Skip to content

O
opencv
Commit 2959e7ab authored by Alexander Alekhin's avatar Alexander Alekhin
Browse files
Options

Merge pull request #9188 from arrybn:mobilenet_ssd_sample

parents d34eec3a ce1cc352
Hide whitespace changes
Inline Side-by-side
Showing with 3352 additions and 1 deletion
modules/dnn/src/layers/detection_output_layer.cpp
View file @ 2959e7ab
......@@ -234,7 +234,7 @@ public:
if (numKept == 0)
{
CV_ErrorNoReturn(Error::StsError, "Couldn't find any detections");
return;
}
int outputShape[] = {1, 1, (int)numKept, 7};
outputs[0].create(4, outputShape, CV_32F);
......
samples/data/dnn/MobileNetSSD_300x300.prototxt 0 → 100644
View file @ 2959e7ab
name: "MobileNet-SSD"
input: "data"
input_shape {
dim: 1
dim: 3
dim: 300
dim: 300
}
layer {
name: "conv0"
type: "Convolution"
bottom: "data"
top: "conv0"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 32
bias_term: false
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv0/bn"
type: "BatchNorm"
bottom: "conv0"
top: "conv0"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv0/scale"
type: "Scale"
bottom: "conv0"
top: "conv0"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv0/relu"
type: "ReLU"
bottom: "conv0"
top: "conv0"
}
layer {
name: "conv1/dw"
type: "Convolution"
bottom: "conv0"
top: "conv1/dw"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 32
bias_term: false
pad: 1
kernel_size: 3
group: 32
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv1/dw/bn"
type: "BatchNorm"
bottom: "conv1/dw"
top: "conv1/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv1/dw/scale"
type: "Scale"
bottom: "conv1/dw"
top: "conv1/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv1/dw/relu"
type: "ReLU"
bottom: "conv1/dw"
top: "conv1/dw"
}
layer {
name: "conv1"
type: "Convolution"
bottom: "conv1/dw"
top: "conv1"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 64
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv1/bn"
type: "BatchNorm"
bottom: "conv1"
top: "conv1"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv1/scale"
type: "Scale"
bottom: "conv1"
top: "conv1"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv1/relu"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "conv2/dw"
type: "Convolution"
bottom: "conv1"
top: "conv2/dw"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 64
bias_term: false
pad: 1
kernel_size: 3
stride: 2
group: 64
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv2/dw/bn"
type: "BatchNorm"
bottom: "conv2/dw"
top: "conv2/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv2/dw/scale"
type: "Scale"
bottom: "conv2/dw"
top: "conv2/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv2/dw/relu"
type: "ReLU"
bottom: "conv2/dw"
top: "conv2/dw"
}
layer {
name: "conv2"
type: "Convolution"
bottom: "conv2/dw"
top: "conv2"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 128
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv2/bn"
type: "BatchNorm"
bottom: "conv2"
top: "conv2"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv2/scale"
type: "Scale"
bottom: "conv2"
top: "conv2"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv2/relu"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "conv3/dw"
type: "Convolution"
bottom: "conv2"
top: "conv3/dw"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 128
bias_term: false
pad: 1
kernel_size: 3
group: 128
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv3/dw/bn"
type: "BatchNorm"
bottom: "conv3/dw"
top: "conv3/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv3/dw/scale"
type: "Scale"
bottom: "conv3/dw"
top: "conv3/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv3/dw/relu"
type: "ReLU"
bottom: "conv3/dw"
top: "conv3/dw"
}
layer {
name: "conv3"
type: "Convolution"
bottom: "conv3/dw"
top: "conv3"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 128
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv3/bn"
type: "BatchNorm"
bottom: "conv3"
top: "conv3"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv3/scale"
type: "Scale"
bottom: "conv3"
top: "conv3"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv3/relu"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4/dw"
type: "Convolution"
bottom: "conv3"
top: "conv4/dw"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 128
bias_term: false
pad: 1
kernel_size: 3
stride: 2
group: 128
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv4/dw/bn"
type: "BatchNorm"
bottom: "conv4/dw"
top: "conv4/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv4/dw/scale"
type: "Scale"
bottom: "conv4/dw"
top: "conv4/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv4/dw/relu"
type: "ReLU"
bottom: "conv4/dw"
top: "conv4/dw"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv4/dw"
top: "conv4"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 256
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv4/bn"
type: "BatchNorm"
bottom: "conv4"
top: "conv4"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv4/scale"
type: "Scale"
bottom: "conv4"
top: "conv4"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv4/relu"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5/dw"
type: "Convolution"
bottom: "conv4"
top: "conv5/dw"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 256
bias_term: false
pad: 1
kernel_size: 3
group: 256
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv5/dw/bn"
type: "BatchNorm"
bottom: "conv5/dw"
top: "conv5/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv5/dw/scale"
type: "Scale"
bottom: "conv5/dw"
top: "conv5/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv5/dw/relu"
type: "ReLU"
bottom: "conv5/dw"
top: "conv5/dw"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv5/dw"
top: "conv5"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 256
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv5/bn"
type: "BatchNorm"
bottom: "conv5"
top: "conv5"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv5/scale"
type: "Scale"
bottom: "conv5"
top: "conv5"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv5/relu"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "conv6/dw"
type: "Convolution"
bottom: "conv5"
top: "conv6/dw"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 256
bias_term: false
pad: 1
kernel_size: 3
stride: 2
group: 256
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv6/dw/bn"
type: "BatchNorm"
bottom: "conv6/dw"
top: "conv6/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv6/dw/scale"
type: "Scale"
bottom: "conv6/dw"
top: "conv6/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv6/dw/relu"
type: "ReLU"
bottom: "conv6/dw"
top: "conv6/dw"
}
layer {
name: "conv6"
type: "Convolution"
bottom: "conv6/dw"
top: "conv6"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 512
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv6/bn"
type: "BatchNorm"
bottom: "conv6"
top: "conv6"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv6/scale"
type: "Scale"
bottom: "conv6"
top: "conv6"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv6/relu"
type: "ReLU"
bottom: "conv6"
top: "conv6"
}
layer {
name: "conv7/dw"
type: "Convolution"
bottom: "conv6"
top: "conv7/dw"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv7/dw/bn"
type: "BatchNorm"
bottom: "conv7/dw"
top: "conv7/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv7/dw/scale"
type: "Scale"
bottom: "conv7/dw"
top: "conv7/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv7/dw/relu"
type: "ReLU"
bottom: "conv7/dw"
top: "conv7/dw"
}
layer {
name: "conv7"
type: "Convolution"
bottom: "conv7/dw"
top: "conv7"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 512
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv7/bn"
type: "BatchNorm"
bottom: "conv7"
top: "conv7"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv7/scale"
type: "Scale"
bottom: "conv7"
top: "conv7"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv7/relu"
type: "ReLU"
bottom: "conv7"
top: "conv7"
}
layer {
name: "conv8/dw"
type: "Convolution"
bottom: "conv7"
top: "conv8/dw"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv8/dw/bn"
type: "BatchNorm"
bottom: "conv8/dw"
top: "conv8/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv8/dw/scale"
type: "Scale"
bottom: "conv8/dw"
top: "conv8/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv8/dw/relu"
type: "ReLU"
bottom: "conv8/dw"
top: "conv8/dw"
}
layer {
name: "conv8"
type: "Convolution"
bottom: "conv8/dw"
top: "conv8"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 512
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv8/bn"
type: "BatchNorm"
bottom: "conv8"
top: "conv8"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv8/scale"
type: "Scale"
bottom: "conv8"
top: "conv8"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv8/relu"
type: "ReLU"
bottom: "conv8"
top: "conv8"
}
layer {
name: "conv9/dw"
type: "Convolution"
bottom: "conv8"
top: "conv9/dw"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv9/dw/bn"
type: "BatchNorm"
bottom: "conv9/dw"
top: "conv9/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv9/dw/scale"
type: "Scale"
bottom: "conv9/dw"
top: "conv9/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv9/dw/relu"
type: "ReLU"
bottom: "conv9/dw"
top: "conv9/dw"
}
layer {
name: "conv9"
type: "Convolution"
bottom: "conv9/dw"
top: "conv9"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 512
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv9/bn"
type: "BatchNorm"
bottom: "conv9"
top: "conv9"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv9/scale"
type: "Scale"
bottom: "conv9"
top: "conv9"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv9/relu"
type: "ReLU"
bottom: "conv9"
top: "conv9"
}
layer {
name: "conv10/dw"
type: "Convolution"
bottom: "conv9"
top: "conv10/dw"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv10/dw/bn"
type: "BatchNorm"
bottom: "conv10/dw"
top: "conv10/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv10/dw/scale"
type: "Scale"
bottom: "conv10/dw"
top: "conv10/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv10/dw/relu"
type: "ReLU"
bottom: "conv10/dw"
top: "conv10/dw"
}
layer {
name: "conv10"
type: "Convolution"
bottom: "conv10/dw"
top: "conv10"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 512
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv10/bn"
type: "BatchNorm"
bottom: "conv10"
top: "conv10"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv10/scale"
type: "Scale"
bottom: "conv10"
top: "conv10"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv10/relu"
type: "ReLU"
bottom: "conv10"
top: "conv10"
}
layer {
name: "conv11/dw"
type: "Convolution"
bottom: "conv10"
top: "conv11/dw"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv11/dw/bn"
type: "BatchNorm"
bottom: "conv11/dw"
top: "conv11/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv11/dw/scale"
type: "Scale"
bottom: "conv11/dw"
top: "conv11/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv11/dw/relu"
type: "ReLU"
bottom: "conv11/dw"
top: "conv11/dw"
}
layer {
name: "conv11"
type: "Convolution"
bottom: "conv11/dw"
top: "conv11"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 512
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv11/bn"
type: "BatchNorm"
bottom: "conv11"
top: "conv11"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv11/scale"
type: "Scale"
bottom: "conv11"
top: "conv11"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv11/relu"
type: "ReLU"
bottom: "conv11"
top: "conv11"
}
layer {
name: "conv12/dw"
type: "Convolution"
bottom: "conv11"
top: "conv12/dw"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
stride: 2
group: 512
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv12/dw/bn"
type: "BatchNorm"
bottom: "conv12/dw"
top: "conv12/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv12/dw/scale"
type: "Scale"
bottom: "conv12/dw"
top: "conv12/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv12/dw/relu"
type: "ReLU"
bottom: "conv12/dw"
top: "conv12/dw"
}
layer {
name: "conv12"
type: "Convolution"
bottom: "conv12/dw"
top: "conv12"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 1024
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv12/bn"
type: "BatchNorm"
bottom: "conv12"
top: "conv12"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv12/scale"
type: "Scale"
bottom: "conv12"
top: "conv12"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv12/relu"
type: "ReLU"
bottom: "conv12"
top: "conv12"
}
layer {
name: "conv13/dw"
type: "Convolution"
bottom: "conv12"
top: "conv13/dw"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 1024
bias_term: false
pad: 1
kernel_size: 3
group: 1024
engine: CAFFE
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv13/dw/bn"
type: "BatchNorm"
bottom: "conv13/dw"
top: "conv13/dw"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv13/dw/scale"
type: "Scale"
bottom: "conv13/dw"
top: "conv13/dw"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv13/dw/relu"
type: "ReLU"
bottom: "conv13/dw"
top: "conv13/dw"
}
layer {
name: "conv13"
type: "Convolution"
bottom: "conv13/dw"
top: "conv13"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 1024
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv13/bn"
type: "BatchNorm"
bottom: "conv13"
top: "conv13"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv13/scale"
type: "Scale"
bottom: "conv13"
top: "conv13"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv13/relu"
type: "ReLU"
bottom: "conv13"
top: "conv13"
}
layer {
name: "conv14_1"
type: "Convolution"
bottom: "conv13"
top: "conv14_1"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 256
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv14_1/bn"
type: "BatchNorm"
bottom: "conv14_1"
top: "conv14_1"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv14_1/scale"
type: "Scale"
bottom: "conv14_1"
top: "conv14_1"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv14_1/relu"
type: "ReLU"
bottom: "conv14_1"
top: "conv14_1"
}
layer {
name: "conv14_2"
type: "Convolution"
bottom: "conv14_1"
top: "conv14_2"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 512
bias_term: false
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv14_2/bn"
type: "BatchNorm"
bottom: "conv14_2"
top: "conv14_2"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv14_2/scale"
type: "Scale"
bottom: "conv14_2"
top: "conv14_2"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv14_2/relu"
type: "ReLU"
bottom: "conv14_2"
top: "conv14_2"
}
layer {
name: "conv15_1"
type: "Convolution"
bottom: "conv14_2"
top: "conv15_1"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 128
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv15_1/bn"
type: "BatchNorm"
bottom: "conv15_1"
top: "conv15_1"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv15_1/scale"
type: "Scale"
bottom: "conv15_1"
top: "conv15_1"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv15_1/relu"
type: "ReLU"
bottom: "conv15_1"
top: "conv15_1"
}
layer {
name: "conv15_2"
type: "Convolution"
bottom: "conv15_1"
top: "conv15_2"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 256
bias_term: false
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv15_2/bn"
type: "BatchNorm"
bottom: "conv15_2"
top: "conv15_2"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv15_2/scale"
type: "Scale"
bottom: "conv15_2"
top: "conv15_2"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv15_2/relu"
type: "ReLU"
bottom: "conv15_2"
top: "conv15_2"
}
layer {
name: "conv16_1"
type: "Convolution"
bottom: "conv15_2"
top: "conv16_1"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 128
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv16_1/bn"
type: "BatchNorm"
bottom: "conv16_1"
top: "conv16_1"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv16_1/scale"
type: "Scale"
bottom: "conv16_1"
top: "conv16_1"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv16_1/relu"
type: "ReLU"
bottom: "conv16_1"
top: "conv16_1"
}
layer {
name: "conv16_2"
type: "Convolution"
bottom: "conv16_1"
top: "conv16_2"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 256
bias_term: false
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv16_2/bn"
type: "BatchNorm"
bottom: "conv16_2"
top: "conv16_2"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv16_2/scale"
type: "Scale"
bottom: "conv16_2"
top: "conv16_2"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv16_2/relu"
type: "ReLU"
bottom: "conv16_2"
top: "conv16_2"
}
layer {
name: "conv17_1"
type: "Convolution"
bottom: "conv16_2"
top: "conv17_1"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 64
bias_term: false
kernel_size: 1
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv17_1/bn"
type: "BatchNorm"
bottom: "conv17_1"
top: "conv17_1"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv17_1/scale"
type: "Scale"
bottom: "conv17_1"
top: "conv17_1"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv17_1/relu"
type: "ReLU"
bottom: "conv17_1"
top: "conv17_1"
}
layer {
name: "conv17_2"
type: "Convolution"
bottom: "conv17_1"
top: "conv17_2"
param {
lr_mult: 1.0
decay_mult: 1.0
}
convolution_param {
num_output: 128
bias_term: false
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "msra"
}
}
}
layer {
name: "conv17_2/bn"
type: "BatchNorm"
bottom: "conv17_2"
top: "conv17_2"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
}
layer {
name: "conv17_2/scale"
type: "Scale"
bottom: "conv17_2"
top: "conv17_2"
param {
lr_mult: 0.1
decay_mult: 0.0
}
param {
lr_mult: 0.2
decay_mult: 0.0
}
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
layer {
name: "conv17_2/relu"
type: "ReLU"
bottom: "conv17_2"
top: "conv17_2"
}
layer {
name: "conv11_mbox_loc"
type: "Convolution"
bottom: "conv11"
top: "conv11_mbox_loc"
param {
lr_mult: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
convolution_param {
num_output: 12
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv11_mbox_loc_perm"
type: "Permute"
bottom: "conv11_mbox_loc"
top: "conv11_mbox_loc_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv11_mbox_loc_flat"
type: "Flatten"
bottom: "conv11_mbox_loc_perm"
top: "conv11_mbox_loc_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv11_mbox_conf"
type: "Convolution"
bottom: "conv11"
top: "conv11_mbox_conf"
param {
lr_mult: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
convolution_param {
num_output: 63
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv11_mbox_conf_perm"
type: "Permute"
bottom: "conv11_mbox_conf"
top: "conv11_mbox_conf_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv11_mbox_conf_flat"
type: "Flatten"
bottom: "conv11_mbox_conf_perm"
top: "conv11_mbox_conf_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv11_mbox_priorbox"
type: "PriorBox"
bottom: "conv11"
bottom: "data"
top: "conv11_mbox_priorbox"
prior_box_param {
min_size: 60.0
aspect_ratio: 2.0
flip: true
clip: false
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
offset: 0.5
}
}
layer {
name: "conv13_mbox_loc"
type: "Convolution"
bottom: "conv13"
top: "conv13_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
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv13_mbox_loc_perm"
type: "Permute"
bottom: "conv13_mbox_loc"
top: "conv13_mbox_loc_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv13_mbox_loc_flat"
type: "Flatten"
bottom: "conv13_mbox_loc_perm"
top: "conv13_mbox_loc_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv13_mbox_conf"
type: "Convolution"
bottom: "conv13"
top: "conv13_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
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv13_mbox_conf_perm"
type: "Permute"
bottom: "conv13_mbox_conf"
top: "conv13_mbox_conf_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv13_mbox_conf_flat"
type: "Flatten"
bottom: "conv13_mbox_conf_perm"
top: "conv13_mbox_conf_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv13_mbox_priorbox"
type: "PriorBox"
bottom: "conv13"
bottom: "data"
top: "conv13_mbox_priorbox"
prior_box_param {
min_size: 105.0
max_size: 150.0
aspect_ratio: 2.0
aspect_ratio: 3.0
flip: true
clip: false
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
offset: 0.5
}
}
layer {
name: "conv14_2_mbox_loc"
type: "Convolution"
bottom: "conv14_2"
top: "conv14_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
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv14_2_mbox_loc_perm"
type: "Permute"
bottom: "conv14_2_mbox_loc"
top: "conv14_2_mbox_loc_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv14_2_mbox_loc_flat"
type: "Flatten"
bottom: "conv14_2_mbox_loc_perm"
top: "conv14_2_mbox_loc_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv14_2_mbox_conf"
type: "Convolution"
bottom: "conv14_2"
top: "conv14_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
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv14_2_mbox_conf_perm"
type: "Permute"
bottom: "conv14_2_mbox_conf"
top: "conv14_2_mbox_conf_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv14_2_mbox_conf_flat"
type: "Flatten"
bottom: "conv14_2_mbox_conf_perm"
top: "conv14_2_mbox_conf_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv14_2_mbox_priorbox"
type: "PriorBox"
bottom: "conv14_2"
bottom: "data"
top: "conv14_2_mbox_priorbox"
prior_box_param {
min_size: 150.0
max_size: 195.0
aspect_ratio: 2.0
aspect_ratio: 3.0
flip: true
clip: false
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
offset: 0.5
}
}
layer {
name: "conv15_2_mbox_loc"
type: "Convolution"
bottom: "conv15_2"
top: "conv15_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
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv15_2_mbox_loc_perm"
type: "Permute"
bottom: "conv15_2_mbox_loc"
top: "conv15_2_mbox_loc_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv15_2_mbox_loc_flat"
type: "Flatten"
bottom: "conv15_2_mbox_loc_perm"
top: "conv15_2_mbox_loc_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv15_2_mbox_conf"
type: "Convolution"
bottom: "conv15_2"
top: "conv15_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
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv15_2_mbox_conf_perm"
type: "Permute"
bottom: "conv15_2_mbox_conf"
top: "conv15_2_mbox_conf_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv15_2_mbox_conf_flat"
type: "Flatten"
bottom: "conv15_2_mbox_conf_perm"
top: "conv15_2_mbox_conf_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv15_2_mbox_priorbox"
type: "PriorBox"
bottom: "conv15_2"
bottom: "data"
top: "conv15_2_mbox_priorbox"
prior_box_param {
min_size: 195.0
max_size: 240.0
aspect_ratio: 2.0
aspect_ratio: 3.0
flip: true
clip: false
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
offset: 0.5
}
}
layer {
name: "conv16_2_mbox_loc"
type: "Convolution"
bottom: "conv16_2"
top: "conv16_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
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv16_2_mbox_loc_perm"
type: "Permute"
bottom: "conv16_2_mbox_loc"
top: "conv16_2_mbox_loc_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv16_2_mbox_loc_flat"
type: "Flatten"
bottom: "conv16_2_mbox_loc_perm"
top: "conv16_2_mbox_loc_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv16_2_mbox_conf"
type: "Convolution"
bottom: "conv16_2"
top: "conv16_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
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv16_2_mbox_conf_perm"
type: "Permute"
bottom: "conv16_2_mbox_conf"
top: "conv16_2_mbox_conf_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv16_2_mbox_conf_flat"
type: "Flatten"
bottom: "conv16_2_mbox_conf_perm"
top: "conv16_2_mbox_conf_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv16_2_mbox_priorbox"
type: "PriorBox"
bottom: "conv16_2"
bottom: "data"
top: "conv16_2_mbox_priorbox"
prior_box_param {
min_size: 240.0
max_size: 285.0
aspect_ratio: 2.0
aspect_ratio: 3.0
flip: true
clip: false
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
offset: 0.5
}
}
layer {
name: "conv17_2_mbox_loc"
type: "Convolution"
bottom: "conv17_2"
top: "conv17_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
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv17_2_mbox_loc_perm"
type: "Permute"
bottom: "conv17_2_mbox_loc"
top: "conv17_2_mbox_loc_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv17_2_mbox_loc_flat"
type: "Flatten"
bottom: "conv17_2_mbox_loc_perm"
top: "conv17_2_mbox_loc_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv17_2_mbox_conf"
type: "Convolution"
bottom: "conv17_2"
top: "conv17_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
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv17_2_mbox_conf_perm"
type: "Permute"
bottom: "conv17_2_mbox_conf"
top: "conv17_2_mbox_conf_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv17_2_mbox_conf_flat"
type: "Flatten"
bottom: "conv17_2_mbox_conf_perm"
top: "conv17_2_mbox_conf_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv17_2_mbox_priorbox"
type: "PriorBox"
bottom: "conv17_2"
bottom: "data"
top: "conv17_2_mbox_priorbox"
prior_box_param {
min_size: 285.0
max_size: 300.0
aspect_ratio: 2.0
aspect_ratio: 3.0
flip: true
clip: false
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
offset: 0.5
}
}
layer {
name: "mbox_loc"
type: "Concat"
bottom: "conv11_mbox_loc_flat"
bottom: "conv13_mbox_loc_flat"
bottom: "conv14_2_mbox_loc_flat"
bottom: "conv15_2_mbox_loc_flat"
bottom: "conv16_2_mbox_loc_flat"
bottom: "conv17_2_mbox_loc_flat"
top: "mbox_loc"
concat_param {
axis: 1
}
}
layer {
name: "mbox_conf"
type: "Concat"
bottom: "conv11_mbox_conf_flat"
bottom: "conv13_mbox_conf_flat"
bottom: "conv14_2_mbox_conf_flat"
bottom: "conv15_2_mbox_conf_flat"
bottom: "conv16_2_mbox_conf_flat"
bottom: "conv17_2_mbox_conf_flat"
top: "mbox_conf"
concat_param {
axis: 1
}
}
layer {
name: "mbox_priorbox"
type: "Concat"
bottom: "conv11_mbox_priorbox"
bottom: "conv13_mbox_priorbox"
bottom: "conv14_2_mbox_priorbox"
bottom: "conv15_2_mbox_priorbox"
bottom: "conv16_2_mbox_priorbox"
bottom: "conv17_2_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: 100
}
code_type: CENTER_SIZE
keep_top_k: 100
confidence_threshold: 0.25
}
}
\ No newline at end of file
samples/dnn/mobilenet_ssd_python.py 0 → 100644
View file @ 2959e7ab
import numpy as np
import argparse
try:
import cv2 as cv
except ImportError:
raise ImportError('Can\'t find OpenCV Python module. If you\'ve built it from sources without installation, '
'configure environemnt variable PYTHONPATH to "opencv_build_dir/lib" directory (with "python3" subdirectory if required)')
inWidth = 300
inHeight = 300
WHRatio = inWidth / float(inHeight)
inScaleFactor = 0.007843
meanVal = 127.5
classNames = ('background',
'aeroplane', 'bicycle', 'bird', 'boat',
'bottle', 'bus', 'car', 'cat', 'chair',
'cow', 'diningtable', 'dog', 'horse',
'motorbike', 'person', 'pottedplant',
'sheep', 'sofa', 'train', 'tvmonitor')
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--video", help="path to video file. If empty, camera's stream will be used")
parser.add_argument("--prototxt", default="MobileNetSSD_300x300.prototxt",
help="path to caffe prototxt")
parser.add_argument("-c", "--caffemodel", help="path to caffemodel file, download it here: "
"https://github.com/chuanqi305/MobileNet-SSD/blob/master/MobileNetSSD_train.caffemodel")
parser.add_argument("--thr", default=0.2, help="confidence threshold to filter out weak detections")
args = parser.parse_args()
net = dnn.readNetFromCaffe(args.prototxt, args.caffemodel)
if len(args.video):
cap = cv2.VideoCapture(args.video)
else:
cap = cv2.VideoCapture(0)
while True:
# Capture frame-by-frame
ret, frame = cap.read()
blob = dnn.blobFromImage(frame, inScaleFactor, (inWidth, inHeight), meanVal)
net.setInput(blob)
detections = net.forward()
cols = frame.shape[1]
rows = frame.shape[0]
if cols / float(rows) > WHRatio:
cropSize = (int(rows * WHRatio), rows)
else:
cropSize = (cols, int(cols / WHRatio))
y1 = (rows - cropSize[1]) / 2
y2 = y1 + cropSize[1]
x1 = (cols - cropSize[0]) / 2
x2 = x1 + cropSize[0]
frame = frame[y1:y2, x1:x2]
cols = frame.shape[1]
rows = frame.shape[0]
for i in range(detections.shape[2]):
confidence = detections[0, 0, i, 2]
if confidence > args.thr:
class_id = int(detections[0, 0, i, 1])
xLeftBottom = int(detections[0, 0, i, 3] * cols)
yLeftBottom = int(detections[0, 0, i, 4] * rows)
xRightTop = int(detections[0, 0, i, 5] * cols)
yRightTop = int(detections[0, 0, i, 6] * rows)
cv2.rectangle(frame, (xLeftBottom, yLeftBottom), (xRightTop, yRightTop),
(0, 255, 0))
label = classNames[class_id] + ": " + str(confidence)
labelSize, baseLine = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1)
cv2.rectangle(frame, (xLeftBottom, yLeftBottom - labelSize[1]),
(xLeftBottom + labelSize[0], yLeftBottom + baseLine),
(255, 255, 255), cv2.FILLED)
cv2.putText(frame, label, (xLeftBottom, yLeftBottom),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))
cv2.imshow("detections", frame)
if cv2.waitKey(1) >= 0:
break
samples/dnn/ssd_mobilenet_object_detection.cpp 0 → 100644
View file @ 2959e7ab
#include <opencv2/dnn.hpp>
#include <opencv2/dnn/shape_utils.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
using namespace cv;
using namespace cv::dnn;
#include <fstream>
#include <iostream>
#include <cstdlib>
using namespace std;
const size_t inWidth = 300;
const size_t inHeight = 300;
const float WHRatio = inWidth / (float)inHeight;
const float inScaleFactor = 0.007843f;
const float meanVal = 127.5;
const char* classNames[] = {"background",
"aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair",
"cow", "diningtable", "dog", "horse",
"motorbike", "person", "pottedplant",
"sheep", "sofa", "train", "tvmonitor"};
const char* about = "This sample uses Single-Shot Detector "
"(https://arxiv.org/abs/1512.02325)"
"to detect objects on image.\n"
".caffemodel model's file is avaliable here: "
"https://github.com/chuanqi305/MobileNet-SSD/blob/master/MobileNetSSD_train.caffemodel\n";
const char* params
= "{ help | false | print usage }"
"{ proto | MobileNetSSD_300x300.prototxt | model configuration }"
"{ model | | model weights }"
"{ video | | video for detection }"
"{ out | | path to output video file}"
"{ min_confidence | 0.2 | min confidence }";
int main(int argc, char** argv)
{
cv::CommandLineParser parser(argc, argv, params);
if (parser.get<bool>("help"))
{
cout << about << endl;
parser.printMessage();
return 0;
}
String modelConfiguration = parser.get<string>("proto");
String modelBinary = parser.get<string>("model");
//! [Initialize network]
dnn::Net net = readNetFromCaffe(modelConfiguration, modelBinary);
//! [Initialize network]
VideoCapture cap(parser.get<String>("video"));
if(!cap.isOpened()) // check if we succeeded
{
cap = VideoCapture(0);
if(!cap.isOpened())
{
cout << "Couldn't find camera" << endl;
return -1;
}
}
Size inVideoSize = Size((int) cap.get(CV_CAP_PROP_FRAME_WIDTH), //Acquire input size
(int) cap.get(CV_CAP_PROP_FRAME_HEIGHT));
Size cropSize;
if (inVideoSize.width / (float)inVideoSize.height > WHRatio)
{
cropSize = Size(static_cast<int>(inVideoSize.height * WHRatio),
inVideoSize.height);
}
else
{
cropSize = Size(inVideoSize.width,
static_cast<int>(inVideoSize.width / WHRatio));
}
Rect crop(Point((inVideoSize.width - cropSize.width) / 2,
(inVideoSize.height - cropSize.height) / 2),
cropSize);
VideoWriter outputVideo;
outputVideo.open(parser.get<String>("out") ,
static_cast<int>(cap.get(CV_CAP_PROP_FOURCC)),
cap.get(CV_CAP_PROP_FPS), cropSize, true);
for(;;)
{
Mat frame;
cap >> frame; // get a new frame from camera
//! [Prepare blob]
Mat inputBlob = blobFromImage(frame, inScaleFactor,
Size(inWidth, inHeight), meanVal); //Convert Mat to batch of images
//! [Prepare blob]
//! [Set input blob]
net.setInput(inputBlob, "data"); //set the network input
//! [Set input blob]
TickMeter tm;
tm.start();
//! [Make forward pass]
Mat detection = net.forward("detection_out"); //compute output
tm.stop();
cout << "Inference time, ms: " << tm.getTimeMilli() << endl;
//! [Make forward pass]
Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr<float>());
frame = frame(crop);
float confidenceThreshold = parser.get<float>("min_confidence");
for(int i = 0; i < detectionMat.rows; i++)
{
float confidence = detectionMat.at<float>(i, 2);
if(confidence > confidenceThreshold)
{
size_t objectClass = (size_t)(detectionMat.at<float>(i, 1));
int xLeftBottom = static_cast<int>(detectionMat.at<float>(i, 3) * frame.cols);
int yLeftBottom = static_cast<int>(detectionMat.at<float>(i, 4) * frame.rows);
int xRightTop = static_cast<int>(detectionMat.at<float>(i, 5) * frame.cols);
int yRightTop = static_cast<int>(detectionMat.at<float>(i, 6) * frame.rows);
ostringstream ss;
ss << confidence;
String conf(ss.str());
Rect object((int)xLeftBottom, (int)yLeftBottom,
(int)(xRightTop - xLeftBottom),
(int)(yRightTop - yLeftBottom));
rectangle(frame, object, Scalar(0, 255, 0));
String label = String(classNames[objectClass]) + ": " + conf;
int baseLine = 0;
Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
rectangle(frame, Rect(Point(xLeftBottom, yLeftBottom - labelSize.height),
Size(labelSize.width, labelSize.height + baseLine)),
Scalar(255, 255, 255), CV_FILLED);
putText(frame, label, Point(xLeftBottom, yLeftBottom),
FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0,0,0));
}
}
if (outputVideo.isOpened())
outputVideo << frame;
imshow("detections", frame);
if (waitKey(1) >= 0) break;
}
return 0;
} // main
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment