该值为类别数+1  
  }  
}  

layer {  
  name: 'data'  
  type: 'Python'  
  top: 'data'  
  top: 'rois'  
  top: 'labels'  
  top: 'bbox_targets'  
  top: 'bbox_inside_weights'  
  top: 'bbox_outside_weights'  
  python_param {  
    module: 'roi_data_layer.layer'  
    layer: 'RoIDataLayer'  
    param_str: "'num_classes': 2" #按训练集类别改，该值为类别数+1  
  }  
}  

layer {  
  name: "cls_score"  
  type: "InnerProduct"  
  bottom: "fc7"  
  top: "cls_score"  
  param { 
  lr_mult: 1.0 
  }  
  param { 
  lr_mult: 2.0 
  }  
  inner_product_param {  
    num_output: 2 #按训练集类别改，该值为类别数+1  
    weight_filler {  
      type: "gaussian"  
      std: 0.01  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  

layer {  
  name: "bbox_pred"  
  type: "InnerProduct"  
  bottom: "fc7"  
  top: "bbox_pred"  
  param { 
  lr_mult: 1.0
  }  
  param { 
  lr_mult: 2.0 
  }  
  inner_product_param {  
    num_output: 8 #按训练集类别改，该值为（类别数+1）*4,四个顶点坐标  
    weight_filler {  
      type: "gaussian"  
      std: 0.001  
    }  
    bias_filler {  
      type: "constant"  
      value: 0  
    }  
  }  
}  

layer {  
  name: 'input-data'  
  type: 'Python'  
  top: 'data'  
  top: 'im_info'  
  top: 'gt_boxes'  
  python_param {  
    module: 'roi_data_layer.layer'  
    layer: 'RoIDataLayer'  
    param_str: "'num_classes': 2" #按训练集类别改，该值为类别数+1  
  }  
}  

layer {  
  name: "cls_score"  
  type: "InnerProduct"  
  bottom: "fc7"  
  top: "cls_score"  
  inner_product_param {  
    num_output: 2 #按训练集类别改，该值为类别数+1  
  }  
}  

class pascal_voc(imdb):  
    def __init__(self, image_set, year, devkit_path=None):  
        imdb.__init__(self, 'voc_' + year + '_' + image_set)  
        self._year = year  
        self._image_set = image_set  
        self._devkit_path = self._get_default_path() if devkit_path is None \  
                            else devkit_path  
        self._data_path = os.path.join(self._devkit_path, 'VOC' + self._year)  
        self._classes = ('__background__', # always index 0  
                         captcha' # 有几个类别此处就写几个，我是两个
                      )  

cls = self._class_to_ind[obj.find('name').text.lower().strip()]  

def append_flipped_images(self):  
        num_images = self.num_images  
        widths = [PIL.Image.open(self.image_path_at(i)).size[0]  
                  for i in xrange(num_images)]  
        for i in xrange(num_images):  
            boxes = self.roidb[i]['boxes'].copy()  
            oldx1 = boxes[:, 0].copy()  
            oldx2 = boxes[:, 2].copy()  
            boxes[:, 0] = widths[i] - oldx2 - 1  
            print boxes[:, 0]  
            boxes[:, 2] = widths[i] - oldx1 - 1  
            print boxes[:, 0]  
            assert (boxes[:, 2] >= boxes[:, 0]).all()  
            entry = {'boxes' : boxes,  
                     'gt_overlaps' : self.roidb[i]['gt_overlaps'],  
                     'gt_classes' : self.roidb[i]['gt_classes'],  
                     'flipped' : True}  
            self.roidb.append(entry)  
        self._image_index = self._image_index * 2  

base_lr: 0.001
lr_policy: 'step'
step_size: 30000
display: 20
....

max_iters = [80000, 40000, 80000, 40000]

cd py-faster-rcnn
./experiments/scripts/faster_rcnn_alt_opt.sh 0 VGG16 pascal_voc 

im_names = ['1559.jpg','1564.jpg']  # 改成自己的test image的name