大家好,又见面了,我是你们的朋友全栈君。
Overview
RPN的本质是 “ 基于滑窗的无类别object检测器 ” :
RPN所在的位置:
Note:
- 只有在train时,cls+reg才能得到强监督信息(来源于ground truth)。即ground truth会告诉cls+reg结构,哪些才是真的前景,从而引导cls+reg结构学得正确区分前后景的能力;在inference阶段,就要靠cls+reg自力更生了。
- 在train阶段,会输出约2000个proposal,但只会抽取其中256个proposal来训练RPN的cls+reg结构(其中,128个前景proposal用来训练cls+reg,128个背景proposal用来只训练cls);到了inference阶段,则直接输出最高score的300个proposal。此时由于没有了监督信息,所有RPN并不知道这些proposal是否为前景,整个过程只是惯性地推送一波无tag的proposal给后面的Fast R-CNN。
- RPN的运用使得region proposal的额外开销就只有一个两层网络。
放大之后是这样:
庖丁解牛
RPN由以下三部分构成:
-
在 RPN头部 ,通过以下结构生成 anchor(其实就是一堆有编号有坐标的bbox):
论文中的这幅插图对应的就是 RPN头部:
(曾经以为这张图就是整个RPN,于是百思不得其解,走了不少弯路。。。) -
在 RPN中部, 分类分支(cls) 和 边框回归分支(bbox reg) 分别对这堆anchor进行各种计算:
Note: two stage型的检测算法在RPN 之后 还会进行 再一次 的 分类任务 和 边框回归任务,以进一步提升检测精度。 -
在 RPN末端,通过对 两个分支的结果进行汇总,来实现对anchor的 初步筛除(先剔除越界的anchor,再根据cls结果通过NMS算法去重)和 初步偏移(根据bbox reg结果),此时输出的都改头换面叫 Proposal 了:
后话
RPN之后,proposal 成为 RoI (感兴趣区域) ,被输入 RoIPooling 或 RoIAlign 中进行 size上的归一化。当然,这些都是 RPN网络 之后 的操作了,严格来说并 不属于 RPN 的范围 了。
图中 绿框内
为 RPN
,红圈内
为 RoI 以及其对应的 Pooling 操作
:
Note
- 如果只在最后一层 feature map 上映射回原图像,且初始产生的anchor被限定了尺寸下限,那么低于最小anchor尺寸的小目标虽然被anchor圈入,在后面的过程中依然容易被漏检。
- 但是FPN的出现,大大降低了小目标的漏检率,使得RPN如虎添翼。
- 关于RPN的具体结构,我自己也画了一张图解。有兴趣的可以看一下:论文阅读: Faster R-CNN
Source Code
作者的源码 :
#========= RPN ============
layer {
name: "rpn_conv/3x3"
type: "Convolution"
bottom: "conv5"
top: "rpn/output"
param {
lr_mult: 1.0 }
param {
lr_mult: 2.0 }
convolution_param {
num_output: 256
kernel_size: 3 pad: 1 stride: 1
weight_filler {
type: "gaussian" std: 0.01 }
bias_filler {
type: "constant" value: 0 }
}
}
layer {
name: "rpn_relu/3x3"
type: "ReLU"
bottom: "rpn/output"
top: "rpn/output"
}
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: 18 # 2(bg/fg) * 9(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: 36 # 4 * 9(anchors)
kernel_size: 1 pad: 0 stride: 1
weight_filler {
type: "gaussian" std: 0.01 }
bias_filler {
type: "constant" value: 0 }
}
}
layer {
bottom: "rpn_cls_score"
top: "rpn_cls_score_reshape"
name: "rpn_cls_score_reshape"
type: "Reshape"
reshape_param {
shape {
dim: 0 dim: 2 dim: -1 dim: 0 } }
}
layer {
name: 'rpn-data'
type: 'Python'
bottom: 'rpn_cls_score'
bottom: 'gt_boxes'
bottom: 'im_info'
bottom: 'data'
top: 'rpn_labels'
top: 'rpn_bbox_targets'
top: 'rpn_bbox_inside_weights'
top: 'rpn_bbox_outside_weights'
python_param {
module: 'rpn.anchor_target_layer'
layer: 'AnchorTargetLayer'
param_str: "'feat_stride': 16"
}
}
layer {
name: "rpn_loss_cls"
type: "SoftmaxWithLoss"
bottom: "rpn_cls_score_reshape"
bottom: "rpn_labels"
propagate_down: 1
propagate_down: 0
top: "rpn_cls_loss"
loss_weight: 1
loss_param {
ignore_label: -1
normalize: true
}
}
layer {
name: "rpn_loss_bbox"
type: "SmoothL1Loss"
bottom: "rpn_bbox_pred"
bottom: "rpn_bbox_targets"
bottom: 'rpn_bbox_inside_weights'
bottom: 'rpn_bbox_outside_weights'
top: "rpn_loss_bbox"
loss_weight: 1
smooth_l1_loss_param {
sigma: 3.0 }
}
#========= RoI Proposal ============
layer {
name: "rpn_cls_prob"
type: "Softmax"
bottom: "rpn_cls_score_reshape"
top: "rpn_cls_prob"
}
layer {
name: 'rpn_cls_prob_reshape'
type: 'Reshape'
bottom: 'rpn_cls_prob'
top: 'rpn_cls_prob_reshape'
reshape_param {
shape {
dim: 0 dim: 18 dim: -1 dim: 0 } }
}
layer {
name: 'proposal'
type: 'Python'
bottom: 'rpn_cls_prob_reshape'
bottom: 'rpn_bbox_pred'
bottom: 'im_info'
top: 'rpn_rois'
# top: 'rpn_scores'
python_param {
module: 'rpn.proposal_layer'
layer: 'ProposalLayer'
param_str: "'feat_stride': 16"
}
}
layer {
name: 'roi-data'
type: 'Python'
bottom: 'rpn_rois'
bottom: 'gt_boxes'
top: 'rois'
top: 'labels'
top: 'bbox_targets'
top: 'bbox_inside_weights'
top: 'bbox_outside_weights'
python_param {
module: 'rpn.proposal_target_layer'
layer: 'ProposalTargetLayer'
param_str: "'num_classes': 21"
}
}
#========= RCNN ============
layer {
name: "roi_pool_conv5"
type: "ROIPooling"
bottom: "conv5"
bottom: "rois"
top: "roi_pool_conv5"
roi_pooling_param {
pooled_w: 6
pooled_h: 6
spatial_scale: 0.0625 # 1/16
}
}
layer {
name: "fc6"
type: "InnerProduct"
bottom: "roi_pool_conv5"
top: "fc6"
param {
lr_mult: 1.0 }
param {
lr_mult: 2.0 }
inner_product_param {
num_output: 4096
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
scale_train: false
}
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
param {
lr_mult: 1.0 }
param {
lr_mult: 2.0 }
inner_product_param {
num_output: 4096
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
scale_train: false
}
}
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: 21
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: 84
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "loss_cls"
type: "SoftmaxWithLoss"
bottom: "cls_score"
bottom: "labels"
propagate_down: 1
propagate_down: 0
top: "cls_loss"
loss_weight: 1
loss_param {
ignore_label: -1
normalize: true
}
}
layer {
name: "loss_bbox"
type: "SmoothL1Loss"
bottom: "bbox_pred"
bottom: "bbox_targets"
bottom: 'bbox_inside_weights'
bottom: 'bbox_outside_weights'
top: "bbox_loss"
loss_weight: 1
}
发布者:全栈程序员-用户IM,转载请注明出处:https://javaforall.cn/152319.html原文链接:https://javaforall.cn
【正版授权,激活自己账号】: Jetbrains全家桶Ide使用,1年售后保障,每天仅需1毛
【官方授权 正版激活】: 官方授权 正版激活 支持Jetbrains家族下所有IDE 使用个人JB账号...