基于CNN的人脸识别

前些日子读了一篇关于人脸识别的文章，age and gender classificiation using convolutional neural networks，这是一篇发表在cvpr2015的一篇文章，文章写得很好，条理清晰，逻辑性强，非常适合深度学习者学习，在这里特别做一个相关笔记。

当然，我也尝试着去实现这篇论文，文章中说到要用adience benchmark人脸数据库，我上网上找了找并没有找到这个数据库，于是乎我只能找其他的数据库来代替。开始的时候自己搜集数据库（汗！），搜集了大概1000张人脸，去训练神经网络时损失函数直接爆炸，完全不收敛，折腾了好久才想到可能是数据库样本太小的原因，后来在知乎大牛的指导下扩大自己的数据库，然后在caffe上运行试验，结果不但收敛了，准确率竟能达到约98%！！！

在实现的过程中需要注意的是数据库的大小一定不能太小，否则会不收敛，再者，要适当选择网络中的参数。我用cuda-convnet（也就是cifar10分类问题中比较流行的一个网络结构）来训练速度很快，最高准确率能达到96%，用论文中所述的网络结构时，速度要慢很多，但是最后准确率最高达到98.5%。

我只实现了人脸性别检测，人脸年龄检测问题可以说是换汤不换药，因为数据库准备需要大量的人力物力，所以就没有继续做下去！

卷积神经网络的结构如下图：

多的不说，先看看代码：

age_net:

name: "facenet"
layers {
  name: "data"
  type: DATA
  top: "data"
  top: "label"
  data_param {
    source: "data/mywork/face_train_lmdb"
    backend: LMDB
    batch_size: 50
  }
  transform_param {
    crop_size: 227
    mean_file: "data/mywork/face_mean.binaryproto"
    mirror: true
  }
  include: { phase: TRAIN }
}
layers {
  name: "data"
  type: DATA
  top: "data"
  top: "label"
  data_param {
    source:  "data/mywork/face_val_lmdb"
    backend: LMDB
    batch_size: 50
  }
  transform_param {
    crop_size: 227
    mean_file: "data/mywork/face_mean.binaryproto"
    mirror: false
  }
  include: { phase: TEST }
}
layers {
  name: "conv1"
  type: CONVOLUTION
  bottom: "data"
  top: "conv1"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 96
    kernel_size: 7
    stride: 4
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  name: "relu1"
  type: RELU
  bottom: "conv1"
  top: "conv1"
}
layers {
  name: "pool1"
  type: POOLING
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layers {
  name: "norm1"
  type: LRN
  bottom: "pool1"
  top: "norm1"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layers {
  name: "conv2"
  type: CONVOLUTION
  bottom: "norm1"
  top: "conv2"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 256
    pad: 2
    kernel_size: 5
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layers {
  name: "relu2"
  type: RELU
  bottom: "conv2"
  top: "conv2"
}
layers {
  name: "pool2"
  type: POOLING
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layers {
  name: "norm2"
  type: LRN
  bottom: "pool2"
  top: "norm2"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layers {
  name: "conv3"
  type: CONVOLUTION
  bottom: "norm2"
  top: "conv3"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers{
  name: "relu3" 
  type: RELU
  bottom: "conv3"
  top: "conv3"
}
layers {
  name: "pool5"
  type: POOLING
  bottom: "conv3"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layers {
  name: "fc6"
  type: INNER_PRODUCT
  bottom: "pool5"
  top: "fc6"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  inner_product_param {
    num_output: 512
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layers {
  name: "relu6"
  type: RELU
  bottom: "fc6"
  top: "fc6"
}
layers {
  name: "drop6"
  type: DROPOUT
  bottom: "fc6"
  top: "fc6"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  name: "fc7"
  type: INNER_PRODUCT
  bottom: "fc6"
  top: "fc7"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  inner_product_param {
    num_output: 512
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layers {
  name: "relu7"
  type: RELU
  bottom: "fc7"
  top: "fc7"
}
layers {
  name: "drop7"
  type: DROPOUT
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  name: "fc8"
  type: INNER_PRODUCT
  bottom: "fc7"
  top: "fc8"
  blobs_lr: 10
  blobs_lr: 20
  weight_decay: 1
  weight_decay: 0
  inner_product_param {
    num_output: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  name: "accuracy"
  type: ACCURACY
  bottom: "fc8"
  bottom: "label"
  top: "accuracy"
  include: { phase: TEST }
}
layers {
  name: "loss"
  type: SOFTMAX_LOSS
  bottom: "fc8"
  bottom: "label"
  top: "loss"
}

结构非常简单，经过大概4个小时的训练达到预期准确率。