【caffe】SSD网络源码分析

最新推荐文章于 2024-04-22 21:43:37 发布
最新推荐文章于 2024-04-22 21:43:37 发布
阅读量434 收藏 1
点赞数
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/chen1234520nnn/article/details/102548940
版权 
name: "VGG_VOC0712_SSD_300x300_train"
layer {
  name: "data"
  type: "AnnotatedData"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mirror: true   #支持图像镜像
    mean_value: 104.0  #blue层的mean value
    mean_value: 117.0  #green层的mean value 
    mean_value: 123.0  #red层的mean value
    resize_param {
      prob: 1.0       #RESIZE策略的概率，此处只用到一种策略，所以设为概率设为1.
      resize_mode: WARP    #resize采用拉伸（WARP）的方式，即图像尺寸不为300*300时，拉伸到300*300
      height: 300    #训练的尺寸
      width: 300
      interp_mode: LINEAR     #放大图像时，采用的图像插值方式。  下面设置几种方式随机使用。
      interp_mode: AREA
      interp_mode: NEAREST
      interp_mode: CUBIC
      interp_mode: LANCZOS4
    }
    emit_constraint {
      emit_type: CENTER
    }
    distort_param {
      brightness_prob: 0.5
      brightness_delta: 32.0
      contrast_prob: 0.5
      contrast_lower: 0.5
      contrast_upper: 1.5
      hue_prob: 0.5
      hue_delta: 18.0
      saturation_prob: 0.5
      saturation_lower: 0.5
      saturation_upper: 1.5
      random_order_prob: 0.0
    }
    expand_param {
      prob: 0.5
      max_expand_ratio: 4.0
    }
  }
  data_param {
    source: "examples/VOC0712/VOC0712_trainval_lmdb"
    batch_size: 16
    backend: LMDB
  }
  annotated_data_param {  #定义一组batch_sampler,训练时会随机选用其中一种方式对batch中图像进行处理。该方法可以增加训练数据的随机性和多样性。
    batch_sampler {    #该方式为：保持原图，不进行任何处理
      max_sample: 1
      max_trials: 1
    }
    batch_sampler {
      sampler {
        min_scale: 0.300000011921   #缩放因子为（0.3,1.0）间的随机值
        max_scale: 1.0
        min_aspect_ratio: 0.5    #缩放宽高比为（0.5,2.0）间的随机值
        max_aspect_ratio: 2.0
      }
      sample_constraint {
        min_jaccard_overlap: 0.10000000149      #
        }
      max_sample: 1
      max_trials: 50
    }
    batch_sampler {
      sampler {
        min_scale: 0.300000011921
        max_scale: 1.0
        min_aspect_ratio: 0.5
        max_aspect_ratio: 2.0
      }
      sample_constraint {
        min_jaccard_overlap: 0.300000011921
      }
      max_sample: 1
      max_trials: 50
    }
    batch_sampler {
      sampler {
        min_scale: 0.300000011921
        max_scale: 1.0
        min_aspect_ratio: 0.5
        max_aspect_ratio: 2.0
      }
      sample_constraint {
        min_jaccard_overlap: 0.5
      }
      max_sample: 1
      max_trials: 50
    }
    batch_sampler {
      sampler {
        min_scale: 0.300000011921
        max_scale: 1.0
        min_aspect_ratio: 0.5
        max_aspect_ratio: 2.0
      }
      sample_constraint {
        min_jaccard_overlap: 0.699999988079
      }
      max_sample: 1
      max_trials: 50
    }
    batch_sampler {
      sampler {
        min_scale: 0.300000011921
        max_scale: 1.0
        min_aspect_ratio: 0.5
        max_aspect_ratio: 2.0
      }
      sample_constraint {
        min_jaccard_overlap: 0.899999976158
      }
      max_sample: 1
      max_trials: 50
    }
    batch_sampler {
      sampler {
        min_scale: 0.300000011921
        max_scale: 1.0
        min_aspect_ratio: 0.5
        max_aspect_ratio: 2.0
      }
      sample_constraint {
        max_jaccard_overlap: 1.0
      }
      max_sample: 1
      max_trials: 50
    }
    label_map_file: "data/VOC0712/labelmap_voc.prototxt"
  }
}
layer {
  name: "conv1_1"
  type: "Convolution"
  bottom: "data"
  top: "conv1_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 64
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu1_1"
  type: "ReLU"
  bottom: "conv1_1"
  top: "conv1_1"
}
layer {
  name: "conv1_2"
  type: "Convolution"
  bottom: "conv1_1"
  top: "conv1_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 64
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu1_2"
  type: "ReLU"
  bottom: "conv1_2"
  top: "conv1_2"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1_2"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv2_1"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu2_1"
  type: "ReLU"
  bottom: "conv2_1"
  top: "conv2_1"
}
layer {
  name: "conv2_2"
  type: "Convolution"
  bottom: "conv2_1"
  top: "conv2_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu2_2"
  type: "ReLU"
  bottom: "conv2_2"
  top: "conv2_2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2_2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv3_1"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu3_1"
  type: "ReLU"
  bottom: "conv3_1"
  top: "conv3_1"
}
layer {
  name: "conv3_2"
  type: "Convolution"
  bottom: "conv3_1"
  top: "conv3_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu3_2"
  type: "ReLU"
  bottom: "conv3_2"
  top: "conv3_2"
}
layer {
  name: "conv3_3"
  type: "Convolution"
  bottom: "conv3_2"
  top: "conv3_3"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu3_3"
  type: "ReLU"
  bottom: "conv3_3"
  top: "conv3_3"
}
layer {
  name: "pool3"
  type: "Pooling"
  bottom: "conv3_3"
  top: "pool3"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv4_1"
  type: "Convolution"
  bottom: "pool3"
  top: "conv4_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu4_1"
  type: "ReLU"
  bottom: "conv4_1"
  top: "conv4_1"
}
layer {
  name: "conv4_2"
  type: "Convolution"
  bottom: "conv4_1"
  top: "conv4_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu4_2"
  type: "ReLU"
  bottom: "conv4_2"
  top: "conv4_2"
}
layer {
  name: "conv4_3"
  type: "Convolution"
  bottom: "conv4_2"
  top: "conv4_3"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu4_3"
  type: "ReLU"
  bottom: "conv4_3"
  top: "conv4_3"
}
layer {
  name: "pool4"
  type: "Pooling"
  bottom: "conv4_3"
  top: "pool4"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv5_1"
  type: "Convolution"
  bottom: "pool4"
  top: "conv5_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
    dilation: 1
  }
}
layer {
  name: "relu5_1"
  type: "ReLU"
  bottom: "conv5_1"
  top: "conv5_1"
}
layer {
  name: "conv5_2"
  type: "Convolution"
  bottom: "conv5_1"
  top: "conv5_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
    dilation: 1
  }
}
layer {
  name: "relu5_2"
  type: "ReLU"
  bottom: "conv5_2"
  top: "conv5_2"
}
layer {
  name: "conv5_3"
  type: "Convolution"
  bottom: "conv5_2"
  top: "conv5_3"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
    dilation: 1
  }
}
layer {
  name: "relu5_3"
  type: "ReLU"
  bottom: "conv5_3"
  top: "conv5_3"
}
layer {
  name: "pool5"
  type: "Pooling"
  bottom: "conv5_3"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 1
    pad: 1
  }
}
layer {
  name: "fc6"
  type: "Convolution"
  bottom: "pool5"
  top: "fc6"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 1024
    pad: 6
    kernel_size: 3
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
    dilation: 6
  }
}
layer {
  name: "relu6"
  type: "ReLU"
  bottom: "fc6"
  top: "fc6"
}
layer {
  name: "fc7"
  type: "Convolution"
  bottom: "fc6"
  top: "fc7"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 1024
    kernel_size: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "relu7"
  type: "ReLU"
  bottom: "fc7"
  top: "fc7"
}
layer {
  name: "conv6_1"
  type: "Convolution"
  bottom: "fc7"
  top: "conv6_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv6_1_relu"
  type: "ReLU"
  bottom: "conv6_1"
  top: "conv6_1"
}
layer {
  name: "conv6_2"
  type: "Convolution"
  bottom: "conv6_1"
  top: "conv6_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv6_2_relu"
  type: "ReLU"
  bottom: "conv6_2"
  top: "conv6_2"
}
layer {
  name: "conv7_1"
  type: "Convolution"
  bottom: "conv6_2"
  top: "conv7_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 128
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv7_1_relu"
  type: "ReLU"
  bottom: "conv7_1"
  top: "conv7_1"
}
layer {
  name: "conv7_2"
  type: "Convolution"
  bottom: "conv7_1"
  top: "conv7_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    stride: 2
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv7_2_relu"
  type: "ReLU"
  bottom: "conv7_2"
  top: "conv7_2"
}
layer {
  name: "conv8_1"
  type: "Convolution"
  bottom: "conv7_2"
  top: "conv8_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 128
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv8_1_relu"
  type: "ReLU"
  bottom: "conv8_1"
  top: "conv8_1"
}
layer {
  name: "conv8_2"
  type: "Convolution"
  bottom: "conv8_1"
  top: "conv8_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 0
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv8_2_relu"
  type: "ReLU"
  bottom: "conv8_2"
  top: "conv8_2"
}
layer {
  name: "conv9_1"
  type: "Convolution"
  bottom: "conv8_2"
  top: "conv9_1"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 128
    pad: 0
    kernel_size: 1
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv9_1_relu"
  type: "ReLU"
  bottom: "conv9_1"
  top: "conv9_1"
}
layer {
  name: "conv9_2"
  type: "Convolution"
  bottom: "conv9_1"
  top: "conv9_2"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 256
    pad: 0
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv9_2_relu"
  type: "ReLU"
  bottom: "conv9_2"
  top: "conv9_2"
}
layer {
  name: "conv4_3_norm"
  type: "Normalize"
  bottom: "conv4_3"
  top: "conv4_3_norm"
  norm_param {
    across_spatial: false
    scale_filler {
      type: "constant"
      value: 20.0
    }
    channel_shared: false
  }
}
layer {
  name: "conv4_3_norm_mbox_loc"
  type: "Convolution"
  bottom: "conv4_3_norm"
  top: "conv4_3_norm_mbox_loc"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 16  # priorbox_num * 4 ,该层每个cell有4个预测框。每个框有4个坐标值
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {    #permutelayer层的作用：将blob中n*c*w*h的顺序改为n*w*h*c的顺序.(为了使后续flatten后blob的顺序与priorbox一致)
  name: "conv4_3_norm_mbox_loc_perm"
  type: "Permute"
  bottom: "conv4_3_norm_mbox_loc"
  top: "conv4_3_norm_mbox_loc_perm"
  permute_param { # 0:n,1:c,2:w,3:h (n是指batcsize的数量)，按照0231的顺序排列后，数据顺序变成了n*w*h*c
    order: 0 # n 
    order: 2 # w
    order: 3 # h
    order: 1 # c
  }
}
layer {  # Flatten层的作用：将blob数据中每个样本的维度扁平化成1维的。
  name: "conv4_3_norm_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv4_3_norm_mbox_loc_perm"
  top: "conv4_3_norm_mbox_loc_flat"
  flatten_param {
    axis: 1   #此处制定从1号axis开始flatten，即从w开始，将w、h、c维flatten成1维。flatten处理后n*w*h*c变成了n*(whc)，四维blob变成了2维blob。
	      #以conv4_3层为例，batchsize*38*38*16变成batchsize*23104维。
  }
}
layer {
  name: "conv4_3_norm_mbox_conf"
  type: "Convolution"
  bottom: "conv4_3_norm"
  top: "conv4_3_norm_mbox_conf"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 84	# 4*class_num. con4_3层每个cell有4个预测框
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv4_3_norm_mbox_conf_perm"
  type: "Permute"
  bottom: "conv4_3_norm_mbox_conf"
  top: "conv4_3_norm_mbox_conf_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv4_3_norm_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv4_3_norm_mbox_conf_perm"
  top: "conv4_3_norm_mbox_conf_flat"
  flatten_param {
    axis: 1
  }
}
layer {    #生成默认框
  name: "conv4_3_norm_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv4_3_norm"
  bottom: "data"
  top: "conv4_3_norm_mbox_priorbox"
  prior_box_param {
    min_size: 30.0
    max_size: 60.0
    aspect_ratio: 2.0
    flip: true
    clip: false
    variance: 0.10000000149
    variance: 0.10000000149
    variance: 0.20000000298
    variance: 0.20000000298
    step: 8.0
    offset: 0.5
  }
}
layer {
  name: "fc7_mbox_loc"
  type: "Convolution"
  bottom: "fc7"
  top: "fc7_mbox_loc"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 24	# priorbox_num * 4 ,该层每个cell有6个预测框.每个框有4个坐标值
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "fc7_mbox_loc_perm"
  type: "Permute"
  bottom: "fc7_mbox_loc"
  top: "fc7_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "fc7_mbox_loc_flat"
  type: "Flatten"
  bottom: "fc7_mbox_loc_perm"
  top: "fc7_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "fc7_mbox_conf"
  type: "Convolution"
  bottom: "fc7"
  top: "fc7_mbox_conf"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 126  #class_num * 6.  fc7层每个cell有6个预测框
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "fc7_mbox_conf_perm"
  type: "Permute"
  bottom: "fc7_mbox_conf"
  top: "fc7_mbox_conf_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "fc7_mbox_conf_flat"
  type: "Flatten"
  bottom: "fc7_mbox_conf_perm"
  top: "fc7_mbox_conf_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "fc7_mbox_priorbox"
  type: "PriorBox"
  bottom: "fc7"
  bottom: "data"
  top: "fc7_mbox_priorbox"
  prior_box_param {
    min_size: 60.0
    max_size: 111.0
    aspect_ratio: 2.0
    aspect_ratio: 3.0
    flip: true
    clip: false
    variance: 0.10000000149
    variance: 0.10000000149
    variance: 0.20000000298
    variance: 0.20000000298
    step: 16.0
    offset: 0.5
  }
}
layer {
  name: "conv6_2_mbox_loc"
  type: "Convolution"
  bottom: "conv6_2"
  top: "conv6_2_mbox_loc"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 24
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv6_2_mbox_loc_perm"
  type: "Permute"
  bottom: "conv6_2_mbox_loc"
  top: "conv6_2_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv6_2_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv6_2_mbox_loc_perm"
  top: "conv6_2_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv6_2_mbox_conf"
  type: "Convolution"
  bottom: "conv6_2"
  top: "conv6_2_mbox_conf"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 126
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv6_2_mbox_conf_perm"
  type: "Permute"
  bottom: "conv6_2_mbox_conf"
  top: "conv6_2_mbox_conf_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv6_2_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv6_2_mbox_conf_perm"
  top: "conv6_2_mbox_conf_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv6_2_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv6_2"
  bottom: "data"
  top: "conv6_2_mbox_priorbox"
  prior_box_param {
    min_size: 111.0
    max_size: 162.0
    aspect_ratio: 2.0
    aspect_ratio: 3.0
    flip: true
    clip: false
    variance: 0.10000000149
    variance: 0.10000000149
    variance: 0.20000000298
    variance: 0.20000000298
    step: 32.0
    offset: 0.5
  }
}
layer {
  name: "conv7_2_mbox_loc"
  type: "Convolution"
  bottom: "conv7_2"
  top: "conv7_2_mbox_loc"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 24
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv7_2_mbox_loc_perm"
  type: "Permute"
  bottom: "conv7_2_mbox_loc"
  top: "conv7_2_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv7_2_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv7_2_mbox_loc_perm"
  top: "conv7_2_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv7_2_mbox_conf"
  type: "Convolution"
  bottom: "conv7_2"
  top: "conv7_2_mbox_conf"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 126
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv7_2_mbox_conf_perm"
  type: "Permute"
  bottom: "conv7_2_mbox_conf"
  top: "conv7_2_mbox_conf_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv7_2_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv7_2_mbox_conf_perm"
  top: "conv7_2_mbox_conf_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv7_2_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv7_2"
  bottom: "data"
  top: "conv7_2_mbox_priorbox"
  prior_box_param {
    min_size: 162.0
    max_size: 213.0
    aspect_ratio: 2.0
    aspect_ratio: 3.0
    flip: true
    clip: false
    variance: 0.10000000149
    variance: 0.10000000149
    variance: 0.20000000298
    variance: 0.20000000298
    step: 64.0
    offset: 0.5
  }
}
layer {
  name: "conv8_2_mbox_loc"
  type: "Convolution"
  bottom: "conv8_2"
  top: "conv8_2_mbox_loc"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 16
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv8_2_mbox_loc_perm"
  type: "Permute"
  bottom: "conv8_2_mbox_loc"
  top: "conv8_2_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv8_2_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv8_2_mbox_loc_perm"
  top: "conv8_2_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv8_2_mbox_conf"
  type: "Convolution"
  bottom: "conv8_2"
  top: "conv8_2_mbox_conf"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 84
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv8_2_mbox_conf_perm"
  type: "Permute"
  bottom: "conv8_2_mbox_conf"
  top: "conv8_2_mbox_conf_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv8_2_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv8_2_mbox_conf_perm"
  top: "conv8_2_mbox_conf_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv8_2_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv8_2"
  bottom: "data"
  top: "conv8_2_mbox_priorbox"
  prior_box_param {
    min_size: 213.0
    max_size: 264.0
    aspect_ratio: 2.0
    flip: true
    clip: false
    variance: 0.10000000149
    variance: 0.10000000149
    variance: 0.20000000298
    variance: 0.20000000298
    step: 100.0
    offset: 0.5
  }
}
layer {
  name: "conv9_2_mbox_loc"
  type: "Convolution"
  bottom: "conv9_2"
  top: "conv9_2_mbox_loc"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 16
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv9_2_mbox_loc_perm"
  type: "Permute"
  bottom: "conv9_2_mbox_loc"
  top: "conv9_2_mbox_loc_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv9_2_mbox_loc_flat"
  type: "Flatten"
  bottom: "conv9_2_mbox_loc_perm"
  top: "conv9_2_mbox_loc_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv9_2_mbox_conf"
  type: "Convolution"
  bottom: "conv9_2"
  top: "conv9_2_mbox_conf"
  param {
    lr_mult: 1.0
    decay_mult: 1.0
  }
  param {
    lr_mult: 2.0
    decay_mult: 0.0
  }
  convolution_param {
    num_output: 84
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0.0
    }
  }
}
layer {
  name: "conv9_2_mbox_conf_perm"
  type: "Permute"
  bottom: "conv9_2_mbox_conf"
  top: "conv9_2_mbox_conf_perm"
  permute_param {
    order: 0
    order: 2
    order: 3
    order: 1
  }
}
layer {
  name: "conv9_2_mbox_conf_flat"
  type: "Flatten"
  bottom: "conv9_2_mbox_conf_perm"
  top: "conv9_2_mbox_conf_flat"
  flatten_param {
    axis: 1
  }
}
layer {
  name: "conv9_2_mbox_priorbox"
  type: "PriorBox"
  bottom: "conv9_2"
  bottom: "data"
  top: "conv9_2_mbox_priorbox"
  prior_box_param {
    min_size: 264.0
    max_size: 315.0
    aspect_ratio: 2.0
    flip: true
    clip: false
    variance: 0.10000000149
    variance: 0.10000000149
    variance: 0.20000000298
    variance: 0.20000000298
    step: 300.0
    offset: 0.5
  }
}
layer {   # Concat层，将前面6个loc层的blob数据连接起来。batchsize*(conv4_3+fc7+conv6_2+conv7_2+conv8_2+conv9_2)=batchsize*(38*38*4*4+19*19*6*4+10*10*6*4+5*5*6*4+3*3*4*4+1*1*4*4)=batch*34928
  name: "mbox_loc"
  type: "Concat"
  bottom: "conv4_3_norm_mbox_loc_flat"
  bottom: "fc7_mbox_loc_flat"
  bottom: "conv6_2_mbox_loc_flat"
  bottom: "conv7_2_mbox_loc_flat"
  bottom: "conv8_2_mbox_loc_flat"
  bottom: "conv9_2_mbox_loc_flat"
  top: "mbox_loc"
  concat_param {
    axis: 1    #此处也axis是为1，因为第0维是batchsize数量。
  }
}
layer {
  name: "mbox_conf"
  type: "Concat"
  bottom: "conv4_3_norm_mbox_conf_flat"
  bottom: "fc7_mbox_conf_flat"
  bottom: "conv6_2_mbox_conf_flat"
  bottom: "conv7_2_mbox_conf_flat"
  bottom: "conv8_2_mbox_conf_flat"
  bottom: "conv9_2_mbox_conf_flat"
  top: "mbox_conf"
  concat_param {
    axis: 1
  }
}
layer {
  name: "mbox_priorbox"
  type: "Concat"
  bottom: "conv4_3_norm_mbox_priorbox"  #每个featuremap上的储存方式为C×H×W的顺序，维度为C*H*W=2*1*(w*h*prior_num*4),此处不是nchw,因为每个batch中的图像都是一样尺寸的，它们生成的priorbox也是完全相同。另外channel=2，是因为存入了对应位置的方差值。
  bottom: "fc7_mbox_priorbox"
  bottom: "conv6_2_mbox_priorbox"
  bottom: "conv7_2_mbox_priorbox"
  bottom: "conv8_2_mbox_priorbox"
  bottom: "conv9_2_mbox_priorbox"
  top: "mbox_priorbox"
  concat_param {
    axis: 2   #此处axis为2，表示从W的维度将blob连接起来。(W不是指featuremap的宽度w)
  }
}
layer {
  name: "mbox_loss"
  type: "MultiBoxLoss"
  bottom: "mbox_loc"
  bottom: "mbox_conf"
  bottom: "mbox_priorbox"
  bottom: "label"
  top: "mbox_loss"
  include {
    phase: TRAIN
  }
  propagate_down: true
  propagate_down: true
  propagate_down: false
  propagate_down: false
  loss_param {
    normalization: VALID
  }
  multibox_loss_param {
    loc_loss_type: SMOOTH_L1
    conf_loss_type: SOFTMAX
    loc_weight: 1.0
    num_classes: 21
    share_location: true
    match_type: PER_PREDICTION
    overlap_threshold: 0.5
    use_prior_for_matching: true
    background_label_id: 0
    use_difficult_gt: true
    neg_pos_ratio: 3.0
    neg_overlap: 0.5
    code_type: CENTER_SIZE
    ignore_cross_boundary_bbox: false
    mining_type: MAX_NEGATIVE
  }
}

 

主要从三大块来分析源码：

1）mbox_loc层：将6个featuremap得到的moc_loc数据连接到一起。

2）mbox_conf层：将6个featuremap得到的mbox_conf数据连接到一起。

3）mbox_priorbox层：将6个featuremap得到的mbox_priorbox数据连接到一起。

PS：具体的解释，见源码中的注释。

 

超级无敌陈大佬的跟班
关注
SSD源码分析
FelixHaHa的博客
05-18 3821
SSD基本原理 SSD code:https://github.com/balancap/SSD-Tensorflow/issues SSD paper:https://arxiv.org/abs/1512.02325 SSD，全称Single Shot MultiBox Dector，是ECCV 2016刘伟提出的一种目标检测算法，类似于YOLO将目标检测转化为回归的思想。基于Faste...
【caffe】SSD中的default box的可视化
wudi_X的博客
03-23 2431
前言 博主在测试分析目标检测网络SSD的时候，想知道每个检测框是来自哪个default box的，因此需要对SSD源码做适当修改，使其在测试时输出相应的信息。SSD算法的介绍有很多博客讲得很好，这里不多说了。这篇博客主要记录了如何用caffe的python接口测试SSD并获取SSD预测框的default box的索引。 具体步骤 1. 源码修改 首先修改detection_outp...
caffe-SSD网络预训练模型
08-23
这是一个SSD网络的预训练模型，在训练网络的时候你可能需要他
SSD caffe 官方源码分析
qq_31610789的博客
04-07 1005
原理请参考这篇文章 https://www.cnblogs.com/fariver/p/7347197.html 关于每层抽取的特征对应的anchors的种类个数 300x300输入下 fc7层抽取的到 可以看到,后处理后是19x19的grid 每个格子生成24/4=6个anchors对应的location 如上图可以看到类别的预测, fc7对用每个格子126/6=21 每个...
caffe之SSD算法词袋解析
不积跬步，无以致千里；不积小流，无以成江海
07-27 457
text解析接口函数： https://developers.google.com/protocol-buffers/docs/reference/cpp/google.protobuf.text_format 代码如下：#include "caffe/proto/caffe.pb.h" #include <caffe/caffe.hpp> #include <iostream> #includ
caffe-ssd细节梳理
qq_35699505的博客
04-18 1754
为期一周结合ssd源码对ssd的细节进行梳理，其实有些地方仍然不是很明白，但是还是要对自己一周的工作进行总结。 ssd算法，其英文全名是Single Shot MultiBox Detector，属于one-stage方法，MultiBox指明了ssd算法是多框预测，是相对于RCNN系列目标检测算法，yolo系列目标检测算法的改进算法，ssd算法在准确度和速度上都比yolo要好很多，对于Fast...
ubuntu上使用draw_net.py绘制caffe ssd网络结构
jay463261929的博客
03-02 1719
1.先安装依赖库 安装graphviz：    sudo apt-get install graphviz 安装pydot: 先安装pip sudo apt-get install python-pip python-dev build-essential  sudo pip install --upgrade pip  sudo pip install --upgr
caffe-ssd-windows.zip
03-16
解压缩后，你会看到一个名为"caffe-ssd-windows-master"的文件夹，这是Caffe-SSD的项目源码。这个项目已经为Windows平台进行了优化，以便我们能够在CPU上运行SSD模型。 在安装和配置Caffe-SSD之前，确保你的计算机...
caffe 源码解析部分
07-06
**深度学习框架Caffe源码解析** Caffe（Convolutional Architecture for Fast Feature Embedding）是由Berkeley Vision and Learning Center（BVLC）开发的一款高效、开源的深度学习框架，广泛应用于计算机视觉领域...
SSD 源码分析
dengheCSDN的博客
08-22 2042
1、将随机数字去重+排序 程序如下： bool comp(const int &s1, const int &s2) { return s1 < s2; } int main() { int num_total,num; int a[1000] = {0}; // 注意：此时的下标索引不再仅仅是0~9的数字了，而是一个数，可能很大 cin >> num_total;
目标检测算法SSD运行代码caffe
09-27
目标检测算法SSD运行代码,caffe版本，具体代码在目录/caffe-ssd/examples/ssd/下，运行检测代码为py_detect.py
网络结构图SSD
03-31
SSD网络图
【caffe】SSD网络模型中solver.prototxt文件详解
chen1234520nnn的博客
07-19 679
train_net: "models/VGGNet/VOC0712/SSD_300x300/train.prototxt" test_net: "models/VGGNet/VOC0712/SSD_300x300/test.prototxt" test_iter: 619 #测试时的迭代次数 test_interval: 10000 #每10000次迭代测试一次 base_lr: 0.0...
caffe版本和pytorch版本的SSD网络学习及训练过程记录
weixin_42825229的博客
08-15 398
caffe版本和pytorch版本的SSD训练过程记录 caffe版本的SSD 源代码：https://github.com/weiliu89/caffe/tree/ssd 问题一 protobuf版本不一致 .build_release/src/caffe/proto/caffe.pb.h:23:35: fatal error: google/protobuf/arena.h: 没有那个文件或目录 compilation terminated. Makefile:575: recipe for targe
caffe中网络结构参数详解
liu_xiao_cheng的专栏
09-04 652
各种教学视频或文档资料 +QQ：635992897 prototxt文件是caffe的配置文件，用于保存CNN的网络结构和配置信息。prototxt文件有三种，分别是deploy.prototxt，train_val.prototxt和solver.prototxt。   1. solver.prototxt solver.prototxt是caffe的配置文件。里面定义了网络训练时候的...
（12）目标检测_SSD主干网络基于pytorch搭建代码
chencaw的专栏
10-14 1297
dd
SSD源码解析
最新发布
weixin_51363643的博客
04-22 396
借鉴的代码使用的是resnet50作为backbone,具体网络结构如下所示，舍弃conv_5x结构及其之后的网络，并且改变conv_4中第一个block的卷积核的stride，从2->1。因此在backbone中，用net.children()取前7个，同时系应该conv_4中block的步距。forward中传入的参数：bboxes_in是预测的回归参数，scores_in是预测的类别参数。之后采用论文中的方法获取负样本，具体代码编写的方法是英伟达在实现过程中编写的代码方法。
ssd网络结构_SSD 源码实现详细解析 (PyTorch)-模型定义篇
weixin_39989862的博客
11-27 1809
概览SSD 和 YOLO 都是非常主流的 one-stage 目标检测模型, 并且相对于 two-stage 的 RCNN 系列来说, SSD 的实现更加的简明易懂, 接下来我将从以下几个方面展开对 SSD 模型的源码实现讲解: - 模型结构定义 - DefaultBox 生成候选框 - 解析预测结果 - MultiBox 损失函数 - Augmentations Trick - 模型训练 - 模...
2.2 SSD源码解析
qq_45825952的博客
10-05 1516
随着人工智能的不断发展，机器学习这门技术也越来越重要，很多人都开启了学习机器学习，本文就介绍了机器学习的基础内容。来源于哔哩哔哩博主“霹雳吧啦Wz”，博主学习作为笔记记录，欢迎大家一起讨论学习交流。
Caffe Blob源码详解：基础数据结构
源码分析开始于(blob.hpp)文件，引入了四个关键头文件：`caffe/common.hpp`、`caffe/proto/caffe.pb.h`、`caffe/syncedmem.hpp` 和 `caffe/util/math_functions.hpp`。`caffe.pb.h`是Google Protocol Buffers ...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值