Caffe深度学习入门（5）—— caffenet 微调网络 训练自己的数据并测试训练的模型

微调网络，通常我们有一个初始化的模型参数文件，这里是不同于training from scratch，scrachtch指的是我们训练一个新的网络，在训练过程中，这些参数都被随机初始化，而fine-tuning，是我们可以在ImageNet上1000类分类训练好的参数的基础上，根据我们的分类识别任务进行特定的微调

这里我以一个车的识别为例，假设我们有1种车需要识别，我的任务对象是车，现在有ImageNet的模型参数文件，在这里使用的网络模型是CaffeNet，是一个小型的网络，其实别的网络如GoogleNet也是一样的原理。那么这个任务的变化可以表示为：

任务：分类 类别数目：1000（ImageNet上1000类的分类任务）------> 1(自己的特定数据集的分类任务车)

那么在网络的微调中，我们的整个流程分为以下几步：

1. 依然是准备好我们的训练数据和测试数据
2. 计算数据集的均值文件，因为集中特定领域的图像均值文件会跟ImageNet上比较General的数据的均值不太一样
3. 修改网络最后一层的输出类别，并且需要加快最后一层的参数学习速率
4. 调整Solver的配置参数，通常学习速率和步长，迭代次数都要适当减少
5. 启动训练，并且需要加载pretrained模型的参数

1.准备数据集
这一点就不用说了，准备两个txt文件，放成list的形式，可以参考caffe下的example，图像路径之后一个空格之后跟着类别的ID，如下，这里记住ID必须从0开始，要连续，否则会出错，loss不下降，按照要求写就OK。
这个是训练的图像label，测试的也同理

1. 创建lmdb文件，使用caffe下的convert_imageset 工具，具体命令如下：

./build/tools/convert_imageset /media/***/801328a5-39c6-4e08-b070-19fc662a5236/resnet/caffe/data/cartest/  data/cartest/carlist.txt data/cartest/train_car_lmdb -resize_width=227 -resize_height=227 -check_size -shuffle true

其中第一个参数是基地址路径用来拼接的，第二个是label的文件，第三个是生成的数据库文件支持leveldb或者lmdb，接着是resize的大小，最后是否随机图片顺序

计算均值，使用caffe下的convert_imageset 工具，具体命令

./build/tools/compute_image_mean /media/***/801328a5-39c6-4e08-b070-19fc662a5236/resnet/caffe/data/cartest/train_car_lmdb/ data/carmean.binaryproto

第一个参数是基地址路径用来拼接的，第二个是lmdb文件，第三个是生成的均值文件carmean.binaryproto

3.调整网络层参数
参照Caffe上的例程，我用的是CaffeNet，首先在输入层data层，修改我们的source 和 meanfile， 根据之前生成的lmdb 和mean.binaryproto修改即可。

最后输出层是fc8，

1.首先修改名字，这样预训练模型赋值的时候这里就会因为名字不匹配从而重新训练，也就达成了我们适应新任务的目的。
2.调整学习速率，因为最后一层是重新学习，因此需要有更快的学习速率相比较其他层，因此我们将，weight和bias的学习速率加快10倍。

修改./models/bvlc_reference_caffenet/train_cal_resnet_lily.prototxt中 train和test对应的相关路径

mean_file: "/media/***/801328a5-39c6-4e08-b070-19fc662a5236/resnet/caffe/data/cartest/carmean.binaryproto
source: "/media/***/801328a5-39c6-4e08-b070-19fc662a5236/resnet/caffe/data/cartest/train_car_lmdb"

修改./models/bvlc_reference_caffenet/solver_resnet_lily.prototxt

net: "models/bvlc_reference_caffenet/train_val_resnet_lily.prototxt"
test_iter: 100
test_interval: 1000
base_lr: 0.001
lr_policy: "step"
gamma: 0.1
stepsize: 20000
display: 20
max_iter: 50000
momentum: 0.9
weight_decay: 0.0005
snapshot: 10000
snapshot_prefix: "models/bvlc_reference_caffenet/caffenet_resnet_model_lily"
solver_mode: GPU

原来是fc8，记得把跟fc8连接的名字都要修改掉，修改修改./models/bvlc_reference_caffenet/train_val_resnet_lily.prototxt 后如下

layer {
  name: "fc8_comp_model"
  type: "InnerProduct"
  bottom: "fc7"
  top: "fc8_comp_model"
  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_comp_model"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "fc8_comp_model"
  bottom: "label"
  top: "loss"
}

主要的调整有：test_iter从1000改为了100，因为数据量减少了，base_lr从0.01变成了0.001，这个很重要，微调时的基本学习速率不能太大，学习策略没有改变，步长从原来的100000变成了20000，最大的迭代次数也从450000变成了50000，动量和权重衰减项都没有修改，依然是GPU模型，网络模型文件和快照的路径根据自己修改

train_val_resnet_lily.prototxt完整文件为：

name: "CaffeNet"
layer {
  name: "data"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mirror: true
    crop_size: 227
    mean_file: "/media/***/801328a5-39c6-4e08-b070-19fc662a5236/resnet/caffe/data/cartest/carmean.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: "/media/***/801328a5-39c6-4e08-b070-19fc662a5236/resnet/caffe/data/cartest/train_car_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: "/media/***/801328a5-39c6-4e08-b070-19fc662a5236/resnet/caffe/data/cartest/carmean.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: "/media/***/801328a5-39c6-4e08-b070-19fc662a5236/resnet/caffe/data/cartest/train_car_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_comp_model"
  type: "InnerProduct"
  bottom: "fc7"
  top: "fc8_comp_model"
  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_comp_model"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "fc8_comp_model"
  bottom: "label"
  top: "loss"
}


训练的指令如下：
./build/tools/caffe train --solver ./models/bvlc_reference_caffenet/solver_resnet_lily.prototxt --weights ./models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel --gpu 0

测试指令：

python ./python/classify02.py --model_def ./models/bvlc_reference_caffenet/train_val_test_resnet_lily.prototxt --pretrained_model ./models/bvlc_reference_caffenet/caffenet_resnet_model_lily_iter_50000.caffemodel --labels_file ./data/cartest/cartest.txt --center_only ./data/cartest/JPEGImages/crk201706301341.jpg foo

注意这里的train_val_test_resnet_lily.prototxt文件与训练时的文件train_val_resnet_lily.prototxt文件是不一样的。

train_val_resnet_lily.prototxt文件为：

name: "train_resnet_lily"

layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param { shape: { dim: 1 dim: 3 dim: 227 dim: 227 } }
}

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
    }
}
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
    
  }
}
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
  
    }
}
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_comp_model"
  type: "InnerProduct"
  bottom: "fc7"
  top: "fc8_comp_model"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 1000
    
  }
}
layer {
  name: "prob"
  type: "Softmax"
  bottom: "fc8_comp_model"
  top: "prob"
}

报错及解决方案

在最后一步测试的时候运行报错

报错：

File "python/classify.py", line 138, in 
    main(sys.argv)
  File "python/classify.py", line 110, in main
    channel_swap=channel_swap)
  File "/media/futurus/801328a5-39c6-4e08-b070-19fc662a5236/resnet/caffe/python/caffe/classifier.py", line 29, in __init__
    in_ = self.inputs[0]
IndexError: list index out of range

参考解决方案;
加入：

net: "train_resnet_lily"
input: "data"
input_shape {
  dim: 10
  dim: 3
  dim: 224
  dim: 224
}

加入之后 又报了其他错误：

[libprotobuf ERROR google/protobuf/text_format.cc:274] Error parsing text-format caffe.NetParameter: 1:4: Message type "caffe.NetParameter" has no field named "net".
F0125 11:48:14.708683 42586 upgrade_proto.cpp:88] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: ./models/bvlc_reference_caffenet/train_val_test_resnet_lily.prototxt
*** Check failure stack trace: ***
Aborted (core dumped)

根据网友的博客修改加入为

net: "train_resnet_lily"
input: "data"
input_dim: 10
input_dim: 3
input_dim: 224
input_dim: 224

测试还不不行，还是报错。

最终解决方案如下,运行通过。加入

name: "train_resnet_lily"
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param { shape: { dim: 1 dim: 3 dim: 227 dim: 227 } }
}

Reference:

https://www.cnblogs.com/louyihang-loves-baiyan/p/5038758.html
http://blog.csdn.net/sunshine_in_moon/article/details/49472901