【caffe】caffenet在windows下训练以及遇到的一系列问题——【caffe学习二】

继上篇http://blog.csdn.net/qq_15947787/article/details/78351390成功编译GPU版caffe后，尝试训练自己的样本。

以下整个工程可以下载，由于上传大小限制，分成了两部分上传：

http://download.csdn.net/download/qq_15947787/10051096

http://download.csdn.net/download/qq_15947787/10051099

1.新建文件夹caffe-train，将之前编译好的D:\caffe\scripts\build\tools\Release文件复制到caffe-train文件夹下，重命名为tools

2.将D:\caffe\models文件夹复制到caffe-train下。

3.制作样本，在caffe-train下新建data文件夹，放入制作好的样本及标签文件。一共5类，训练集每类80张图，测试集每类20张图。样本下载链接 http://download.csdn.net/download/qq_15947787/10050928

4.复制D:\caffe\examples\imagenet下create_imagenet.sh，make_imagenet_mean.sh，train_caffenet.sh到caffe-train下。

5.修改create_imagenet.sh内容：

完整的create_imagenet.sh内容为：

#!/usr/bin/env sh# Create the imagenet lmdb inputs# N.B. set the path to the imagenet train + val data dirsset -eEXAMPLE=dataDATA=dataTOOLS=toolsTRAIN_DATA_ROOT=data/train/VAL_DATA_ROOT=data/val/# Set RESIZE=true to resize the images to 256x256. Leave as false if images have# already been resized using another tool.RESIZE=trueif $RESIZE; then  RESIZE_HEIGHT=256  RESIZE_WIDTH=256else  RESIZE_HEIGHT=0  RESIZE_WIDTH=0fiif [ ! -d "$TRAIN_DATA_ROOT" ]; then  echo "Error: TRAIN_DATA_ROOT is not a path to a directory: $TRAIN_DATA_ROOT"  echo "Set the TRAIN_DATA_ROOT variable in create_imagenet.sh to the path" \       "where the ImageNet training data is stored."  exit 1fiif [ ! -d "$VAL_DATA_ROOT" ]; then  echo "Error: VAL_DATA_ROOT is not a path to a directory: $VAL_DATA_ROOT"  echo "Set the VAL_DATA_ROOT variable in create_imagenet.sh to the path" \       "where the ImageNet validation data is stored."  exit 1fiecho "Creating train lmdb..."GLOG_logtostderr=1 $TOOLS/convert_imageset \    --resize_height=$RESIZE_HEIGHT \    --resize_width=$RESIZE_WIDTH \    --shuffle \    $TRAIN_DATA_ROOT \    $DATA/train.txt \    $EXAMPLE/img_train_lmdbecho "Creating val lmdb..."GLOG_logtostderr=1 $TOOLS/convert_imageset \    --resize_height=$RESIZE_HEIGHT \    --resize_width=$RESIZE_WIDTH \    --shuffle \    $VAL_DATA_ROOT \    $DATA/val.txt \    $EXAMPLE/img_val_lmdbecho "Done."read

6.运行create_imagenet.sh，在data下生成img_train_lmdb以及img_val_lmdb，运行过程中可能遇到问题1。

7.修改make_imagenet_mean.sh内容：

#!/usr/bin/env sh# Compute the mean image from the imagenet training lmdb# N.B. this is available in data/ilsvrc12EXAMPLE=dataDATA=dataTOOLS=tools$TOOLS/compute_image_mean $EXAMPLE/img_train_lmdb \  $DATA/imagenet_mean.binaryprotoecho "Done."read

8.运行make_imagenet_mean.sh，在data下生成imagenet_mean.binaryproto

9.修改D:\caffe-train\models\bvlc_reference_caffenet下

solver.prototxt内容：

net: "D:/caffe-train/models/bvlc_reference_caffenet/train_val.prototxt"test_iter: 20test_interval: 100base_lr: 0.01lr_policy: "step"gamma: 0.1stepsize: 100display: 20max_iter: 1000momentum: 0.9weight_decay: 0.0005snapshot: 500snapshot_prefix: "D:/caffe-train/models/bvlc_reference_caffenet"solver_mode: GPU

train_val.prototxt内容：

mean_file以及source文件绝对路径，batch_size，fc8层num_output:5

name: "CaffeNet"layer {  name: "data"  type: "Data"  top: "data"  top: "label"  include {    phase: TRAIN  }  transform_param {    mirror: true    crop_size: 227    mean_file: "D:/caffe-train/data/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: "D:/caffe-train/data/img_train_lmdb"    batch_size: 128    backend: LMDB  }}layer {  name: "data"  type: "Data"  top: "data"  top: "label"  include {    phase: TEST  }  transform_param {    mirror: false    crop_size: 227    mean_file: "D:/caffe-train/data/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: "D:/caffe-train/data/img_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: 5    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"}

10.修改train_caffenet.sh内容：

#!/usr/bin/env shset -eD:/caffe-train/tools/caffe.exe train \    --solver=D:/caffe-train/models/bvlc_reference_caffenet/solver.prototxt $@

11.运行train_caffenet.sh

备注，运行train_caffenet.sh感觉一卡一卡的，不如cmd来的痛快

在caffe-train打开cmd，输入指令：

tools\caffe.exe train --solver=D:\caffe-train\models\bvlc_reference_caffenet\solver.prototxt

———————————————————————————————————————————————————

问题1：运行create_imagenet.sh时，System entropy source not available, using fallback algorithm to generate seed instead. 然后后面一系列Could not open or find file xxx/xxx/xxx。具体如下图所示：

解决方法：在create_imagenet.sh中检查路径并没有错误，但是提示找不到图片，所以打开相应的train.txt以及val.txt 标签文件，选择文件—另存为—编码ANSI—保存。即可解决上述问题。另存为编码UNICODE上述问题就会出现。