那些遇到过的问题

暹罗网络输出

Mas*_*ard 9 machine-learning computer-vision neural-network deep-learning caffe

我正在尝试在caffe中实现一个暹罗网络,它由两个不共享权重的图像网组成.所以我基本上要做的就是给每个网络一个图像,最后试着找出它们之间的相似距离,下面是我的原型.所以我的主要问题是我应该如何设置"num_output"呢？我的训练只有2个课程,0个不同,他们不相同,1个是相似的.

name: "Siamese_ImageNet"
layers {
  name: "data"
  type: IMAGE_DATA
  top: "data"
  top: "label"
  image_data_param {
    source: "train1.txt"
    batch_size: 32
    new_height: 256
    new_width: 256
  }
  include: { phase: TRAIN }
}
layers {
  name: "data"
  type: IMAGE_DATA
  top: "data"
  top: "label"
  image_data_param {
    source: "test1.txt"
    batch_size: 32
    new_height: 256
    new_width: 256
  }
  include: { phase: TEST }
}

layers {
  name: "data_p"
  type: IMAGE_DATA
  top: "data_p"
  top: "label_p"
  image_data_param {
    source: "train2.txt"
    batch_size: 32
    new_height: 256
    new_width: 256
  }
  include: { phase: TRAIN }
}
layers {
  name: "data_p"
  type: IMAGE_DATA
  top: "data_p"
  top: "label_p"
  image_data_param {
    source: "test2.txt"
    batch_size: 32
    new_height: 256
    new_width: 256
  }
  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: 11
    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
    group: 2
    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: "conv4"
  type: CONVOLUTION
  bottom: "conv3"
  top: "conv4"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layers {
  name: "relu4"
  type: RELU
  bottom: "conv4"
  top: "conv4"
}
layers {
  name: "conv5"
  type: CONVOLUTION
  bottom: "conv4"
  top: "conv5"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layers {
  name: "relu5"
  type: RELU
  bottom: "conv5"
  top: "conv5"
}
layers {
  name: "pool5"
  type: POOLING
  bottom: "conv5"
  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: 4096
    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: 2
    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: "conv1_p"
  type: CONVOLUTION
  bottom: "data_p"
  top: "conv1_p"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 96
    kernel_size: 11
    stride: 4
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layers {
  name: "relu1_p"
  type: RELU
  bottom: "conv1_p"
  top: "conv1_p"
}
layers {
  name: "pool1_p"
  type: POOLING
  bottom: "conv1_p"
  top: "pool1_p"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layers {
  name: "norm1_p"
  type: LRN
  bottom: "pool1_p"
  top: "norm1_p"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layers {
  name: "conv2_p"
  type: CONVOLUTION
  bottom: "norm1_p"
  top: "conv2_p"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 256
    pad: 2
    kernel_size: 5
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layers {
  name: "relu2_p"
  type: RELU
  bottom: "conv2_p"
  top: "conv2_p"
}
layers {
  name: "pool2_p"
  type: POOLING
  bottom: "conv2_p"
  top: "pool2_p"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layers {
  name: "norm2_p"
  type: LRN
  bottom: "pool2_p"
  top: "norm2_p"
  lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
  }
}
layers {
  name: "conv3_p"
  type: CONVOLUTION
  bottom: "norm2_p"
  top: "conv3_p"
  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_p"
  type: RELU
  bottom: "conv3_p"
  top: "conv3_p"
}
layers {
  name: "conv4_p"
  type: CONVOLUTION
  bottom: "conv3_p"
  top: "conv4_p"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layers {
  name: "relu4_p"
  type: RELU
  bottom: "conv4_p"
  top: "conv4_p"
}
layers {
  name: "conv5_p"
  type: CONVOLUTION
  bottom: "conv4_p"
  top: "conv5_p"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
    group: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layers {
  name: "relu5_p"
  type: RELU
  bottom: "conv5_p"
  top: "conv5_p"
}
layers {
  name: "pool5_p"
  type: POOLING
  bottom: "conv5_p"
  top: "pool5_p"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layers {
  name: "fc6_p"
  type: INNER_PRODUCT
  bottom: "pool5_p"
  top: "fc6_p"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  inner_product_param {
    num_output: 4096
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layers {
  name: "relu6_p"
  type: RELU
  bottom: "fc6_p"
  top: "fc6_p"
}
layers {
  name: "drop6_p"
  type: DROPOUT
  bottom: "fc6_p"
  top: "fc6_p"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  name: "fc7_p"
  type: INNER_PRODUCT
  bottom: "fc6_p"
  top: "fc7_p"
  blobs_lr: 1
  blobs_lr: 2
  weight_decay: 1
  weight_decay: 0
  inner_product_param {
    num_output: 2
    weight_filler {
      type: "gaussian"
      std: 0.005
    }
    bias_filler {
      type: "constant"
      value: 1
    }
  }
}
layers {
  name: "relu7_p"
  type: RELU
  bottom: "fc7_p"
  top: "fc7_p"
}
layers {
  name: "drop7_p"
  type: DROPOUT
  bottom: "fc7_p"
  top: "fc7_p"
  dropout_param {
    dropout_ratio: 0.5
  }
}

layers {
    name: "loss"
    type: CONTRASTIVE_LOSS
    contrastive_loss_param {
        margin: 1.0
    }
    bottom: "fc7"
    bottom: "fc7_p"
    bottom: "label"
    top: "loss"
}
Run Code Online (Sandbox Code Playgroud)

我的训练文件结构:0不相似,1相似

 train1.txt:
 /aer/img1_1.jpg 0
 /aer/img1_2.jpg 1
 /aer/img1_3.jpg 1

 train2.txt:
 /tpd/img2_1.jpg 0
 /tpd/img2_2.jpg 1
 /tpd/img2_3.jpg 1
Run Code Online (Sandbox Code Playgroud)

Dal*_*ale 7

我该怎么设置"num_output"？

在了解你应该设置多少之前num_output,让我们解释一下它的含义.实际上,您可以查看Simense网络的两侧data -> fc7,data_p -> fc7_p作为2个特征提取器.每一个被提取特征例如fc7 与fc7_p从图像在相应的数据层.因此num_output定义了提取的特征向量的维度.

在训练期间,ContrastiveLoss当矢量表示的图像类似(label == 1)时,图层总是尝试最小化2个提取的特征向量的距离,并且当不相似(label == 0)时最大化距离.即,特征向量的距离越小,图像越相似.

那么特征向量的最佳维度是什么才能最好地包含指示相似性的信息？或者你应该设置num_output什么？可能没有确切的值,它取决于特征提取器的编码质量(您可以将该特征视为图像的代码)以及识别图像的相似性有多难.所以基本上如果网络(特征提取器)很深并且不太难以识别相似性,则可以选择相对较小的num_outputeg200,因为该特征可以由更大的网络很好地编码并且更具辨别力.如果不是,您可以尝试更大的值,例如500,1000或尝试更复杂的网络.

如果您想尝试MultinomialLogisticLoss,而不是ContrastiveLoss一层,你应该先融合2特征向量fc7,fc7_p为1使用层状CONCAT,然后将其送到一个SOFTMAX_LOSS层,就像这样:

...#original layers
layers {
  name: "concat"
  type: CONCAT
  bottom: "fc7"
  bottom: "fc7_p"  
  top: "fc_concat" # concatenate fc7 and fc7_p along channel axis
}
layer {
  name: "fc_cls"
  type: INNER_PRODUCT
  bottom: "fc_concat"
  top: "fc_cls"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 2 # a binary classification problem in this case
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "accuracy"
  type: ACCURACY
  bottom: "fc_cls"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
  name: "loss"
  type: SOFTMAX_LOSS
  bottom: "fc_cls"
  bottom: "label"
  top: "loss"
}
Run Code Online (Sandbox Code Playgroud)

更新

为了比较相似性并将其用于部署,Constrastive Loss或SoftMax Loss,哪种方法最好？

Softmax Loss简单易用.但它只能给你二进制预测,即相似或不相似.在2类(类似,不同)的概率分布,它给常太硬(不均匀),例如[0.9*, 0.0*],[0.0*, 0.9*],....在许多情况下将不能反映真实输入相似度良好.

使用Constrastive Loss时,您可以获得图像的判别特征向量.并且您可以使用向量来计算相似概率,正如CVPR 2005论文学习相似性度量,与应用于面部验证在4.1节中所做的那样(关键点是使用特征向量计算多元法向密度)从属于同一主题的图像生成.您还可以使用阈值来控制模型 的假阳性率和假阴性率,以获得ROC曲线以更好地评估模型.

顺便说一句,为了挖掘更多用于预测相似性的CNN架构,您可以参考CVPR 2015论文学习通过卷积神经网络比较图像补丁.

  • 您可能会发现[此主题](http://stackoverflow.com/q/40510706/1714410)对调试很有用. (3认同)

归档时间：

查看次数：

1645 次

最近记录：

8 年，8 月 前
如何用NumPy计算欧氏距离？ 466
如何用debug_info解释caffe日志？ 14
更多相关链接
相关归档
如何在R中使用keras使用Python安装的tensorflow 13
ANN回归,线性函数逼近 8
Roc_curve pos_label混淆 8
Keras LSTM输入尺寸,带有一个热文本嵌入 6
使用 BERT 的 wordpiece 分词器时如何处理标签 6
Tesseract OCR：字体大小参数（单个字符） 5
Pandas DataFrame 中两个日期之间的差异 3
加载模型时如何使用 min max scaler 拟合测试数据？ 3
如何计算随机森林的类权重 2
从keras模型中将特征提取到数据集中 1
难疑归档
如何重命名本地Git分支？ 8033
如何异步上传文件？ 2841
停止EditText在Activity启动时获得焦点 2770
命令折叠代码的所有部分？ 1576
在Vim中复制整行 1555
如何设置HTML <select>元素的默认值？ 1343
将零填充到字符串的最好方法 1309
如何在JavaScript中合并两个数组并重复删除项目 1256
如何在PHP中进行重定向？ 1201
如何进行HTTP POST Web请求 1033