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。