Faster rcnn–改变anchor的size

• 代码用的是py-faster-rcnn：https://github.com/rbgirshick/py-faster-rcnn
• 训练时用的模型和方法：models\pascal_voc\VGG_CNN_M_1024\faster_rcnn_end2end

---

修改generate_anchors.py

#ratios中加了一种比例1.5，所以anchor的数量为4*3=12def generate_anchors(base_size=16, ratios=[0.5, 1, 1.5, 2],                     scales=2**np.arange(3, 6)):    """    Generate anchor (reference) windows by enumerating aspect ratios X    scales wrt a reference (0, 0, 15, 15) window.    """    base_anchor = np.array([1, 1, base_size, base_size]) - 1    ratio_anchors = _ratio_enum(base_anchor, ratios)    anchors = np.vstack([_scale_enum(ratio_anchors[i, :], scales)                         for i in xrange(ratio_anchors.shape[0])])    return anchors

修改train.prototxt

layer {  name: "rpn_cls_score"  type: "Convolution"  bottom: "rpn/output"  top: "rpn_cls_score"  param { lr_mult: 1.0 }  param { lr_mult: 2.0 }  convolution_param {    num_output: 24   # 2(bg/fg) * 12(anchors)    kernel_size: 1 pad: 0 stride: 1    weight_filler { type: "gaussian" std: 0.01 }    bias_filler { type: "constant" value: 0 }  }

layer {  name: "rpn_bbox_pred"  type: "Convolution"  bottom: "rpn/output"  top: "rpn_bbox_pred"  param { lr_mult: 1.0 }  param { lr_mult: 2.0 }  convolution_param {    num_output: 48   # 4 * 12(anchors)    kernel_size: 1 pad: 0 stride: 1    weight_filler { type: "gaussian" std: 0.01 }    bias_filler { type: "constant" value: 0 }  }}

layer {  name: 'rpn_cls_prob_reshape'  type: 'Reshape'  bottom: 'rpn_cls_prob'  top: 'rpn_cls_prob_reshape'  reshape_param { shape { dim: 0 dim: 24 dim: -1 dim: 0 } }}

修改test.prototxt

同train.prototxt

上述步骤只针对改ratios，如果你想改scales，还要进行以下修改

修改generate_anchors.py

#anchor的数量为4*5=20def generate_anchors(base_size=16, ratios=[0.5, 1, 1.5, 2],                     scales=2**np.arange(1, 6)):    """    Generate anchor (reference) windows by enumerating aspect ratios X    scales wrt a reference (0, 0, 15, 15) window.    """    base_anchor = np.array([1, 1, base_size, base_size]) - 1    ratio_anchors = _ratio_enum(base_anchor, ratios)    anchors = np.vstack([_scale_enum(ratio_anchors[i, :], scales)                         for i in xrange(ratio_anchors.shape[0])])    return anchors

修改anchor_target_layer.py

    def setup(self, bottom, top):        layer_params = yaml.load(self.param_str)        anchor_scales = layer_params.get('scales', (2, 4, 8, 16, 32))        self._anchors = generate_anchors(scales=np.array(anchor_scales))        self._num_anchors = self._anchors.shape[0]        self._feat_stride = layer_params['feat_stride']

修改proposal_layer.py

    def setup(self, bottom, top):        # parse the layer parameter string, which must be valid YAML        layer_params = yaml.load(self.param_str)        self._feat_stride = layer_params['feat_stride']        anchor_scales = layer_params.get('scales', (2, 4, 8, 16, 32))        self._anchors = generate_anchors(scales=np.array(anchor_scales))        self._num_anchors = self._anchors.shape[0]

如果报错，删除faster_rcnn_version\fasterRcnn_final_v1_3\data\cache下.pkl文件

---