zoukankan      html  css  js  c++  java
  • 浅谈caffe中train_val.prototxt和deploy.prototxt文件的区别

    本文以CaffeNet为例:

    1. train_val.prototxt 
    首先,train_val.prototxt文件是网络配置文件。该文件是在训练的时候用的。
    2.deploy.prototxt
    该文件是在测试时使用的文件。

    区别:
    首先deploy.prototxt文件都是在train_val.prototxt文件的基础上删除了一些东西,所形成的。
    由于两个文件的性质,train_val.prototxt文件里面训练的部分都会在deploy.prototxt文件中删除。

    在train_val.prototxt文件中,开头要加入一下训练设置文件和准备文件。例如,transform_param中的mirror: true(开启镜像);crop_size: ***(图像尺寸);mean_file: ""(求解均值的文件),还有data_param中的source:""(处理过得数据训练集文件);batch_size: ***(训练图片每批次输入图片的数量);backend: LMDB(数据格式设置)。
    然后接下来,训练的时候还有一个测试的设置,测试和训练模式的设置通过一个include{phase: TEST/TRAIN}来设置。接下来就是要设置TEST模块内容。然后其他设置跟上面一样,里面有个batch_size可以调小一点,因为测试的话不需要特别多的图片数量。
    而以上这一块的内容在deploy里表现出来的只有一个数据层的设置。只需设置name,type,top,input_param这些即可。
    接下来,第一个卷积层的设置,train_val.prototxt文件中多了param(反向传播学习率的设置),这里需要设置两个param一个时weight的学习率,一个时bias的学习率,其中一般bias的学习率是weight学习率的两倍。然后就是设置convolution_param,但是在train_val里面需要有对weight_filler的初始化和对bias_filler的初始化。
    然后就是设置激活激活函数。这一块由于没有初始化,所以两个文件都是一样的。
    再接下来就是池化层,由于池化就是降低分辨率,所以这两边是一样的,只需要设置kernel_size,stride,pool即可。无需参数的初始化。
    再下来时LRN层,该层的全称是Local Response Normalization(局部响应值归一化),该层的作用就是对局部输入进行一个归一化操作,不过现在有论文表明,这一层加不加对结果影响不是很大。但这一层的定义都是相同的。
    再接下来就是"conv2"、"relu2"、"pool2"、"LRN2"这样的循环,具体跟之前说的一样,train_val主要多的就是参数的初始化和学习率的设置。
    在第五个卷积层之后,进入了"fc6"层,该层是全连接层,这里train_val里面还是多两个param学习率的设置,和weight_filler、bias_filler的初始化设置,而两者共同的是有一个输出向量元素个数的设置:inner_product_param。
    再接下来就是激活函数RELU。
    再接下来就是Dropout层,该层的目的就是为了防止模型过拟合。这其中有一个dropout_ration的设置一般为0.5即可。
    再接下来就是"fc7",这一层跟"fc6"相同。然后就是"relu7"、"drop7"都是相同的。然后就是"fc8"也与之前相同。
    再接下来就是Accuracy,这个层是用来计算网络输出相对目标值的准确率,它实际上并不是一个损失层,所以没有反传操作。但是在caffe官网中,它在损失层这一部分。所以在deploy.prototxt文件中,这一层的定义是没有的。
    再接下来train_val的最后一个层是"SoftmaxWithLoss"层,也是简单的定义了name,type,bottom,top就完了。而这一块的内容也不在deploy.prototxt文件中。
    而在deploy.prototxt文件中直接定义了一个type:"Softmax"。

    通过对CaffeNet这两个文件的查看发现deploy.prototxt文件和train_val.prototxt文件之间的差异在很多层里面牵扯到训练部分的都会被删除,然后就是反向传播训练部分会被删除。


    其中,这里面有一个区别在里头,就是为什么train_val里面的是SoftmaxWithLoss而deploy里面的是Softmax层(两个都是损失层,都没有任何参数):
    这里面其实都是softmax回归的应用,只是在定义成Softmax时直接计算了概率室友forward部分,而在SoftmaxWithLoss部分时是还有backward的部分。所以这里就出现了区别,具体的区别可以看这两个文件的C++定义。


    下表左边的是train_val.prototxt文件,右边是deploy.prototxt文件。
     
    name: "CaffeNet"
    layer {
    name: "data"
    type: "Data"
    top: "data"
    top: "label"
    include {
    phase: TRAIN
    }
    transform_param {
    mirror: true
    crop_size: 227
    mean_file: "data/ilsvrc12/imagenet_mean.binaryproto"
    }
    # mean pixel / channel-wise mean instead of mean image
    # transform_param {
    # crop_size: 227
    # mean_value: 104
    # mean_value: 117
    # mean_value: 123
    # mirror: true
    # }
    data_param {
    source: "examples/imagenet/ilsvrc12_train_lmdb"
    batch_size: 256
    backend: LMDB
    }
    }
    layer {
    name: "data"
    type: "Data"
    top: "data"
    top: "label"
    include {
    phase: TEST
    }
    transform_param {
    mirror: false
    crop_size: 227
    mean_file: "data/ilsvrc12/imagenet_mean.binaryproto"
    }
    # mean pixel / channel-wise mean instead of mean image
    # transform_param {
    # crop_size: 227
    # mean_value: 104
    # mean_value: 117
    # mean_value: 123
    # mirror: false
    # }
    data_param {
    source: "examples/imagenet/ilsvrc12_val_lmdb"
    batch_size: 50
    backend: LMDB
    }
    }
    layer {
    name: "conv1"
    type: "Convolution"
    bottom: "data"
    top: "conv1"
    param {
    lr_mult: 1
    decay_mult: 1
    }
    param {
    lr_mult: 2
    decay_mult: 0
    }
    convolution_param {
    num_output: 96
    kernel_size: 11
    stride: 4
    weight_filler {
    type: "gaussian"
    std: 0.01
    }
    bias_filler {
    type: "constant"
    value: 0
    }
    }
    }
    layer {
    name: "relu1"
    type: "ReLU"
    bottom: "conv1"
    top: "conv1"
    }
    layer {
    name: "pool1"
    type: "Pooling"
    bottom: "conv1"
    top: "pool1"
    pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
    }
    }
    layer {
    name: "norm1"
    type: "LRN"
    bottom: "pool1"
    top: "norm1"
    lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
    }
    }
    layer {
    name: "conv2"
    type: "Convolution"
    bottom: "norm1"
    top: "conv2"
    param {
    lr_mult: 1
    decay_mult: 1
    }
    param {
    lr_mult: 2
    decay_mult: 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
    }
    }
    }
    layer {
    name: "relu2"
    type: "ReLU"
    bottom: "conv2"
    top: "conv2"
    }
    layer {
    name: "pool2"
    type: "Pooling"
    bottom: "conv2"
    top: "pool2"
    pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
    }
    }
    layer {
    name: "norm2"
    type: "LRN"
    bottom: "pool2"
    top: "norm2"
    lrn_param {
    local_size: 5
    alpha: 0.0001
    beta: 0.75
    }
    }
    layer {
    name: "conv3"
    type: "Convolution"
    bottom: "norm2"
    top: "conv3"
    param {
    lr_mult: 1
    decay_mult: 1
    }
    param {
    lr_mult: 2
    decay_mult: 0
    }
    convolution_param {
    num_output: 384
    pad: 1
    kernel_size: 3
    weight_filler {
    type: "gaussian"
    std: 0.01
    }
    bias_filler {
    type: "constant"
    value: 0
    }
    }
    }
    layer {
    name: "relu3"
    type: "ReLU"
    bottom: "conv3"
    top: "conv3"
    }
    layer {
    name: "conv4"
    type: "Convolution"
    bottom: "conv3"
    top: "conv4"
    param {
    lr_mult: 1
    decay_mult: 1
    }
    param {
    lr_mult: 2
    decay_mult: 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
    }
    }
    }
    layer {
    name: "relu4"
    type: "ReLU"
    bottom: "conv4"
    top: "conv4"
    }
    layer {
    name: "conv5"
    type: "Convolution"
    bottom: "conv4"
    top: "conv5"
    param {
    lr_mult: 1
    decay_mult: 1
    }
    param {
    lr_mult: 2
    decay_mult: 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
    }
    }
    }
    layer {
    name: "relu5"
    type: "ReLU"
    bottom: "conv5"
    top: "conv5"
    }
    layer {
    name: "pool5"
    type: "Pooling"
    bottom: "conv5"
    top: "pool5"
    pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
    }
    }
    layer {
    name: "fc6"
    type: "InnerProduct"
    bottom: "pool5"
    top: "fc6"
    param {
    lr_mult: 1
    decay_mult: 1
    }
    param {
    lr_mult: 2
    decay_mult: 0
    }
    inner_product_param {
    num_output: 4096
    weight_filler {
    type: "gaussian"
    std: 0.005
    }
    bias_filler {
    type: "constant"
    value: 1
    }
    }
    }
    layer {
    name: "relu6"
    type: "ReLU"
    bottom: "fc6"
    top: "fc6"
    }
    layer {
    name: "drop6"
    type: "Dropout"
    bottom: "fc6"
    top: "fc6"
    dropout_param {
    dropout_ratio: 0.5
    }
    }
    layer {
    name: "fc7"
    type: "InnerProduct"
    bottom: "fc6"
    top: "fc7"
    param {
    lr_mult: 1
    decay_mult: 1
    }
    param {
    lr_mult: 2
    decay_mult: 0
    }
    inner_product_param {
    num_output: 4096
    weight_filler {
    type: "gaussian"
    std: 0.005
    }
    bias_filler {
    type: "constant"
    value: 1
    }
    }
    }
    layer {
    name: "relu7"
    type: "ReLU"
    bottom: "fc7"
    top: "fc7"
    }
    layer {
    name: "drop7"
    type: "Dropout"
    bottom: "fc7"
    top: "fc7"
    dropout_param {
    dropout_ratio: 0.5
    }
    }
    layer {
    name: "fc8"
    type: "InnerProduct"
    bottom: "fc7"
    top: "fc8"
    param {
    lr_mult: 1
    decay_mult: 1
    }
    param {
    lr_mult: 2
    decay_mult: 0
    }
    inner_product_param {
    num_output: 1000
    weight_filler {
    type: "gaussian"
    std: 0.01
    }
    bias_filler {
    type: "constant"
    value: 0
    }
    }
    }
    layer {
    name: "accuracy"
    type: "Accuracy"
    bottom: "fc8"
    bottom: "label"
    top: "accuracy"
    include {
    phase: TEST
    }
    }
    layer {
    name: "loss"
    type: "SoftmaxWithLoss"
    bottom: "fc8"
    bottom: "label"
    top: "loss"
    }
    name: "CaffeNet"
    layer {
      name: "data"
      type: "Input"
      top: "data"
      input_param { shape: { dim: 10 dim: 3 dim: 227 dim: 227 } }
    }
    layer {
      name: "conv1"
      type: "Convolution"
      bottom: "data"
      top: "conv1"
      convolution_param {
        num_output: 96
        kernel_size: 11
        stride: 4
      }
    }
    layer {
      name: "relu1"
      type: "ReLU"
      bottom: "conv1"
      top: "conv1"
    }
    layer {
      name: "pool1"
      type: "Pooling"
      bottom: "conv1"
      top: "pool1"
      pooling_param {
        pool: MAX
        kernel_size: 3
        stride: 2
      }
    }
    layer {
      name: "norm1"
      type: "LRN"
      bottom: "pool1"
      top: "norm1"
      lrn_param {
        local_size: 5
        alpha: 0.0001
        beta: 0.75
      }
    }
    layer {
      name: "conv2"
      type: "Convolution"
      bottom: "norm1"
      top: "conv2"
      convolution_param {
        num_output: 256
        pad: 2
        kernel_size: 5
        group: 2
      }
    }
    layer {
      name: "relu2"
      type: "ReLU"
      bottom: "conv2"
      top: "conv2"
    }
    layer {
      name: "pool2"
      type: "Pooling"
      bottom: "conv2"
      top: "pool2"
      pooling_param {
        pool: MAX
        kernel_size: 3
        stride: 2
      }
    }
    layer {
      name: "norm2"
      type: "LRN"
      bottom: "pool2"
      top: "norm2"
      lrn_param {
        local_size: 5
        alpha: 0.0001
        beta: 0.75
      }
    }
    layer {
      name: "conv3"
      type: "Convolution"
      bottom: "norm2"
      top: "conv3"
      convolution_param {
        num_output: 384
        pad: 1
        kernel_size: 3
      }
    }
    layer {
      name: "relu3"
      type: "ReLU"
      bottom: "conv3"
      top: "conv3"
    }
    layer {
      name: "conv4"
      type: "Convolution"
      bottom: "conv3"
      top: "conv4"
      convolution_param {
        num_output: 384
        pad: 1
        kernel_size: 3
        group: 2
      }
    }
    layer {
      name: "relu4"
      type: "ReLU"
      bottom: "conv4"
      top: "conv4"
    }
    layer {
      name: "conv5"
      type: "Convolution"
      bottom: "conv4"
      top: "conv5"
      convolution_param {
        num_output: 256
        pad: 1
        kernel_size: 3
        group: 2
      }
    }
    layer {
      name: "relu5"
      type: "ReLU"
      bottom: "conv5"
      top: "conv5"
    }
    layer {
      name: "pool5"
      type: "Pooling"
      bottom: "conv5"
      top: "pool5"
      pooling_param {
        pool: MAX
        kernel_size: 3
        stride: 2
      }
    }
    layer {
      name: "fc6"
      type: "InnerProduct"
      bottom: "pool5"
      top: "fc6"
      inner_product_param {
        num_output: 4096
      }
    }
    layer {
      name: "relu6"
      type: "ReLU"
      bottom: "fc6"
      top: "fc6"
    }
    layer {
      name: "drop6"
      type: "Dropout"
      bottom: "fc6"
      top: "fc6"
      dropout_param {
        dropout_ratio: 0.5
      }
    }
    layer {
      name: "fc7"
      type: "InnerProduct"
      bottom: "fc6"
      top: "fc7"
      inner_product_param {
        num_output: 4096
      }
    }
    layer {
      name: "relu7"
      type: "ReLU"
      bottom: "fc7"
      top: "fc7"
    }
    layer {
      name: "drop7"
      type: "Dropout"
      bottom: "fc7"
      top: "fc7"
      dropout_param {
        dropout_ratio: 0.5
      }
    }
    layer {
      name: "fc8"
      type: "InnerProduct"
      bottom: "fc7"
      top: "fc8"
      inner_product_param {
        num_output: 1000
      }
    }
    layer {
      name: "prob"
      type: "Softmax"
      bottom: "fc8"
      top: "prob"
    }
  • 相关阅读:
    python移动文件
    python分割多个分隔符
    pywintypes.com_error: (-2147418111, '被呼叫方拒绝接收呼叫。', None, None)
    MySQL查看和修改字符集的方法
    Django创建超级管理员用户
    P2567.[SCOI2009] windy 数(数位DP)
    920G.List of Integers(莫比乌斯函数+二分)
    916E.Jamie and Tree (倍增LCA+线段树维护DFS序)
    GYM100376F.Circle and Trees(树形DP+倍增LCA)
    GYM100376E.LinearMapReduce(线段树维护矩阵乘法)
  • 原文地址:https://www.cnblogs.com/guohaoyu110/p/7487116.html
Copyright © 2011-2022 走看看