深度学习 VGG 网络 实现 face landmark 与 head pose

VGG深度网络实现人脸特征点预测与人脸pose（3D ）估计

一、实现需要的库：

• caffe 
• dlib face detector

  you can down dlib18.17

  cd your dlib folder

  cd python_example

  ./compile_dlib_python_module.bat

  add dlib.so to the python path

  if using dlib18.18, you can follow the official instruction

• opencv

二、运行命令行：

python landmarkPredict.py predictImage testList.txt

三、参数说明：

testList.txt:   图片路径

如下：

img/image_09.jpg
img/image_018.jpg
img/image_019_1.jpg
img/image_020_1.jpg

四、训练好的模型：

点击这里下载： here

五、*.prototxt 文件预览

name: "dlib_vgg"
layers {
  name: "data"
  type: MEMORY_DATA
  top: "data"
  top: "label"
  memory_data_param {
    batch_size: 1 #batch size, so how many prediction youu want to do at once. Best is "1", but higher number get better performance
    channels: 3
    height: 224
    width: 224 
  }
}

layers {
  bottom: "data"
  top: "conv1"
  name: "conv1"
  type: CONVOLUTION
  convolution_param {
    num_output: 96
    kernel_size: 7
    stride: 2
  }
}
layers {
  bottom: "conv1"
  top: "conv1"
  name: "relu1"
  type: RELU
}
layers {
  bottom: "conv1"
  top: "norm1"
  name: "norm1"
  type: LRN
  lrn_param {
    local_size: 5
    alpha: 0.0005
    beta: 0.75
    k: 2
  }
}
layers {
  bottom: "norm1"
  top: "pool1"
  name: "pool1"
  type: POOLING
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 3
  }
}
layers {
  bottom: "pool1"
  top: "conv2"
  name: "conv2"
  type: CONVOLUTION
  convolution_param {
    num_output: 256
    kernel_size: 5
  }
}
layers {
  bottom: "conv2"
  top: "conv2"
  name: "relu2"
  type: RELU
}
layers {
  bottom: "conv2"
  top: "pool2"
  name: "pool2"
  type: POOLING
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layers {
  bottom: "pool2"
  top: "conv3"
  name: "conv3"
  type: CONVOLUTION
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layers {
  bottom: "conv3"
  top: "conv3"
  name: "relu3"
  type: RELU
}
layers {
  bottom: "conv3"
  top: "conv4"
  name: "conv4"
  type: CONVOLUTION
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layers {
  bottom: "conv4"
  top: "conv4"
  name: "relu4"
  type: RELU
}
layers {
  bottom: "conv4"
  top: "conv5"
  name: "conv5"
  type: CONVOLUTION
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layers {
  bottom: "conv5"
  top: "conv5"
  name: "relu5"
  type: RELU
}
layers {
  bottom: "conv5"
  top: "pool5"
  name: "pool5"
  type: POOLING
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 3
  }
}
layers {
  bottom: "pool5"
  top: "fc6"
  name: "fc6"
  type: INNER_PRODUCT
  inner_product_param {
    num_output: 4096
  }
}
layers {
  bottom: "fc6"
  top: "fc6"
  name: "relu6"
  type: RELU
}
layers {
  bottom: "fc6"
  top: "fc6"
  name: "drop6"
  type: DROPOUT
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  bottom: "fc6"
  top: "fc7"
  name: "fc7"
  type: INNER_PRODUCT
  inner_product_param {
    num_output: 4096
  }
}
layers {
  bottom: "fc7"
  top: "fc7"
  name: "relu7"
  type: RELU
}
layers {
  bottom: "fc7"
  top: "fc7"
  name: "drop7"
  type: DROPOUT
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  bottom: "fc7"
  top: "68point"
  name: "68point"
  type: INNER_PRODUCT
  inner_product_param {
    num_output: 136
  }
}




layers {
  bottom: "fc7"
  top: "poselayer"
  name: "poselayer"
  type: INNER_PRODUCT
  inner_product_param {
    num_output: 3
  }
}

实验效果：

 

代码下载：

https://github.com/guozhongluo/fuzzy-luoguozhong