anchor通常设置为3ratio*3scales=9anchors,但实际使用时可能需要进行调整。改变anchor数量或尺寸。先看Faster R-CNN源码产生anchors的部分,位置$Faster RCNN/lib/rpn/generate_anchors.py:
def generate_anchors(base_size=16, ratios=[0.5, 1, 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这个函数三个参数base_size, ratios 和scales,且都有默认值。base_size要和scales集合起来看,anchor的基础尺度=base_size*scales,例如这里默认base_size=16, scales=(8,16,32),那么三个基本尺度分别是128,256和512。然后在这三个基本尺度上才有3个ratio。再来看看哪些地方用到了这个generate_anchors函数,分别是:proposal_layer.py, anchor_target_layer.py和generate.py(三个文件都在目录FRCN_ROOT/lib/rpn/
下)。其中generate.py用到generate_anchors的是RFCN ,Faster RCNN是没有的。
一,不改变anchor数量
如果不需要改变anchor数量,而只是简单改变scales和ratios,直接改generate_anchors函数的默认值就好,比如把base_size改为8或者把scales该为2**np.arrage(2,5),都可以把基础尺度减少为64, 128, 256。ratios也可以根据需要这样改。此外,proposal_layer.py, anchor_target_layer.py和generate.py这三个调用了generate_anchor的地方也要相应改一下:
anchor_scales =layer_params.get('scales', (8, 16, 32)) self._anchors = generate_anchors(scales=np.array(anchor_scales))
直接改成:anchor_scales =layer_params.get('scales', (8, 16, 32)) self._anchors = generate_anchors()generate_anchors
函数用默认参数就好。
二,改变anchor数量
改变anchor数量的方式可以是直接增减anchor的基础尺度数量或者ratios数量,或者直接用YOLOv2那样聚类anchor,只要改变了anchor数量,就要去修改网络pt文件。以Faster RCNN为例,将目录FRCN_ROOT/models/pascal_voc/VGG16/faster_rcnn_end2end/
中test.prototxt、 train.prototxt文件都要改:
layer {
name: "rpn_cls_score"
type: "Convolution"
bottom: "rpn/output"
top: "rpn_cls_score"
param { lr_mult: 1.0 decay_mult: 1.0 }
param { lr_mult: 2.0 decay_mult: 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 decay_mult: 1.0 }
param { lr_mult: 2.0 decay_mult: 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 } }
}
转自博文:
https://blog.csdn.net/hongxingabc/article/details/80001186?utm_source=copy