原文地址:https://www.learnopencv.com/deep-learning-based-human-pose-estimation-using-opencv-cpp-python/
COCO输出格式:
鼻子– 0,脖子– 1,右肩– 2,右肘– 3,右腕– 4,左肩– 5,左肘– 6,左腕– 7,右臀部– 8,右膝盖– 9 ,右脚踝– 10,左髋– 11,左膝– 12,LAnkle – 13,右眼– 14,左眼– 15,右耳– 16,左耳– 17,背景– 18
模型文件:
input: "image"input_dim: 1input_dim: 3input_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 64pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 64pad: 1kernel_size: 3weight_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: 2stride: 2} } layer { name: "conv2_1"type: "Convolution"bottom: "pool1_stage1"top: "conv2_1"param { lr_mult: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 128pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 128pad: 1kernel_size: 3weight_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: 2stride: 2} } layer { name: "conv3_1"type: "Convolution"bottom: "pool2_stage1"top: "conv3_1"param { lr_mult: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 256pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 256pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 256pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 256pad: 1kernel_size: 3weight_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: 2stride: 2} } layer { name: "conv4_1"type: "Convolution"bottom: "pool3_stage1"top: "conv4_1"param { lr_mult: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 512pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 512pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 256pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 128pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 128pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 128pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 128pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 128pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 128pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 128pad: 1kernel_size: 3weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 512pad: 0kernel_size: 1weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 512pad: 0kernel_size: 1weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 38pad: 0kernel_size: 1weight_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: 1.0decay_mult: 1} param { lr_mult: 2.0decay_mult: 0} convolution_param { num_output: 19pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 38pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 19pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 38pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 19pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 38pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 19pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 38pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 19pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 3kernel_size: 7weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 128pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 38pad: 0kernel_size: 1weight_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: 4.0decay_mult: 1} param { lr_mult: 8.0decay_mult: 0} convolution_param { num_output: 19pad: 0kernel_size: 1weight_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} }
下载模型权重
步骤一:
我们正在使用在Caffe深度学习框架上训练的模型。Caffe模型具有2个文件–
- .prototxt文件,指定了神经网络的体系结构–不同层的排列方式等。
- .caffemodel文件,用于存储训练后的模型的权重
我们将使用这两个文件将网络加载到内存中。
protoFile = "model/pose_deploy_linevec.prototxt"weightsFile = "model/pose_iter_440000.caffemodel"net
=
cv2.dnn.readNetFromCaffe(protoFile, weightsFile)
步骤二:
读取图像并准备输入网络
我们使用OpenCV读取的输入帧应转换为输入Blob(例如Caffe),以便可以将其输入到网络。这是使用blobFromImage函数完成的,该函数将图像从OpenCV格式转换为Caffe blob格式。这些参数将在blobFromImage函数中提供。首先,我们将像素值标准化为(0,1)。然后,我们指定图像的尺寸。接下来,要减去的平均值为(0,0,0)。由于OpenCV和Caffe都使用BGR格式,因此无需交换R和B通道。
net = cv2.dnn.readNetFromCaffe(protoFile, weightsFile) #读取caffe模型 inWidth = 368inHeight = 368inpBlob = cv2.dnn.blobFromImage(frame, 1.0 / 255, (inWidth, inHeight), (0, 0, 0), swapRB=False, crop=False) #将输入图片转成相应模型识别的blob数据 net.setInput(inpBlob) #放进网络
步骤三:
进行预测并解析关键点
一旦将图像传递到模型,就可以使用单行代码进行预测。OpenCV中DNN类的正向方法通过网络进行正向传递,这只是说它正在做出预测的另一种方式。
output = net.forward() #向前传播,进行预测
输出为4D矩阵:
- 第一维是图像ID(如果您将多个图像传递到网络)。
- 第二个维度指示关键点的索引。该模型将生成所有连接在一起的置信度图和零件亲和度图。对于COCO模型,它由57个部分组成– 18个关键点置信度图+ 1个背景+ 19 * 2个部分亲和度图。同样,对于MPI,它会产生44点。我们将仅使用与关键点相对应的前几个点。
- 第三维是输出图的高度。
- 第四个维度是输出图的宽度。
我们检查图像中是否存在每个关键点。我们通过找到关键点的置信度图的最大值来获得关键点的位置。我们还使用阈值来减少错误检测。
H = out.shape[2] W = out.shape[3] #Empty list to store the detected keypoints points =[] for i inrange(len()): #confidence map of corresponding body's part. probMap =output[0, i, :, :] #Find global maxima of the probMap. minVal, prob, minLoc, point =cv2.minMaxLoc(probMap) #Scale the point to fit on the original image x = (frameWidth * point[0]) /W y = (frameHeight * point[1]) /H if prob > threshold : cv2.circle(frame, (int(x), int(y)), 15, (0, 255, 255), thickness=-1, lineType=cv.FILLED) cv2.putText(frame, "{}".format(i), (int(x), int(y)), cv2.FONT_HERSHEY_SIMPLEX, 1.4, (0, 0, 255), 3, lineType=cv2.LINE_AA) #Add the point to the list if the probability is greater than the threshold points.append((int(x), int(y))) else: points.append(None) cv2.imshow("Output-Keypoints",frame) cv2.waitKey(0) cv2.destroyAllWindows()
由于我们事先知道了点的索引,因此只要有关键点,我们就可以通过仅加入对来绘制骨架。这是使用下面给出的代码完成的。
for pair inPOSE_PAIRS: partA =pair[0] partB = pair[1] if points[partA] andpoints[partB]: cv2.line(frameCopy, points[partA], points[partB], (0, 255, 0), 3)
完整代码:
importcv2 importtime importnumpy as np MODE = "COCO" if MODE is "COCO": protoFile = "model/pose_deploy_linevec.prototxt"weightsFile = "model/pose_iter_440000.caffemodel"nPoints = 18POSE_PAIRS = [[1, 0], [1, 2], [1, 5], [2, 3], [3, 4], [5, 6], [6, 7], [1, 8], [8, 9], [9, 10], [1, 11], [11, 12], [12, 13], [0, 14], [0, 15], [14, 16], [15, 17]] frame = cv2.imread("image.jpg") frameCopy =np.copy(frame) frameWidth = frame.shape[1] frameHeight =frame.shape[0] threshold = 0.1 net = cv2.dnn.readNetFromCaffe(protoFile, weightsFile) #读取caffe模型 t =time.time() inWidth = 368inHeight = 368inpBlob = cv2.dnn.blobFromImage(frame, 1.0 / 255, (inWidth, inHeight), (0, 0, 0), swapRB=False, crop=False) #将输入图片转成相应模型识别的blob数据 net.setInput(inpBlob) #放进网络 output = net.forward() #向前传播,进行预测 print("time taken by network : {:.3f}".format(time.time() -t)) #print(output.shape, output)#输出4D举证:#第一维是图像ID(如果您将多个图像传递到网络)。#第二个维度指示关键点的索引。该模型将生成所有连接在一起的置信度图和零件亲和度图。对于COCO模型,它由57个部分组成– 18个关键点置信度图+ 1个背景+ 19 * 2个部分亲和度图。同样,对于MPI,它会产生44点。我们将仅使用与关键点相对应的前几个点。#第三维是输出图的高度。#第四个维度是输出图的宽度。 H = output.shape[2] #输出的图像的高度 W = output.shape[3] #输出图像的宽度 #Empty list to store the detected keypoints points =[] for i inrange(nPoints): #confidence map of corresponding body's part. probMap = output[0, i, :, :] #获取关键点 #Find global maxima of the probMap. minVal, prob, minLoc, point = cv2.minMaxLoc(probMap) #通过minMaxLoc得出该矩阵中的最小值、最大值、最小值索引,最大值索引 print(minVal, prob, minLoc, point) #Scale the point to fit on the original image将输出图像中的关键点映射到原始图片上 x = (frameWidth / W) *point[0] y = (frameHeight / H) * point[1] if prob >threshold: cv2.circle(frameCopy, (int(x), int(y)), 4, (0, 255, 255), thickness=-1, lineType=cv2.FILLED) cv2.putText(frameCopy, "{}".format(i), (int(x), int(y)), cv2.FONT_HERSHEY_SIMPLEX, 0.3, (0, 0, 255), lineType=cv2.LINE_AA) #Add the point to the list if the probability is greater than the threshold points.append((int(x), int(y))) else: points.append(None) #Draw Skeleton for pair inPOSE_PAIRS: partA =pair[0] partB = pair[1] if points[partA] andpoints[partB]: cv2.line(frame, points[partA], points[partB], (0, 255, 255), 2) cv2.circle(frame, points[partA], 8, (0, 0, 255), thickness=-1, lineType=cv2.FILLED) cv2.imshow('Output-Keypoints', frameCopy) cv2.imshow('Output-Skeleton', frame) print("Total time taken : {:.3f}".format(time.time() -t)) cv2.waitKey(0)