Caffe: How to train SSD on other model ,such as Alexnet

[songjmcn]

I want to train SSD on other model,such as Alexnet. And I also try to do this. But I can not train the model successful. How can I train SSD with ALexnet?

[weiliu89]

What do you mean you cannot train the model successfully? Does the loss diverge or become nan?

[songjmcn]

I can train the model ,and the loss can descent。But when I test the model，the arruracy became 0

[weiliu89]

Do you see the mAP during training? You can search "detection_eval = " in the .log file. I am guessing you miss some layers or didn't do it right somewhere..

[songjmcn]

I also think。But I don‘t know where is wrong。

[weiliu89]

You can send me your train.prototxt and test.prototxt. I can take a look.

[songjmcn]

name: "AlexNet"
layer {
name: "data"
type: "AnnotatedData"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
mean_value: 104
mean_value: 117
mean_value: 123
resize_param {
prob: 1
resize_mode: WARP
height: 300
width: 300
interp_mode: LINEAR
interp_mode: AREA
interp_mode: NEAREST
interp_mode: CUBIC
interp_mode: LANCZOS4
}
emit_constraint {
emit_type: CENTER
}
}
data_param {
source: "/home/song/data/VOCdevkit/VOC0712/lmdb/VOC0712_trainval_lmdb"
batch_size: 16
backend: LMDB
}
annotated_data_param {
batch_sampler {
max_sample: 1
max_trials: 1
}
batch_sampler {
sampler {
min_scale: 0.3
max_scale: 1.0
min_aspect_ratio: 0.5
max_aspect_ratio: 2.0
}
sample_constraint {
min_jaccard_overlap: 0.1
}
max_sample: 1
max_trials: 50
}
batch_sampler {
sampler {
min_scale: 0.3
max_scale: 1.0
min_aspect_ratio: 0.5
max_aspect_ratio: 2.0
}
sample_constraint {
min_jaccard_overlap: 0.3
}
max_sample: 1
max_trials: 50
}
batch_sampler {
sampler {
min_scale: 0.3
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: 0.3
max_scale: 1.0
min_aspect_ratio: 0.5
max_aspect_ratio: 2.0
}
sample_constraint {
min_jaccard_overlap: 0.7
}
max_sample: 1
max_trials: 50
}
batch_sampler {
sampler {
min_scale: 0.3
max_scale: 1.0
min_aspect_ratio: 0.5
max_aspect_ratio: 2.0
}
sample_constraint {
min_jaccard_overlap: 0.9
}
max_sample: 1
max_trials: 50
}
batch_sampler {
sampler {
min_scale: 0.3
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: "/home/song/caffe-ssd/data/VOC0712/labelmap_voc.prototxt"
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
pad: 5
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "norm1"
type: "LRN"
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "pool1"
type: "Pooling"
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
pad:1
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 2
group:2
kernel_size: 5
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "norm2"
type: "LRN"
bottom: "conv2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}

layer {
name: "conv3"
type: "Convolution"
bottom: "norm2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4_3"
top: "conv4_3"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv4_3"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv5"
type: "Convolution"
bottom: "pool2"
top: "conv5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 1
pad:1
}
}
layer {
name: "fc6-conv"
type: "Convolution"
bottom: "pool5"
top: "fc6"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 1024
kernel_size: 3
#dilation: 3
pad: 6
dilation:6
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}

}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7-conv"
type: "Convolution"
bottom: "fc6"
top: "fc7"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 1024
kernel_size: 1
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "conv6_1"
type: "Convolution"
bottom: "fc7"
top: "conv6_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 128
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 128
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "conv8_2_relu"
type: "ReLU"
bottom: "conv8_2"
top: "conv8_2"
}
layer {
name: "pool6"
type: "Pooling"
bottom: "conv8_2"
top: "pool6"
pooling_param {
pool: AVE
global_pooling: true
}
}
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
}
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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 12
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "conv4_3_norm_mbox_loc_perm"
type: "Permute"
bottom: "conv4_3_norm_mbox_loc"
top: "conv4_3_norm_mbox_loc_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
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
}
}
layer {
name: "conv4_3_norm_mbox_conf"
type: "Convolution"
bottom: "conv4_3_norm"
top: "conv4_3_norm_mbox_conf"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 63
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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 {
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
aspect_ratio: 2
flip: true
clip: true
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
}
}
layer {
name: "fc7_mbox_loc"
type: "Convolution"
bottom: "fc7"
top: "fc7_mbox_loc"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 24
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 126
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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: 114.0
aspect_ratio: 2
aspect_ratio: 3
flip: true
clip: true
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
}
}
layer {
name: "conv6_2_mbox_loc"
type: "Convolution"
bottom: "conv6_2"
top: "conv6_2_mbox_loc"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 24
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 126
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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: 114.0
max_size: 168.0
aspect_ratio: 2
aspect_ratio: 3
flip: true
clip: true
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
}
}
layer {
name: "conv7_2_mbox_loc"
type: "Convolution"
bottom: "conv7_2"
top: "conv7_2_mbox_loc"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 24
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 126
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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: 168.0
max_size: 222.0
aspect_ratio: 2
aspect_ratio: 3
flip: true
clip: true
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
}
}
layer {
name: "conv8_2_mbox_loc"
type: "Convolution"
bottom: "conv8_2"
top: "conv8_2_mbox_loc"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 24
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 126
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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: 222.0
max_size: 276.0
aspect_ratio: 2
aspect_ratio: 3
flip: true
clip: true
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
}
}
layer {
name: "pool6_mbox_loc"
type: "Convolution"
bottom: "pool6"
top: "pool6_mbox_loc"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 24
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "pool6_mbox_loc_perm"
type: "Permute"
bottom: "pool6_mbox_loc"
top: "pool6_mbox_loc_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "pool6_mbox_loc_flat"
type: "Flatten"
bottom: "pool6_mbox_loc_perm"
top: "pool6_mbox_loc_flat"
flatten_param {
axis: 1
}
}
layer {
name: "pool6_mbox_conf"
type: "Convolution"
bottom: "pool6"
top: "pool6_mbox_conf"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 126
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "pool6_mbox_conf_perm"
type: "Permute"
bottom: "pool6_mbox_conf"
top: "pool6_mbox_conf_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "pool6_mbox_conf_flat"
type: "Flatten"
bottom: "pool6_mbox_conf_perm"
top: "pool6_mbox_conf_flat"
flatten_param {
axis: 1
}
}
layer {
name: "pool6_mbox_priorbox"
type: "PriorBox"
bottom: "pool6"
bottom: "data"
top: "pool6_mbox_priorbox"
prior_box_param {
min_size: 276.0
max_size: 330.0
aspect_ratio: 2
aspect_ratio: 3
flip: true
clip: true
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
}
}
layer {
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: "pool6_mbox_loc_flat"
top: "mbox_loc"
concat_param {
axis: 1
}
}
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: "pool6_mbox_conf_flat"
top: "mbox_conf"
concat_param {
axis: 1
}
}
layer {
name: "mbox_priorbox"
type: "Concat"
bottom: "conv4_3_norm_mbox_priorbox"
bottom: "fc7_mbox_priorbox"
bottom: "conv6_2_mbox_priorbox"
bottom: "conv7_2_mbox_priorbox"
bottom: "conv8_2_mbox_priorbox"
bottom: "pool6_mbox_priorbox"
top: "mbox_priorbox"
concat_param {
axis: 2
}
}
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
do_neg_mining: true
neg_pos_ratio: 3.0
neg_overlap: 0.5
code_type: CENTER_SIZE
}
}

This is my train file
name: "AlexNet"
layer {
name: "data"
type: "AnnotatedData"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
mean_value: 104
mean_value: 117
mean_value: 123
resize_param {
prob: 1
resize_mode: WARP
height: 300
width: 300
interp_mode: LINEAR
}
}
data_param {
source: "/home/song/data/VOCdevkit/VOC0712/lmdb/VOC0712_test_lmdb"
batch_size: 1
backend: LMDB
}
annotated_data_param {
batch_sampler {
}
label_map_file: "/home/song/caffe-ssd/data/coco/labelmap_coco.prototxt"
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
pad: 5
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "norm1"
type: "LRN"
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "pool1"
type: "Pooling"
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
pad:1
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 2
group:2
kernel_size: 5
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "norm2"
type: "LRN"
bottom: "conv2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}

layer {
name: "conv3"
type: "Convolution"
bottom: "norm2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
group: 2
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}

layer {
name: "relu4"
type: "ReLU"
bottom: "conv4_3"
top: "conv4_3"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv4_3"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv5"
type: "Convolution"
bottom: "pool2"
top: "conv5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 1
pad:1
}
}
layer {
name: "fc6-conv"
type: "Convolution"
bottom: "pool5"
top: "fc6"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 1024
kernel_size: 3
dilation: 6
pad: 6
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7-conv"
type: "Convolution"
bottom: "fc6"
top: "fc7"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 1024
kernel_size: 1
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "conv6_1"
type: "Convolution"
bottom: "fc7"
top: "conv6_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 128
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 128
pad: 0
kernel_size: 1
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "conv8_2_relu"
type: "ReLU"
bottom: "conv8_2"
top: "conv8_2"
}
layer {
name: "pool6"
type: "Pooling"
bottom: "conv8_2"
top: "pool6"
pooling_param {
pool: AVE
global_pooling: true
}
}
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
}
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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 12
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "conv4_3_norm_mbox_loc_perm"
type: "Permute"
bottom: "conv4_3_norm_mbox_loc"
top: "conv4_3_norm_mbox_loc_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
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
}
}
layer {
name: "conv4_3_norm_mbox_conf"
type: "Convolution"
bottom: "conv4_3_norm"
top: "conv4_3_norm_mbox_conf"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 63
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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 {
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
aspect_ratio: 2
flip: true
clip: true
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
}
}
layer {
name: "fc7_mbox_loc"
type: "Convolution"
bottom: "fc7"
top: "fc7_mbox_loc"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 24
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 126
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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: 114.0
aspect_ratio: 2
aspect_ratio: 3
flip: true
clip: true
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
}
}
layer {
name: "conv6_2_mbox_loc"
type: "Convolution"
bottom: "conv6_2"
top: "conv6_2_mbox_loc"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 24
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 126
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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: 114.0
max_size: 168.0
aspect_ratio: 2
aspect_ratio: 3
flip: true
clip: true
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
}
}
layer {
name: "conv7_2_mbox_loc"
type: "Convolution"
bottom: "conv7_2"
top: "conv7_2_mbox_loc"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 24
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 126
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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: 168.0
max_size: 222.0
aspect_ratio: 2
aspect_ratio: 3
flip: true
clip: true
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
}
}
layer {
name: "conv8_2_mbox_loc"
type: "Convolution"
bottom: "conv8_2"
top: "conv8_2_mbox_loc"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 24
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 126
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 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: 222.0
max_size: 276.0
aspect_ratio: 2
aspect_ratio: 3
flip: true
clip: true
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
}
}
layer {
name: "pool6_mbox_loc"
type: "Convolution"
bottom: "pool6"
top: "pool6_mbox_loc"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 24
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "pool6_mbox_loc_perm"
type: "Permute"
bottom: "pool6_mbox_loc"
top: "pool6_mbox_loc_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "pool6_mbox_loc_flat"
type: "Flatten"
bottom: "pool6_mbox_loc_perm"
top: "pool6_mbox_loc_flat"
flatten_param {
axis: 1
}
}
layer {
name: "pool6_mbox_conf"
type: "Convolution"
bottom: "pool6"
top: "pool6_mbox_conf"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 126
pad: 1
kernel_size: 3
stride: 1
weight_filler {
type: "xavier"
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "pool6_mbox_conf_perm"
type: "Permute"
bottom: "pool6_mbox_conf"
top: "pool6_mbox_conf_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "pool6_mbox_conf_flat"
type: "Flatten"
bottom: "pool6_mbox_conf_perm"
top: "pool6_mbox_conf_flat"
flatten_param {
axis: 1
}
}
layer {
name: "pool6_mbox_priorbox"
type: "PriorBox"
bottom: "pool6"
bottom: "data"
top: "pool6_mbox_priorbox"
prior_box_param {
min_size: 276.0
max_size: 330.0
aspect_ratio: 2
aspect_ratio: 3
flip: true
clip: true
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
}
}
layer {
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: "pool6_mbox_loc_flat"
top: "mbox_loc"
concat_param {
axis: 1
}
}
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: "pool6_mbox_conf_flat"
top: "mbox_conf"
concat_param {
axis: 1
}
}
layer {
name: "mbox_priorbox"
type: "Concat"
bottom: "conv4_3_norm_mbox_priorbox"
bottom: "fc7_mbox_priorbox"
bottom: "conv6_2_mbox_priorbox"
bottom: "conv7_2_mbox_priorbox"
bottom: "conv8_2_mbox_priorbox"
bottom: "pool6_mbox_priorbox"
top: "mbox_priorbox"
concat_param {
axis: 2
}
}
layer {
name: "mbox_conf_reshape"
type: "Reshape"
bottom: "mbox_conf"
top: "mbox_conf_reshape"
reshape_param {
shape {
dim: 0
dim: -1
dim: 21
}
}
}
layer {
name: "mbox_conf_softmax"
type: "Softmax"
bottom: "mbox_conf_reshape"
top: "mbox_conf_softmax"
softmax_param {
axis: 2
}
}
layer {
name: "mbox_conf_flatten"
type: "Flatten"
bottom: "mbox_conf_softmax"
top: "mbox_conf_flatten"
flatten_param {
axis: 1
}
}
layer {
name: "detection_out"
type: "DetectionOutput"
bottom: "mbox_loc"
bottom: "mbox_conf_flatten"
bottom: "mbox_priorbox"
top: "detection_out"
include {
phase: TEST
}
detection_output_param {
num_classes: 21
share_location: true
background_label_id: 0
nms_param {
nms_threshold: 0.45
top_k: 400
}
save_output_param {
output_directory: "/home/song/data/VOCdevkit/results/VOC2007/SSD_300x300/Main"
output_name_prefix: "comp4_det_test_"
output_format: "VOC"
label_map_file: "/home/song/caffe-ssd/data/VOC0712/labelmap_voc.prototxt"
name_size_file: "/home/song/caffe-ssd/data/VOC0712/test_name_size.txt"
num_test_image: 4952
}
code_type: CENTER_SIZE
keep_top_k: 200
confidence_threshold: 0.01
}
}
layer {
name: "detection_eval"
type: "DetectionEvaluate"
bottom: "detection_out"
bottom: "label"
top: "detection_eval"
include {
phase: TEST
}
detection_evaluate_param {
num_classes: 21
background_label_id: 0
overlap_threshold: 0.5
evaluate_difficult_gt: false
name_size_file: "/home/song/caffe-ssd/data/VOC0712/test_name_size.txt"
}
}
this is my test file

[weiliu89]

Hmm, you have labelmap_coco.prototxt in your test.prototxt. You should change it to VOC.

[songjmcn]

What’s wrong withe model struct？ I think there is something wrong in the network

[weiliu89]

You should change "/home/song/caffe-ssd/data/coco/labelmap_coco.prototxt" to "/home/song/caffe-ssd/data/VOC0712/labelmap_voc.prototxt" in your AnnotatedDataLayer in test.prototxt.

[songjmcn]

Thanks，I test it。

[lcj1105]

@songjmcn could you share the code of "def AlexNetBody" , thank you .

[crystalxian]

@songjmcn Hi, what's your detection eval? I can only get 0.45 detection accuracy using alexnet after about 60000 iteration with batchsize 32.

[songjmcn]

I get 0.51 detection accuray using alexnet after 100000 iteraion with batchsize 16.

[leejiajun]

@songjmcn Could you share your slover of AlexNet?

[ghost]

Why did I run the code you gave above and got an error：
Cannot copy param 0 weights from layer 'conv4_3_norm'; shape mismatch. Source param shape is 512(512);target param shape is 384 (384).
While I change num_output to 512,There is another error:
Cannot copy param 0 weights from layer 'conv4'; shape mismatch. Source param shape is 384 192 3 3 (663552);target param shape is 512 192 3 3 (884736).
And while I change con4 to conv4_3,There is another error:
Cannot copy param 0 weights from layer shape is 512 512 3 3 (2359296); target param shape is 384 192 3 3 (663552).
I don't know whether my method is correct.I use 2 caffemodels to fine-tuning the network.