From 078a6ce66deae8f19b9334bafa8842aa5b57e0ab Mon Sep 17 00:00:00 2001 From: Jasper Date: Fri, 28 May 2021 12:27:12 +0200 Subject: [PATCH] [ADD] added all the files --- .gitignore | 2 + res/pose/coco/pose_deploy_linevec.prototxt | 2976 +++++++++++++++++ ...se_deploy_linevec_faster_4_stages.prototxt | 2081 ++++++++++++ src/computervision/ObjectDetection.cpp | 6 +- src/computervision/OpenPoseImage.cpp | 149 + src/computervision/OpenPoseVideo.cpp | 144 + src/computervision/OpenPoseVideo.h | 19 + src/main.cpp | 11 +- 8 files changed, 5383 insertions(+), 5 deletions(-) create mode 100644 res/pose/coco/pose_deploy_linevec.prototxt create mode 100644 res/pose/mpi/pose_deploy_linevec_faster_4_stages.prototxt create mode 100644 src/computervision/OpenPoseImage.cpp create mode 100644 src/computervision/OpenPoseVideo.cpp create mode 100644 src/computervision/OpenPoseVideo.h diff --git a/.gitignore b/.gitignore index 9232336..488f5fe 100644 --- a/.gitignore +++ b/.gitignore @@ -428,4 +428,6 @@ FodyWeavers.xsd **/docs/* **/doc/* +**/pose_iter_160000.caffemodel + # End of https://www.toptal.com/developers/gitignore/api/c++,visualstudio,visualstudiocode,opencv diff --git a/res/pose/coco/pose_deploy_linevec.prototxt b/res/pose/coco/pose_deploy_linevec.prototxt new file mode 100644 index 0000000..90a54fd --- /dev/null +++ b/res/pose/coco/pose_deploy_linevec.prototxt @@ -0,0 +1,2976 @@ +input: "image" +input_dim: 1 +input_dim: 3 +input_dim: 1 # This value will be defined at runtime +input_dim: 1 # This value will be defined at runtime +layer { + name: "conv1_1" + type: "Convolution" + bottom: "image" + top: "conv1_1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 64 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +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 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 64 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu1_2" + type: "ReLU" + bottom: "conv1_2" + top: "conv1_2" +} +layer { + name: "pool1_stage1" + type: "Pooling" + bottom: "conv1_2" + top: "pool1_stage1" + pooling_param { + pool: MAX + kernel_size: 2 + stride: 2 + } +} +layer { + name: "conv2_1" + type: "Convolution" + bottom: "pool1_stage1" + top: "conv2_1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +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 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu2_2" + type: "ReLU" + bottom: "conv2_2" + top: "conv2_2" +} +layer { + name: "pool2_stage1" + type: "Pooling" + bottom: "conv2_2" + top: "pool2_stage1" + pooling_param { + pool: MAX + kernel_size: 2 + stride: 2 + } +} +layer { + name: "conv3_1" + type: "Convolution" + bottom: "pool2_stage1" + top: "conv3_1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +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 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +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 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu3_3" + type: "ReLU" + bottom: "conv3_3" + top: "conv3_3" +} +layer { + name: "conv3_4" + type: "Convolution" + bottom: "conv3_3" + top: "conv3_4" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu3_4" + type: "ReLU" + bottom: "conv3_4" + top: "conv3_4" +} +layer { + name: "pool3_stage1" + type: "Pooling" + bottom: "conv3_4" + top: "pool3_stage1" + pooling_param { + pool: MAX + kernel_size: 2 + stride: 2 + } +} +layer { + name: "conv4_1" + type: "Convolution" + bottom: "pool3_stage1" + top: "conv4_1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 512 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +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 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 512 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu4_2" + type: "ReLU" + bottom: "conv4_2" + top: "conv4_2" +} +layer { + name: "conv4_3_CPM" + type: "Convolution" + bottom: "conv4_2" + top: "conv4_3_CPM" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu4_3_CPM" + type: "ReLU" + bottom: "conv4_3_CPM" + top: "conv4_3_CPM" +} +layer { + name: "conv4_4_CPM" + type: "Convolution" + bottom: "conv4_3_CPM" + top: "conv4_4_CPM" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu4_4_CPM" + type: "ReLU" + bottom: "conv4_4_CPM" + top: "conv4_4_CPM" +} +layer { + name: "conv5_1_CPM_L1" + type: "Convolution" + bottom: "conv4_4_CPM" + top: "conv5_1_CPM_L1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_1_CPM_L1" + type: "ReLU" + bottom: "conv5_1_CPM_L1" + top: "conv5_1_CPM_L1" +} +layer { + name: "conv5_1_CPM_L2" + type: "Convolution" + bottom: "conv4_4_CPM" + top: "conv5_1_CPM_L2" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_1_CPM_L2" + type: "ReLU" + bottom: "conv5_1_CPM_L2" + top: "conv5_1_CPM_L2" +} +layer { + name: "conv5_2_CPM_L1" + type: "Convolution" + bottom: "conv5_1_CPM_L1" + top: "conv5_2_CPM_L1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_2_CPM_L1" + type: "ReLU" + bottom: "conv5_2_CPM_L1" + top: "conv5_2_CPM_L1" +} +layer { + name: "conv5_2_CPM_L2" + type: "Convolution" + bottom: "conv5_1_CPM_L2" + top: "conv5_2_CPM_L2" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_2_CPM_L2" + type: "ReLU" + bottom: "conv5_2_CPM_L2" + top: "conv5_2_CPM_L2" +} +layer { + name: "conv5_3_CPM_L1" + type: "Convolution" + bottom: "conv5_2_CPM_L1" + top: "conv5_3_CPM_L1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_3_CPM_L1" + type: "ReLU" + bottom: "conv5_3_CPM_L1" + top: "conv5_3_CPM_L1" +} +layer { + name: "conv5_3_CPM_L2" + type: "Convolution" + bottom: "conv5_2_CPM_L2" + top: "conv5_3_CPM_L2" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_3_CPM_L2" + type: "ReLU" + bottom: "conv5_3_CPM_L2" + top: "conv5_3_CPM_L2" +} +layer { + name: "conv5_4_CPM_L1" + type: "Convolution" + bottom: "conv5_3_CPM_L1" + top: "conv5_4_CPM_L1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 512 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_4_CPM_L1" + type: "ReLU" + bottom: "conv5_4_CPM_L1" + top: "conv5_4_CPM_L1" +} +layer { + name: "conv5_4_CPM_L2" + type: "Convolution" + bottom: "conv5_3_CPM_L2" + top: "conv5_4_CPM_L2" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 512 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_4_CPM_L2" + type: "ReLU" + bottom: "conv5_4_CPM_L2" + top: "conv5_4_CPM_L2" +} +layer { + name: "conv5_5_CPM_L1" + type: "Convolution" + bottom: "conv5_4_CPM_L1" + top: "conv5_5_CPM_L1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 38 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "conv5_5_CPM_L2" + type: "Convolution" + bottom: "conv5_4_CPM_L2" + top: "conv5_5_CPM_L2" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 19 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "concat_stage2" + type: "Concat" + bottom: "conv5_5_CPM_L1" + bottom: "conv5_5_CPM_L2" + bottom: "conv4_4_CPM" + top: "concat_stage2" + concat_param { + axis: 1 + } +} +layer { + name: "Mconv1_stage2_L1" + type: "Convolution" + bottom: "concat_stage2" + top: "Mconv1_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage2_L1" + type: "ReLU" + bottom: "Mconv1_stage2_L1" + top: "Mconv1_stage2_L1" +} +layer { + name: "Mconv1_stage2_L2" + type: "Convolution" + bottom: "concat_stage2" + top: "Mconv1_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage2_L2" + type: "ReLU" + bottom: "Mconv1_stage2_L2" + top: "Mconv1_stage2_L2" +} +layer { + name: "Mconv2_stage2_L1" + type: "Convolution" + bottom: "Mconv1_stage2_L1" + top: "Mconv2_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage2_L1" + type: "ReLU" + bottom: "Mconv2_stage2_L1" + top: "Mconv2_stage2_L1" +} +layer { + name: "Mconv2_stage2_L2" + type: "Convolution" + bottom: "Mconv1_stage2_L2" + top: "Mconv2_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage2_L2" + type: "ReLU" + bottom: "Mconv2_stage2_L2" + top: "Mconv2_stage2_L2" +} +layer { + name: "Mconv3_stage2_L1" + type: "Convolution" + bottom: "Mconv2_stage2_L1" + top: "Mconv3_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage2_L1" + type: "ReLU" + bottom: "Mconv3_stage2_L1" + top: "Mconv3_stage2_L1" +} +layer { + name: "Mconv3_stage2_L2" + type: "Convolution" + bottom: "Mconv2_stage2_L2" + top: "Mconv3_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage2_L2" + type: "ReLU" + bottom: "Mconv3_stage2_L2" + top: "Mconv3_stage2_L2" +} +layer { + name: "Mconv4_stage2_L1" + type: "Convolution" + bottom: "Mconv3_stage2_L1" + top: "Mconv4_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage2_L1" + type: "ReLU" + bottom: "Mconv4_stage2_L1" + top: "Mconv4_stage2_L1" +} +layer { + name: "Mconv4_stage2_L2" + type: "Convolution" + bottom: "Mconv3_stage2_L2" + top: "Mconv4_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage2_L2" + type: "ReLU" + bottom: "Mconv4_stage2_L2" + top: "Mconv4_stage2_L2" +} +layer { + name: "Mconv5_stage2_L1" + type: "Convolution" + bottom: "Mconv4_stage2_L1" + top: "Mconv5_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage2_L1" + type: "ReLU" + bottom: "Mconv5_stage2_L1" + top: "Mconv5_stage2_L1" +} +layer { + name: "Mconv5_stage2_L2" + type: "Convolution" + bottom: "Mconv4_stage2_L2" + top: "Mconv5_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage2_L2" + type: "ReLU" + bottom: "Mconv5_stage2_L2" + top: "Mconv5_stage2_L2" +} +layer { + name: "Mconv6_stage2_L1" + type: "Convolution" + bottom: "Mconv5_stage2_L1" + top: "Mconv6_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage2_L1" + type: "ReLU" + bottom: "Mconv6_stage2_L1" + top: "Mconv6_stage2_L1" +} +layer { + name: "Mconv6_stage2_L2" + type: "Convolution" + bottom: "Mconv5_stage2_L2" + top: "Mconv6_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage2_L2" + type: "ReLU" + bottom: "Mconv6_stage2_L2" + top: "Mconv6_stage2_L2" +} +layer { + name: "Mconv7_stage2_L1" + type: "Convolution" + bottom: "Mconv6_stage2_L1" + top: "Mconv7_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 38 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mconv7_stage2_L2" + type: "Convolution" + bottom: "Mconv6_stage2_L2" + top: "Mconv7_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 19 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "concat_stage3" + type: "Concat" + bottom: "Mconv7_stage2_L1" + bottom: "Mconv7_stage2_L2" + bottom: "conv4_4_CPM" + top: "concat_stage3" + concat_param { + axis: 1 + } +} +layer { + name: "Mconv1_stage3_L1" + type: "Convolution" + bottom: "concat_stage3" + top: "Mconv1_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage3_L1" + type: "ReLU" + bottom: "Mconv1_stage3_L1" + top: "Mconv1_stage3_L1" +} +layer { + name: "Mconv1_stage3_L2" + type: "Convolution" + bottom: "concat_stage3" + top: "Mconv1_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage3_L2" + type: "ReLU" + bottom: "Mconv1_stage3_L2" + top: "Mconv1_stage3_L2" +} +layer { + name: "Mconv2_stage3_L1" + type: "Convolution" + bottom: "Mconv1_stage3_L1" + top: "Mconv2_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage3_L1" + type: "ReLU" + bottom: "Mconv2_stage3_L1" + top: "Mconv2_stage3_L1" +} +layer { + name: "Mconv2_stage3_L2" + type: "Convolution" + bottom: "Mconv1_stage3_L2" + top: "Mconv2_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage3_L2" + type: "ReLU" + bottom: "Mconv2_stage3_L2" + top: "Mconv2_stage3_L2" +} +layer { + name: "Mconv3_stage3_L1" + type: "Convolution" + bottom: "Mconv2_stage3_L1" + top: "Mconv3_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage3_L1" + type: "ReLU" + bottom: "Mconv3_stage3_L1" + top: "Mconv3_stage3_L1" +} +layer { + name: "Mconv3_stage3_L2" + type: "Convolution" + bottom: "Mconv2_stage3_L2" + top: "Mconv3_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage3_L2" + type: "ReLU" + bottom: "Mconv3_stage3_L2" + top: "Mconv3_stage3_L2" +} +layer { + name: "Mconv4_stage3_L1" + type: "Convolution" + bottom: "Mconv3_stage3_L1" + top: "Mconv4_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage3_L1" + type: "ReLU" + bottom: "Mconv4_stage3_L1" + top: "Mconv4_stage3_L1" +} +layer { + name: "Mconv4_stage3_L2" + type: "Convolution" + bottom: "Mconv3_stage3_L2" + top: "Mconv4_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage3_L2" + type: "ReLU" + bottom: "Mconv4_stage3_L2" + top: "Mconv4_stage3_L2" +} +layer { + name: "Mconv5_stage3_L1" + type: "Convolution" + bottom: "Mconv4_stage3_L1" + top: "Mconv5_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage3_L1" + type: "ReLU" + bottom: "Mconv5_stage3_L1" + top: "Mconv5_stage3_L1" +} +layer { + name: "Mconv5_stage3_L2" + type: "Convolution" + bottom: "Mconv4_stage3_L2" + top: "Mconv5_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage3_L2" + type: "ReLU" + bottom: "Mconv5_stage3_L2" + top: "Mconv5_stage3_L2" +} +layer { + name: "Mconv6_stage3_L1" + type: "Convolution" + bottom: "Mconv5_stage3_L1" + top: "Mconv6_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage3_L1" + type: "ReLU" + bottom: "Mconv6_stage3_L1" + top: "Mconv6_stage3_L1" +} +layer { + name: "Mconv6_stage3_L2" + type: "Convolution" + bottom: "Mconv5_stage3_L2" + top: "Mconv6_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage3_L2" + type: "ReLU" + bottom: "Mconv6_stage3_L2" + top: "Mconv6_stage3_L2" +} +layer { + name: "Mconv7_stage3_L1" + type: "Convolution" + bottom: "Mconv6_stage3_L1" + top: "Mconv7_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 38 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mconv7_stage3_L2" + type: "Convolution" + bottom: "Mconv6_stage3_L2" + top: "Mconv7_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 19 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "concat_stage4" + type: "Concat" + bottom: "Mconv7_stage3_L1" + bottom: "Mconv7_stage3_L2" + bottom: "conv4_4_CPM" + top: "concat_stage4" + concat_param { + axis: 1 + } +} +layer { + name: "Mconv1_stage4_L1" + type: "Convolution" + bottom: "concat_stage4" + top: "Mconv1_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage4_L1" + type: "ReLU" + bottom: "Mconv1_stage4_L1" + top: "Mconv1_stage4_L1" +} +layer { + name: "Mconv1_stage4_L2" + type: "Convolution" + bottom: "concat_stage4" + top: "Mconv1_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage4_L2" + type: "ReLU" + bottom: "Mconv1_stage4_L2" + top: "Mconv1_stage4_L2" +} +layer { + name: "Mconv2_stage4_L1" + type: "Convolution" + bottom: "Mconv1_stage4_L1" + top: "Mconv2_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage4_L1" + type: "ReLU" + bottom: "Mconv2_stage4_L1" + top: "Mconv2_stage4_L1" +} +layer { + name: "Mconv2_stage4_L2" + type: "Convolution" + bottom: "Mconv1_stage4_L2" + top: "Mconv2_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage4_L2" + type: "ReLU" + bottom: "Mconv2_stage4_L2" + top: "Mconv2_stage4_L2" +} +layer { + name: "Mconv3_stage4_L1" + type: "Convolution" + bottom: "Mconv2_stage4_L1" + top: "Mconv3_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage4_L1" + type: "ReLU" + bottom: "Mconv3_stage4_L1" + top: "Mconv3_stage4_L1" +} +layer { + name: "Mconv3_stage4_L2" + type: "Convolution" + bottom: "Mconv2_stage4_L2" + top: "Mconv3_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage4_L2" + type: "ReLU" + bottom: "Mconv3_stage4_L2" + top: "Mconv3_stage4_L2" +} +layer { + name: "Mconv4_stage4_L1" + type: "Convolution" + bottom: "Mconv3_stage4_L1" + top: "Mconv4_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage4_L1" + type: "ReLU" + bottom: "Mconv4_stage4_L1" + top: "Mconv4_stage4_L1" +} +layer { + name: "Mconv4_stage4_L2" + type: "Convolution" + bottom: "Mconv3_stage4_L2" + top: "Mconv4_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage4_L2" + type: "ReLU" + bottom: "Mconv4_stage4_L2" + top: "Mconv4_stage4_L2" +} +layer { + name: "Mconv5_stage4_L1" + type: "Convolution" + bottom: "Mconv4_stage4_L1" + top: "Mconv5_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage4_L1" + type: "ReLU" + bottom: "Mconv5_stage4_L1" + top: "Mconv5_stage4_L1" +} +layer { + name: "Mconv5_stage4_L2" + type: "Convolution" + bottom: "Mconv4_stage4_L2" + top: "Mconv5_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage4_L2" + type: "ReLU" + bottom: "Mconv5_stage4_L2" + top: "Mconv5_stage4_L2" +} +layer { + name: "Mconv6_stage4_L1" + type: "Convolution" + bottom: "Mconv5_stage4_L1" + top: "Mconv6_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage4_L1" + type: "ReLU" + bottom: "Mconv6_stage4_L1" + top: "Mconv6_stage4_L1" +} +layer { + name: "Mconv6_stage4_L2" + type: "Convolution" + bottom: "Mconv5_stage4_L2" + top: "Mconv6_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage4_L2" + type: "ReLU" + bottom: "Mconv6_stage4_L2" + top: "Mconv6_stage4_L2" +} +layer { + name: "Mconv7_stage4_L1" + type: "Convolution" + bottom: "Mconv6_stage4_L1" + top: "Mconv7_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 38 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mconv7_stage4_L2" + type: "Convolution" + bottom: "Mconv6_stage4_L2" + top: "Mconv7_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 19 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "concat_stage5" + type: "Concat" + bottom: "Mconv7_stage4_L1" + bottom: "Mconv7_stage4_L2" + bottom: "conv4_4_CPM" + top: "concat_stage5" + concat_param { + axis: 1 + } +} +layer { + name: "Mconv1_stage5_L1" + type: "Convolution" + bottom: "concat_stage5" + top: "Mconv1_stage5_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage5_L1" + type: "ReLU" + bottom: "Mconv1_stage5_L1" + top: "Mconv1_stage5_L1" +} +layer { + name: "Mconv1_stage5_L2" + type: "Convolution" + bottom: "concat_stage5" + top: "Mconv1_stage5_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage5_L2" + type: "ReLU" + bottom: "Mconv1_stage5_L2" + top: "Mconv1_stage5_L2" +} +layer { + name: "Mconv2_stage5_L1" + type: "Convolution" + bottom: "Mconv1_stage5_L1" + top: "Mconv2_stage5_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage5_L1" + type: "ReLU" + bottom: "Mconv2_stage5_L1" + top: "Mconv2_stage5_L1" +} +layer { + name: "Mconv2_stage5_L2" + type: "Convolution" + bottom: "Mconv1_stage5_L2" + top: "Mconv2_stage5_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage5_L2" + type: "ReLU" + bottom: "Mconv2_stage5_L2" + top: "Mconv2_stage5_L2" +} +layer { + name: "Mconv3_stage5_L1" + type: "Convolution" + bottom: "Mconv2_stage5_L1" + top: "Mconv3_stage5_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage5_L1" + type: "ReLU" + bottom: "Mconv3_stage5_L1" + top: "Mconv3_stage5_L1" +} +layer { + name: "Mconv3_stage5_L2" + type: "Convolution" + bottom: "Mconv2_stage5_L2" + top: "Mconv3_stage5_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage5_L2" + type: "ReLU" + bottom: "Mconv3_stage5_L2" + top: "Mconv3_stage5_L2" +} +layer { + name: "Mconv4_stage5_L1" + type: "Convolution" + bottom: "Mconv3_stage5_L1" + top: "Mconv4_stage5_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage5_L1" + type: "ReLU" + bottom: "Mconv4_stage5_L1" + top: "Mconv4_stage5_L1" +} +layer { + name: "Mconv4_stage5_L2" + type: "Convolution" + bottom: "Mconv3_stage5_L2" + top: "Mconv4_stage5_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage5_L2" + type: "ReLU" + bottom: "Mconv4_stage5_L2" + top: "Mconv4_stage5_L2" +} +layer { + name: "Mconv5_stage5_L1" + type: "Convolution" + bottom: "Mconv4_stage5_L1" + top: "Mconv5_stage5_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage5_L1" + type: "ReLU" + bottom: "Mconv5_stage5_L1" + top: "Mconv5_stage5_L1" +} +layer { + name: "Mconv5_stage5_L2" + type: "Convolution" + bottom: "Mconv4_stage5_L2" + top: "Mconv5_stage5_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage5_L2" + type: "ReLU" + bottom: "Mconv5_stage5_L2" + top: "Mconv5_stage5_L2" +} +layer { + name: "Mconv6_stage5_L1" + type: "Convolution" + bottom: "Mconv5_stage5_L1" + top: "Mconv6_stage5_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage5_L1" + type: "ReLU" + bottom: "Mconv6_stage5_L1" + top: "Mconv6_stage5_L1" +} +layer { + name: "Mconv6_stage5_L2" + type: "Convolution" + bottom: "Mconv5_stage5_L2" + top: "Mconv6_stage5_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage5_L2" + type: "ReLU" + bottom: "Mconv6_stage5_L2" + top: "Mconv6_stage5_L2" +} +layer { + name: "Mconv7_stage5_L1" + type: "Convolution" + bottom: "Mconv6_stage5_L1" + top: "Mconv7_stage5_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 38 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mconv7_stage5_L2" + type: "Convolution" + bottom: "Mconv6_stage5_L2" + top: "Mconv7_stage5_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 19 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "concat_stage6" + type: "Concat" + bottom: "Mconv7_stage5_L1" + bottom: "Mconv7_stage5_L2" + bottom: "conv4_4_CPM" + top: "concat_stage6" + concat_param { + axis: 1 + } +} +layer { + name: "Mconv1_stage6_L1" + type: "Convolution" + bottom: "concat_stage6" + top: "Mconv1_stage6_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage6_L1" + type: "ReLU" + bottom: "Mconv1_stage6_L1" + top: "Mconv1_stage6_L1" +} +layer { + name: "Mconv1_stage6_L2" + type: "Convolution" + bottom: "concat_stage6" + top: "Mconv1_stage6_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage6_L2" + type: "ReLU" + bottom: "Mconv1_stage6_L2" + top: "Mconv1_stage6_L2" +} +layer { + name: "Mconv2_stage6_L1" + type: "Convolution" + bottom: "Mconv1_stage6_L1" + top: "Mconv2_stage6_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage6_L1" + type: "ReLU" + bottom: "Mconv2_stage6_L1" + top: "Mconv2_stage6_L1" +} +layer { + name: "Mconv2_stage6_L2" + type: "Convolution" + bottom: "Mconv1_stage6_L2" + top: "Mconv2_stage6_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage6_L2" + type: "ReLU" + bottom: "Mconv2_stage6_L2" + top: "Mconv2_stage6_L2" +} +layer { + name: "Mconv3_stage6_L1" + type: "Convolution" + bottom: "Mconv2_stage6_L1" + top: "Mconv3_stage6_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage6_L1" + type: "ReLU" + bottom: "Mconv3_stage6_L1" + top: "Mconv3_stage6_L1" +} +layer { + name: "Mconv3_stage6_L2" + type: "Convolution" + bottom: "Mconv2_stage6_L2" + top: "Mconv3_stage6_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage6_L2" + type: "ReLU" + bottom: "Mconv3_stage6_L2" + top: "Mconv3_stage6_L2" +} +layer { + name: "Mconv4_stage6_L1" + type: "Convolution" + bottom: "Mconv3_stage6_L1" + top: "Mconv4_stage6_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage6_L1" + type: "ReLU" + bottom: "Mconv4_stage6_L1" + top: "Mconv4_stage6_L1" +} +layer { + name: "Mconv4_stage6_L2" + type: "Convolution" + bottom: "Mconv3_stage6_L2" + top: "Mconv4_stage6_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage6_L2" + type: "ReLU" + bottom: "Mconv4_stage6_L2" + top: "Mconv4_stage6_L2" +} +layer { + name: "Mconv5_stage6_L1" + type: "Convolution" + bottom: "Mconv4_stage6_L1" + top: "Mconv5_stage6_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage6_L1" + type: "ReLU" + bottom: "Mconv5_stage6_L1" + top: "Mconv5_stage6_L1" +} +layer { + name: "Mconv5_stage6_L2" + type: "Convolution" + bottom: "Mconv4_stage6_L2" + top: "Mconv5_stage6_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage6_L2" + type: "ReLU" + bottom: "Mconv5_stage6_L2" + top: "Mconv5_stage6_L2" +} +layer { + name: "Mconv6_stage6_L1" + type: "Convolution" + bottom: "Mconv5_stage6_L1" + top: "Mconv6_stage6_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage6_L1" + type: "ReLU" + bottom: "Mconv6_stage6_L1" + top: "Mconv6_stage6_L1" +} +layer { + name: "Mconv6_stage6_L2" + type: "Convolution" + bottom: "Mconv5_stage6_L2" + top: "Mconv6_stage6_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage6_L2" + type: "ReLU" + bottom: "Mconv6_stage6_L2" + top: "Mconv6_stage6_L2" +} +layer { + name: "Mconv7_stage6_L1" + type: "Convolution" + bottom: "Mconv6_stage6_L1" + top: "Mconv7_stage6_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 38 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mconv7_stage6_L2" + type: "Convolution" + bottom: "Mconv6_stage6_L2" + top: "Mconv7_stage6_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 19 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "concat_stage7" + type: "Concat" + bottom: "Mconv7_stage6_L2" + bottom: "Mconv7_stage6_L1" + # top: "concat_stage7" + top: "net_output" + concat_param { + axis: 1 + } +} \ No newline at end of file diff --git a/res/pose/mpi/pose_deploy_linevec_faster_4_stages.prototxt b/res/pose/mpi/pose_deploy_linevec_faster_4_stages.prototxt new file mode 100644 index 0000000..02ec183 --- /dev/null +++ b/res/pose/mpi/pose_deploy_linevec_faster_4_stages.prototxt @@ -0,0 +1,2081 @@ +input: "image" +input_dim: 1 +input_dim: 3 +input_dim: 1 # This value will be defined at runtime +input_dim: 1 # This value will be defined at runtime +layer { + name: "conv1_1" + type: "Convolution" + bottom: "image" + top: "conv1_1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 64 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +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 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 64 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu1_2" + type: "ReLU" + bottom: "conv1_2" + top: "conv1_2" +} +layer { + name: "pool1_stage1" + type: "Pooling" + bottom: "conv1_2" + top: "pool1_stage1" + pooling_param { + pool: MAX + kernel_size: 2 + stride: 2 + } +} +layer { + name: "conv2_1" + type: "Convolution" + bottom: "pool1_stage1" + top: "conv2_1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +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 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu2_2" + type: "ReLU" + bottom: "conv2_2" + top: "conv2_2" +} +layer { + name: "pool2_stage1" + type: "Pooling" + bottom: "conv2_2" + top: "pool2_stage1" + pooling_param { + pool: MAX + kernel_size: 2 + stride: 2 + } +} +layer { + name: "conv3_1" + type: "Convolution" + bottom: "pool2_stage1" + top: "conv3_1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +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 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +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 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu3_3" + type: "ReLU" + bottom: "conv3_3" + top: "conv3_3" +} +layer { + name: "conv3_4" + type: "Convolution" + bottom: "conv3_3" + top: "conv3_4" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu3_4" + type: "ReLU" + bottom: "conv3_4" + top: "conv3_4" +} +layer { + name: "pool3_stage1" + type: "Pooling" + bottom: "conv3_4" + top: "pool3_stage1" + pooling_param { + pool: MAX + kernel_size: 2 + stride: 2 + } +} +layer { + name: "conv4_1" + type: "Convolution" + bottom: "pool3_stage1" + top: "conv4_1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 512 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +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 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 512 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu4_2" + type: "ReLU" + bottom: "conv4_2" + top: "conv4_2" +} +layer { + name: "conv4_3_CPM" + type: "Convolution" + bottom: "conv4_2" + top: "conv4_3_CPM" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 256 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu4_3_CPM" + type: "ReLU" + bottom: "conv4_3_CPM" + top: "conv4_3_CPM" +} +layer { + name: "conv4_4_CPM" + type: "Convolution" + bottom: "conv4_3_CPM" + top: "conv4_4_CPM" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu4_4_CPM" + type: "ReLU" + bottom: "conv4_4_CPM" + top: "conv4_4_CPM" +} +layer { + name: "conv5_1_CPM_L1" + type: "Convolution" + bottom: "conv4_4_CPM" + top: "conv5_1_CPM_L1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_1_CPM_L1" + type: "ReLU" + bottom: "conv5_1_CPM_L1" + top: "conv5_1_CPM_L1" +} +layer { + name: "conv5_1_CPM_L2" + type: "Convolution" + bottom: "conv4_4_CPM" + top: "conv5_1_CPM_L2" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_1_CPM_L2" + type: "ReLU" + bottom: "conv5_1_CPM_L2" + top: "conv5_1_CPM_L2" +} +layer { + name: "conv5_2_CPM_L1" + type: "Convolution" + bottom: "conv5_1_CPM_L1" + top: "conv5_2_CPM_L1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_2_CPM_L1" + type: "ReLU" + bottom: "conv5_2_CPM_L1" + top: "conv5_2_CPM_L1" +} +layer { + name: "conv5_2_CPM_L2" + type: "Convolution" + bottom: "conv5_1_CPM_L2" + top: "conv5_2_CPM_L2" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_2_CPM_L2" + type: "ReLU" + bottom: "conv5_2_CPM_L2" + top: "conv5_2_CPM_L2" +} +layer { + name: "conv5_3_CPM_L1" + type: "Convolution" + bottom: "conv5_2_CPM_L1" + top: "conv5_3_CPM_L1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_3_CPM_L1" + type: "ReLU" + bottom: "conv5_3_CPM_L1" + top: "conv5_3_CPM_L1" +} +layer { + name: "conv5_3_CPM_L2" + type: "Convolution" + bottom: "conv5_2_CPM_L2" + top: "conv5_3_CPM_L2" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 1 + kernel_size: 3 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_3_CPM_L2" + type: "ReLU" + bottom: "conv5_3_CPM_L2" + top: "conv5_3_CPM_L2" +} +layer { + name: "conv5_4_CPM_L1" + type: "Convolution" + bottom: "conv5_3_CPM_L1" + top: "conv5_4_CPM_L1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 512 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_4_CPM_L1" + type: "ReLU" + bottom: "conv5_4_CPM_L1" + top: "conv5_4_CPM_L1" +} +layer { + name: "conv5_4_CPM_L2" + type: "Convolution" + bottom: "conv5_3_CPM_L2" + top: "conv5_4_CPM_L2" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 512 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "relu5_4_CPM_L2" + type: "ReLU" + bottom: "conv5_4_CPM_L2" + top: "conv5_4_CPM_L2" +} +layer { + name: "conv5_5_CPM_L1" + type: "Convolution" + bottom: "conv5_4_CPM_L1" + top: "conv5_5_CPM_L1" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 28 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "conv5_5_CPM_L2" + type: "Convolution" + bottom: "conv5_4_CPM_L2" + top: "conv5_5_CPM_L2" + param { + lr_mult: 1.0 + decay_mult: 1 + } + param { + lr_mult: 2.0 + decay_mult: 0 + } + convolution_param { + num_output: 16 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "concat_stage2" + type: "Concat" + bottom: "conv5_5_CPM_L1" + bottom: "conv5_5_CPM_L2" + bottom: "conv4_4_CPM" + top: "concat_stage2" + concat_param { + axis: 1 + } +} +layer { + name: "Mconv1_stage2_L1" + type: "Convolution" + bottom: "concat_stage2" + top: "Mconv1_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage2_L1" + type: "ReLU" + bottom: "Mconv1_stage2_L1" + top: "Mconv1_stage2_L1" +} +layer { + name: "Mconv1_stage2_L2" + type: "Convolution" + bottom: "concat_stage2" + top: "Mconv1_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage2_L2" + type: "ReLU" + bottom: "Mconv1_stage2_L2" + top: "Mconv1_stage2_L2" +} +layer { + name: "Mconv2_stage2_L1" + type: "Convolution" + bottom: "Mconv1_stage2_L1" + top: "Mconv2_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage2_L1" + type: "ReLU" + bottom: "Mconv2_stage2_L1" + top: "Mconv2_stage2_L1" +} +layer { + name: "Mconv2_stage2_L2" + type: "Convolution" + bottom: "Mconv1_stage2_L2" + top: "Mconv2_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage2_L2" + type: "ReLU" + bottom: "Mconv2_stage2_L2" + top: "Mconv2_stage2_L2" +} +layer { + name: "Mconv3_stage2_L1" + type: "Convolution" + bottom: "Mconv2_stage2_L1" + top: "Mconv3_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage2_L1" + type: "ReLU" + bottom: "Mconv3_stage2_L1" + top: "Mconv3_stage2_L1" +} +layer { + name: "Mconv3_stage2_L2" + type: "Convolution" + bottom: "Mconv2_stage2_L2" + top: "Mconv3_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage2_L2" + type: "ReLU" + bottom: "Mconv3_stage2_L2" + top: "Mconv3_stage2_L2" +} +layer { + name: "Mconv4_stage2_L1" + type: "Convolution" + bottom: "Mconv3_stage2_L1" + top: "Mconv4_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage2_L1" + type: "ReLU" + bottom: "Mconv4_stage2_L1" + top: "Mconv4_stage2_L1" +} +layer { + name: "Mconv4_stage2_L2" + type: "Convolution" + bottom: "Mconv3_stage2_L2" + top: "Mconv4_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage2_L2" + type: "ReLU" + bottom: "Mconv4_stage2_L2" + top: "Mconv4_stage2_L2" +} +layer { + name: "Mconv5_stage2_L1" + type: "Convolution" + bottom: "Mconv4_stage2_L1" + top: "Mconv5_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage2_L1" + type: "ReLU" + bottom: "Mconv5_stage2_L1" + top: "Mconv5_stage2_L1" +} +layer { + name: "Mconv5_stage2_L2" + type: "Convolution" + bottom: "Mconv4_stage2_L2" + top: "Mconv5_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage2_L2" + type: "ReLU" + bottom: "Mconv5_stage2_L2" + top: "Mconv5_stage2_L2" +} +layer { + name: "Mconv6_stage2_L1" + type: "Convolution" + bottom: "Mconv5_stage2_L1" + top: "Mconv6_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage2_L1" + type: "ReLU" + bottom: "Mconv6_stage2_L1" + top: "Mconv6_stage2_L1" +} +layer { + name: "Mconv6_stage2_L2" + type: "Convolution" + bottom: "Mconv5_stage2_L2" + top: "Mconv6_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage2_L2" + type: "ReLU" + bottom: "Mconv6_stage2_L2" + top: "Mconv6_stage2_L2" +} +layer { + name: "Mconv7_stage2_L1" + type: "Convolution" + bottom: "Mconv6_stage2_L1" + top: "Mconv7_stage2_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 28 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mconv7_stage2_L2" + type: "Convolution" + bottom: "Mconv6_stage2_L2" + top: "Mconv7_stage2_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 16 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "concat_stage3" + type: "Concat" + bottom: "Mconv7_stage2_L1" + bottom: "Mconv7_stage2_L2" + bottom: "conv4_4_CPM" + top: "concat_stage3" + concat_param { + axis: 1 + } +} +layer { + name: "Mconv1_stage3_L1" + type: "Convolution" + bottom: "concat_stage3" + top: "Mconv1_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage3_L1" + type: "ReLU" + bottom: "Mconv1_stage3_L1" + top: "Mconv1_stage3_L1" +} +layer { + name: "Mconv1_stage3_L2" + type: "Convolution" + bottom: "concat_stage3" + top: "Mconv1_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage3_L2" + type: "ReLU" + bottom: "Mconv1_stage3_L2" + top: "Mconv1_stage3_L2" +} +layer { + name: "Mconv2_stage3_L1" + type: "Convolution" + bottom: "Mconv1_stage3_L1" + top: "Mconv2_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage3_L1" + type: "ReLU" + bottom: "Mconv2_stage3_L1" + top: "Mconv2_stage3_L1" +} +layer { + name: "Mconv2_stage3_L2" + type: "Convolution" + bottom: "Mconv1_stage3_L2" + top: "Mconv2_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage3_L2" + type: "ReLU" + bottom: "Mconv2_stage3_L2" + top: "Mconv2_stage3_L2" +} +layer { + name: "Mconv3_stage3_L1" + type: "Convolution" + bottom: "Mconv2_stage3_L1" + top: "Mconv3_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage3_L1" + type: "ReLU" + bottom: "Mconv3_stage3_L1" + top: "Mconv3_stage3_L1" +} +layer { + name: "Mconv3_stage3_L2" + type: "Convolution" + bottom: "Mconv2_stage3_L2" + top: "Mconv3_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage3_L2" + type: "ReLU" + bottom: "Mconv3_stage3_L2" + top: "Mconv3_stage3_L2" +} +layer { + name: "Mconv4_stage3_L1" + type: "Convolution" + bottom: "Mconv3_stage3_L1" + top: "Mconv4_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage3_L1" + type: "ReLU" + bottom: "Mconv4_stage3_L1" + top: "Mconv4_stage3_L1" +} +layer { + name: "Mconv4_stage3_L2" + type: "Convolution" + bottom: "Mconv3_stage3_L2" + top: "Mconv4_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage3_L2" + type: "ReLU" + bottom: "Mconv4_stage3_L2" + top: "Mconv4_stage3_L2" +} +layer { + name: "Mconv5_stage3_L1" + type: "Convolution" + bottom: "Mconv4_stage3_L1" + top: "Mconv5_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage3_L1" + type: "ReLU" + bottom: "Mconv5_stage3_L1" + top: "Mconv5_stage3_L1" +} +layer { + name: "Mconv5_stage3_L2" + type: "Convolution" + bottom: "Mconv4_stage3_L2" + top: "Mconv5_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage3_L2" + type: "ReLU" + bottom: "Mconv5_stage3_L2" + top: "Mconv5_stage3_L2" +} +layer { + name: "Mconv6_stage3_L1" + type: "Convolution" + bottom: "Mconv5_stage3_L1" + top: "Mconv6_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage3_L1" + type: "ReLU" + bottom: "Mconv6_stage3_L1" + top: "Mconv6_stage3_L1" +} +layer { + name: "Mconv6_stage3_L2" + type: "Convolution" + bottom: "Mconv5_stage3_L2" + top: "Mconv6_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage3_L2" + type: "ReLU" + bottom: "Mconv6_stage3_L2" + top: "Mconv6_stage3_L2" +} +layer { + name: "Mconv7_stage3_L1" + type: "Convolution" + bottom: "Mconv6_stage3_L1" + top: "Mconv7_stage3_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 28 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mconv7_stage3_L2" + type: "Convolution" + bottom: "Mconv6_stage3_L2" + top: "Mconv7_stage3_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 16 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "concat_stage4" + type: "Concat" + bottom: "Mconv7_stage3_L1" + bottom: "Mconv7_stage3_L2" + bottom: "conv4_4_CPM" + top: "concat_stage4" + concat_param { + axis: 1 + } +} +layer { + name: "Mconv1_stage4_L1" + type: "Convolution" + bottom: "concat_stage4" + top: "Mconv1_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage4_L1" + type: "ReLU" + bottom: "Mconv1_stage4_L1" + top: "Mconv1_stage4_L1" +} +layer { + name: "Mconv1_stage4_L2" + type: "Convolution" + bottom: "concat_stage4" + top: "Mconv1_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu1_stage4_L2" + type: "ReLU" + bottom: "Mconv1_stage4_L2" + top: "Mconv1_stage4_L2" +} +layer { + name: "Mconv2_stage4_L1" + type: "Convolution" + bottom: "Mconv1_stage4_L1" + top: "Mconv2_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage4_L1" + type: "ReLU" + bottom: "Mconv2_stage4_L1" + top: "Mconv2_stage4_L1" +} +layer { + name: "Mconv2_stage4_L2" + type: "Convolution" + bottom: "Mconv1_stage4_L2" + top: "Mconv2_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu2_stage4_L2" + type: "ReLU" + bottom: "Mconv2_stage4_L2" + top: "Mconv2_stage4_L2" +} +layer { + name: "Mconv3_stage4_L1" + type: "Convolution" + bottom: "Mconv2_stage4_L1" + top: "Mconv3_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage4_L1" + type: "ReLU" + bottom: "Mconv3_stage4_L1" + top: "Mconv3_stage4_L1" +} +layer { + name: "Mconv3_stage4_L2" + type: "Convolution" + bottom: "Mconv2_stage4_L2" + top: "Mconv3_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu3_stage4_L2" + type: "ReLU" + bottom: "Mconv3_stage4_L2" + top: "Mconv3_stage4_L2" +} +layer { + name: "Mconv4_stage4_L1" + type: "Convolution" + bottom: "Mconv3_stage4_L1" + top: "Mconv4_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage4_L1" + type: "ReLU" + bottom: "Mconv4_stage4_L1" + top: "Mconv4_stage4_L1" +} +layer { + name: "Mconv4_stage4_L2" + type: "Convolution" + bottom: "Mconv3_stage4_L2" + top: "Mconv4_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu4_stage4_L2" + type: "ReLU" + bottom: "Mconv4_stage4_L2" + top: "Mconv4_stage4_L2" +} +layer { + name: "Mconv5_stage4_L1" + type: "Convolution" + bottom: "Mconv4_stage4_L1" + top: "Mconv5_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage4_L1" + type: "ReLU" + bottom: "Mconv5_stage4_L1" + top: "Mconv5_stage4_L1" +} +layer { + name: "Mconv5_stage4_L2" + type: "Convolution" + bottom: "Mconv4_stage4_L2" + top: "Mconv5_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 3 + kernel_size: 7 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu5_stage4_L2" + type: "ReLU" + bottom: "Mconv5_stage4_L2" + top: "Mconv5_stage4_L2" +} +layer { + name: "Mconv6_stage4_L1" + type: "Convolution" + bottom: "Mconv5_stage4_L1" + top: "Mconv6_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage4_L1" + type: "ReLU" + bottom: "Mconv6_stage4_L1" + top: "Mconv6_stage4_L1" +} +layer { + name: "Mconv6_stage4_L2" + type: "Convolution" + bottom: "Mconv5_stage4_L2" + top: "Mconv6_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 128 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mrelu6_stage4_L2" + type: "ReLU" + bottom: "Mconv6_stage4_L2" + top: "Mconv6_stage4_L2" +} +layer { + name: "Mconv7_stage4_L1" + type: "Convolution" + bottom: "Mconv6_stage4_L1" + top: "Mconv7_stage4_L1" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 28 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "Mconv7_stage4_L2" + type: "Convolution" + bottom: "Mconv6_stage4_L2" + top: "Mconv7_stage4_L2" + param { + lr_mult: 4.0 + decay_mult: 1 + } + param { + lr_mult: 8.0 + decay_mult: 0 + } + convolution_param { + num_output: 16 + pad: 0 + kernel_size: 1 + weight_filler { + type: "gaussian" + std: 0.01 + } + bias_filler { + type: "constant" + } + } +} +layer { + name: "concat_stage7" + type: "Concat" + bottom: "Mconv7_stage4_L2" + bottom: "Mconv7_stage4_L1" + top: "net_output" + concat_param { + axis: 1 + } +} diff --git a/src/computervision/ObjectDetection.cpp b/src/computervision/ObjectDetection.cpp index 62236d2..381b3cf 100644 --- a/src/computervision/ObjectDetection.cpp +++ b/src/computervision/ObjectDetection.cpp @@ -11,7 +11,7 @@ namespace computervision { - cv::VideoCapture cap(0); + cv::VideoCapture cap(1); cv::Mat img, imgGray, img2, img2Gray, img3, img4; @@ -59,10 +59,10 @@ namespace computervision putText(cameraFrame,hand_text, Point(10, 75), FONT_HERSHEY_PLAIN, 2.0, Scalar(255, 0, 255),3); imshow("camera", cameraFrame); - /* imshow("output", frameOut); + imshow("output", frameOut); imshow("foreground", foreground); imshow("handMask", handMask); - imshow("handDetection", fingerCountDebug);*/ + imshow("handDetection", fingerCountDebug); int key = waitKey(1); diff --git a/src/computervision/OpenPoseImage.cpp b/src/computervision/OpenPoseImage.cpp new file mode 100644 index 0000000..9e6578a --- /dev/null +++ b/src/computervision/OpenPoseImage.cpp @@ -0,0 +1,149 @@ +#include "OpenPoseImage.h" + +using namespace std; +using namespace cv; +using namespace cv::dnn; + +namespace computervision +{ +#define MPI + + +#ifdef MPI + const int POSE_PAIRS[14][2] = + { + {0,1}, {1,2}, {2,3}, + {3,4}, {1,5}, {5,6}, + {6,7}, {1,14}, {14,8}, {8,9}, + {9,10}, {14,11}, {11,12}, {12,13} + }; + + string protoFile = "res/pose/mpi/pose_deploy_linevec_faster_4_stages.prototxt"; + string weightsFile = "res/pose/mpi/pose_iter_160000.caffemodel"; + + int nPoints = 15; +#endif + +#ifdef COCO + const int POSE_PAIRS[17][2] = + { + {1,2}, {1,5}, {2,3}, + {3,4}, {5,6}, {6,7}, + {1,8}, {8,9}, {9,10}, + {1,11}, {11,12}, {12,13}, + {1,0}, {0,14}, + {14,16}, {0,15}, {15,17} + }; + + string protoFile = "pose/coco/pose_deploy_linevec.prototxt"; + string weightsFile = "pose/coco/pose_iter_440000.caffemodel"; + + int nPoints = 18; +#endif + + void OpenPoseImage::movementSkeleton(Mat inputImage) { + + + cout << "USAGE : ./OpenPose " << endl; + cout << "USAGE : ./OpenPose " << endl; + + string device = "cpu"; + + //string imageFile = "single.jpeg"; + // Take arguments from commmand line + /* if (argc == 2) + { + if ((string)argv[1] == "gpu") + device = "gpu"; + else + imageFile = argv[1]; + } + else if (argc == 3) + { + imageFile = argv[1]; + if ((string)argv[2] == "gpu") + device = "gpu"; + }*/ + + + + int inWidth = 368; + int inHeight = 368; + float thresh = 0.1; + + Mat frame = inputImage; + Mat frameCopy = frame.clone(); + int frameWidth = frame.cols; + int frameHeight = frame.rows; + + double t = (double)cv::getTickCount(); + Net net = readNetFromCaffe(protoFile, weightsFile); + + if (device == "cpu") + { + cout << "Using CPU device" << endl; + net.setPreferableBackend(DNN_TARGET_CPU); + } + else if (device == "gpu") + { + cout << "Using GPU device" << endl; + net.setPreferableBackend(DNN_BACKEND_CUDA); + net.setPreferableTarget(DNN_TARGET_CUDA); + } + + Mat inpBlob = blobFromImage(frame, 1.0 / 255, Size(inWidth, inHeight), Scalar(0, 0, 0), false, false); + + net.setInput(inpBlob); + + Mat output = net.forward(); + + int H = output.size[2]; + int W = output.size[3]; + + // find the position of the body parts + vector points(nPoints); + for (int n = 0; n < nPoints; n++) + { + // Probability map of corresponding body's part. + Mat probMap(H, W, CV_32F, output.ptr(0, n)); + + Point2f p(-1, -1); + Point maxLoc; + double prob; + minMaxLoc(probMap, 0, &prob, 0, &maxLoc); + if (prob > thresh) + { + p = maxLoc; + p.x *= (float)frameWidth / W; + p.y *= (float)frameHeight / H; + + circle(frameCopy, cv::Point((int)p.x, (int)p.y), 8, Scalar(0, 255, 255), -1); + cv::putText(frameCopy, cv::format("%d", n), cv::Point((int)p.x, (int)p.y), cv::FONT_HERSHEY_COMPLEX, 1, cv::Scalar(0, 0, 255), 2); + + } + points[n] = p; + } + + int nPairs = sizeof(POSE_PAIRS) / sizeof(POSE_PAIRS[0]); + + for (int n = 0; n < nPairs; n++) + { + // lookup 2 connected body/hand parts + Point2f partA = points[POSE_PAIRS[n][0]]; + Point2f partB = points[POSE_PAIRS[n][1]]; + + if (partA.x <= 0 || partA.y <= 0 || partB.x <= 0 || partB.y <= 0) + continue; + + line(frame, partA, partB, Scalar(0, 255, 255), 8); + circle(frame, partA, 8, Scalar(0, 0, 255), -1); + circle(frame, partB, 8, Scalar(0, 0, 255), -1); + } + + t = ((double)cv::getTickCount() - t) / cv::getTickFrequency(); + cout << "Time Taken = " << t << endl; + imshow("Output-Keypoints", frameCopy); + imshow("Output-Skeleton", frame); + imwrite("Output-Skeleton.jpg", frame); + } +} \ No newline at end of file diff --git a/src/computervision/OpenPoseVideo.cpp b/src/computervision/OpenPoseVideo.cpp new file mode 100644 index 0000000..882c728 --- /dev/null +++ b/src/computervision/OpenPoseVideo.cpp @@ -0,0 +1,144 @@ +#include "OpenPoseVideo.h" + +using namespace std; +using namespace cv; +using namespace cv::dnn; + +namespace computervision +{ +#define MPI + +#ifdef MPI + const int POSE_PAIRS[7][2] = + { + {0,1}, {1,2}, {2,3}, + {3,4}, {1,5}, {5,6}, + {6,7} + }; + + string protoFile = "res/pose/mpi/pose_deploy_linevec_faster_4_stages.prototxt"; + string weightsFile = "res/pose/mpi/pose_iter_160000.caffemodel"; + + int nPoints = 8; +#endif + +#ifdef COCO + const int POSE_PAIRS[17][2] = + { + {1,2}, {1,5}, {2,3}, + {3,4}, {5,6}, {6,7}, + {1,8}, {8,9}, {9,10}, + {1,11}, {11,12}, {12,13}, + {1,0}, {0,14}, + {14,16}, {0,15}, {15,17} + }; + + string protoFile = "pose/coco/pose_deploy_linevec.prototxt"; + string weightsFile = "pose/coco/pose_iter_440000.caffemodel"; + + int nPoints = 18; +#endif + Net net; + + void OpenPoseVideo::setup() { + net = readNetFromCaffe(protoFile, weightsFile); + } + + void OpenPoseVideo::movementSkeleton(Mat inputImage) { + + //string device = "cpu"; + //string videoFile = "sample_video.mp4"; + + // Take arguments from commmand line + /*if (argc == 2) + { + if ((string)argv[1] == "gpu") + device = "gpu"; + else + videoFile = argv[1]; + } + else if (argc == 3) + { + videoFile = argv[1]; + if ((string)argv[2] == "gpu") + device = "gpu"; + }*/ + + int inWidth = 368; + int inHeight = 368; + float thresh = 0.01; + + Mat frame, frameCopy; + int frameWidth = inputImage.size().width; + int frameHeight = inputImage.size().height; + + /*if (device == "cpu") + { + cout << "Using CPU device" << endl; + net.setPreferableBackend(DNN_TARGET_CPU); + } + else if (device == "gpu") + { + cout << "Using GPU device" << endl; + net.setPreferableBackend(DNN_BACKEND_CUDA); + net.setPreferableTarget(DNN_TARGET_CUDA); + }*/ + + double t = (double)cv::getTickCount(); + + frame = inputImage; + frameCopy = frame.clone(); + Mat inpBlob = blobFromImage(frame, 1.0 / 255, Size(inWidth, inHeight), Scalar(0, 0, 0), false, false); + + net.setInput(inpBlob); + + Mat output = net.forward(); + + int H = output.size[2]; + int W = output.size[3]; + + // find the position of the body parts + vector points(nPoints); + for (int n = 0; n < nPoints; n++) + { + // Probability map of corresponding body's part. + Mat probMap(H, W, CV_32F, output.ptr(0, n)); + + Point2f p(-1, -1); + Point maxLoc; + double prob; + minMaxLoc(probMap, 0, &prob, 0, &maxLoc); + if (prob > thresh) + { + p = maxLoc; + p.x *= (float)frameWidth / W; + p.y *= (float)frameHeight / H; + + circle(frameCopy, cv::Point((int)p.x, (int)p.y), 8, Scalar(0, 255, 255), -1); + cv::putText(frameCopy, cv::format("%d", n), cv::Point((int)p.x, (int)p.y), cv::FONT_HERSHEY_COMPLEX, 1.1, cv::Scalar(0, 0, 255), 2); + } + points[n] = p; + } + + int nPairs = sizeof(POSE_PAIRS) / sizeof(POSE_PAIRS[0]); + + for (int n = 0; n < nPairs; n++) + { + // lookup 2 connected body/hand parts + Point2f partA = points[POSE_PAIRS[n][0]]; + Point2f partB = points[POSE_PAIRS[n][1]]; + + if (partA.x <= 0 || partA.y <= 0 || partB.x <= 0 || partB.y <= 0) + continue; + + line(frame, partA, partB, Scalar(0, 255, 255), 8); + circle(frame, partA, 8, Scalar(0, 0, 255), -1); + circle(frame, partB, 8, Scalar(0, 0, 255), -1); + } + + t = ((double)cv::getTickCount() - t) / cv::getTickFrequency(); + cv::putText(frame, cv::format("time taken = %.2f sec", t), cv::Point(50, 50), cv::FONT_HERSHEY_COMPLEX, .8, cv::Scalar(255, 50, 0), 2); + // imshow("Output-Keypoints", frameCopy); + imshow("Output-Skeleton", frame); + } +} \ No newline at end of file diff --git a/src/computervision/OpenPoseVideo.h b/src/computervision/OpenPoseVideo.h new file mode 100644 index 0000000..eaef736 --- /dev/null +++ b/src/computervision/OpenPoseVideo.h @@ -0,0 +1,19 @@ +#pragma once + +#include +#include +#include +#include + +using namespace cv; + +namespace computervision +{ + class OpenPoseVideo{ + private: + + public: + void movementSkeleton(Mat inputImage); + void setup(); + }; +} diff --git a/src/main.cpp b/src/main.cpp index 7bab3f9..1e78430 100644 --- a/src/main.cpp +++ b/src/main.cpp @@ -18,6 +18,8 @@ #include "toolbox/toolbox.h" #include "computervision/ObjectDetection.h" +//#include "computervision/OpenPoseImage.h" +#include "computervision/OpenPoseVideo.h" #pragma comment(lib, "glfw3.lib") #pragma comment(lib, "glew32s.lib") @@ -64,12 +66,17 @@ int main(void) // create object detection object instance computervision::ObjectDetection objDetect; + //computervision::OpenPoseImage openPoseImage; + computervision::OpenPoseVideo openPoseVideo; // set up object detection //objDetect.setup(); cv::Mat cameraFrame; + + openPoseVideo.setup(); + // Main game loop while (!glfwWindowShouldClose(window)) { @@ -87,8 +94,8 @@ int main(void) render_engine::renderer::Render(entity, shader); cameraFrame = objDetect.readCamera(); - objDetect.detectHand(cameraFrame); - + //objDetect.detectHand(cameraFrame); + openPoseVideo.movementSkeleton(cameraFrame); // Finish up shader.Stop();