深度学习: Faster R-CNN 网络

Structure

Loss Computation

多任务：
Faster R-CNN论文笔记——FR

Fast R-CNN网络有两个同级输出层（cls score和bbox_prdict层），都是全连接层，称为multi-task。
① clsscore层：用于分类，输出k+1维数组p，表示属于k类和背景的概率。对每个RoI（Region of Interesting）输出离散型概率分布

通常，p由k+1类的全连接层利用softmax计算得出。

② bbox_prdict层：用于调整候选区域位置，输出bounding box回归的位移，输出4*K维数组t，表示分别属于k类时，应该平移缩放的参数。

k表示类别的索引，是指相对于objectproposal尺度不变的平移，是指对数空间中相对于objectproposal的高与宽。
loss_cls层评估分类损失函数。由真实分类u对应的概率决定：

loss_bbox评估检测框定位的损失函数。比较真实分类对应的预测平移缩放参数和真实平移缩放参数为
的差别：

其中，smooth L1损失函数为：

smooth L1损失函数曲线如下图9所示，作者这样设置的目的是想让loss对于离群点更加鲁棒，相比于L2损失函数，其对离群点、异常值（outlier）不敏感，可控制梯度的量级使训练时不容易跑飞。

最后总损失为（两者加权和，如果分类为背景则不考虑定位损失）：

规定u=0为背景类（也就是负标签），那么艾弗森括号指数函数[u≥1]表示背景候选区域即负样本不参与回归损失，不需要对候选区域进行回归操作。λ控制分类损失和回归损失的平衡。Fast R-CNN论文中，所有实验λ=1。
艾弗森括号指数函数为：

源码中bbox_loss_weights用于标记每一个bbox是否属于某一个类。

Code

附上作者的源码 rbgirshick/py-faster-rcnn/models/pascal_voc/ZF/faster_rcnn_end2end/train.prototxt ：

name: "ZF"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': 21"  }}#========= conv1-conv5 ============layer {    name: "conv1"    type: "Convolution"    bottom: "data"    top: "conv1"    param { lr_mult: 1.0 }    param { lr_mult: 2.0 }    convolution_param {        num_output: 96        kernel_size: 7        pad: 3        stride: 2    }}layer {    name: "relu1"    type: "ReLU"    bottom: "conv1"    top: "conv1"}layer {    name: "norm1"    type: "LRN"    bottom: "conv1"    top: "norm1"    lrn_param {        local_size: 3        alpha: 0.00005        beta: 0.75        norm_region: WITHIN_CHANNEL    engine: CAFFE    }}layer {    name: "pool1"    type: "Pooling"    bottom: "norm1"    top: "pool1"    pooling_param {        kernel_size: 3        stride: 2        pad: 1        pool: MAX    }}layer {    name: "conv2"    type: "Convolution"    bottom: "pool1"    top: "conv2"    param { lr_mult: 1.0 }    param { lr_mult: 2.0 }    convolution_param {        num_output: 256        kernel_size: 5        pad: 2        stride: 2    }}layer {    name: "relu2"    type: "ReLU"    bottom: "conv2"    top: "conv2"}layer {    name: "norm2"    type: "LRN"    bottom: "conv2"    top: "norm2"    lrn_param {        local_size: 3        alpha: 0.00005        beta: 0.75        norm_region: WITHIN_CHANNEL    engine: CAFFE    }}layer {    name: "pool2"    type: "Pooling"    bottom: "norm2"    top: "pool2"    pooling_param {        kernel_size: 3        stride: 2        pad: 1        pool: MAX    }}layer {    name: "conv3"    type: "Convolution"    bottom: "pool2"    top: "conv3"    param { lr_mult: 1.0 }    param { lr_mult: 2.0 }    convolution_param {        num_output: 384        kernel_size: 3        pad: 1        stride: 1    }}layer {    name: "relu3"    type: "ReLU"    bottom: "conv3"    top: "conv3"}layer {    name: "conv4"    type: "Convolution"    bottom: "conv3"    top: "conv4"    param { lr_mult: 1.0 }    param { lr_mult: 2.0 }    convolution_param {        num_output: 384        kernel_size: 3        pad: 1        stride: 1    }}layer {    name: "relu4"    type: "ReLU"    bottom: "conv4"    top: "conv4"}layer {    name: "conv5"    type: "Convolution"    bottom: "conv4"    top: "conv5"    param { lr_mult: 1.0 }    param { lr_mult: 2.0 }    convolution_param {        num_output: 256        kernel_size: 3        pad: 1        stride: 1    }}layer {    name: "relu5"    type: "ReLU"    bottom: "conv5"    top: "conv5"}#========= 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_conv/3x3"#  type: "Convolution"#  bottom: "conv5"#  top: "rpn_conv/3x3"#  param { lr_mult: 1.0 }#  param { lr_mult: 2.0 }#  convolution_param {#    num_output: 192#    kernel_size: 3 pad: 1 stride: 1#    weight_filler { type: "gaussian" std: 0.01 }#    bias_filler { type: "constant" value: 0 }#  }#}#layer {#  name: "rpn_conv/5x5"#  type: "Convolution"#  bottom: "conv5"#  top: "rpn_conv/5x5"#  param { lr_mult: 1.0 }#  param { lr_mult: 2.0 }#  convolution_param {#    num_output: 64#    kernel_size: 5 pad: 2 stride: 1#    weight_filler { type: "gaussian" std: 0.0036 }#    bias_filler { type: "constant" value: 0 }#  }#}#layer {#  name: "rpn/output"#  type: "Concat"#  bottom: "rpn_conv/3x3"#  bottom: "rpn_conv/5x5"#  top: "rpn/output"#}#layer {#  name: "rpn_relu/output"#  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: 'debug-data'#  type: 'Python'#  bottom: 'data'#  bottom: 'rpn_rois'#  bottom: 'rpn_scores'#  python_param {#    module: 'rpn.debug_layer'#    layer: 'RPNDebugLayer'#  }#}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}