码迷,mamicode.com
首页 > 其他好文 > 详细

deep learning实践经验总结2--准确率再次提升,到达0.8,再来总结一下

时间:2014-06-22 20:16:47      阅读:212      评论:0      收藏:0      [点我收藏+]

标签:deep learning   机器学习   caffe   图像处理   

deep learning实践经验总结2


最近拿caffe来做图片分类,遇到不少问题,同时也吸取不少教训和获得不少经验。



这次拿大摆裙和一步裙做分类,

多次训练效果一直在0.7,后来改动了全链接层的初始化参数。高斯分布的标准差由0.001改为0.0001,就是调小了。

然后效果很明显,准确率高了,权重图画出来后,也看得出是有意义的了,部分权重图是人的轮廓或者裙子的轮廓。


先看看图片:

大摆裙

bubuko.com,布布扣  bubuko.com,布布扣  bubuko.com,布布扣


一步裙

bubuko.com,布布扣  bubuko.com,布布扣  bubuko.com,布布扣


然后找一些响应图看一下,当然我这里展示的是一些效果好的响应图。

大摆裙

bubuko.com,布布扣  bubuko.com,布布扣   bubuko.com,布布扣

一步裙

bubuko.com,布布扣  bubuko.com,布布扣   bubuko.com,布布扣


一些权重图:

bubuko.com,布布扣  bubuko.com,布布扣  bubuko.com,布布扣


bubuko.com,布布扣  bubuko.com,布布扣  bubuko.com,布布扣

bubuko.com,布布扣  bubuko.com,布布扣  bubuko.com,布布扣


这是网络的结构参数:

name: "CIFAR10_full_train"
layers {
 layer {
   name: "cifar"
   type: "data"
   #source: "/home/linger/linger/testfile/crop_train_db"
   #source: "/home/linger/linger/testfile/collar_train_db"
   source: "/home/linger/linger/testfile/skirt_train_db"
   #source: "/home/linger/linger/testfile/pattern_train_db"
   meanfile: "/home/linger/linger/testfile/skirt_train_mean.binaryproto"
   #cropsize: 200
   batchsize: 20
 }
 top: "data"
 top: "label"
}

layers {
  layer {
    name: "conv1"
    type: "conv"
    num_output: 16
    kernelsize: 5
    stride:1 
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0.
    }
    blobs_lr: 1.
    blobs_lr: 1.
    weight_decay: 0.001
    weight_decay: 0.
  }
  bottom: "data"
  top: "conv1"
}
layers {
  layer {
    name: "relu1"
    type: "relu"
  }
  bottom: "conv1"
  top: "conv1"
}
layers {
  layer {
    name: "pool1"
    type: "pool"
    pool: MAX
    kernelsize: 2
    stride:1 
  }
  bottom: "conv1"
  top: "pool1"
}
layers {
  layer {
    name: "conv2"
    type: "conv"
    num_output: 16
    group: 2
    kernelsize: 5
    stride:1 
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0.
    }
    blobs_lr: 1.
    blobs_lr: 1.
    weight_decay: 0.001
    weight_decay: 0.
  }
  bottom: "pool1"
  top: "conv2"
}
layers {
  layer {
    name: "relu2"
    type: "relu"
  }
  bottom: "conv2"
  top: "conv2"
}
layers {
  layer {
    name: "pool2"
    type: "pool"
    pool: MAX
    kernelsize: 2
    stride: 1
  }
  bottom: "conv2"
  top: "pool2"
}

layers {
  layer {
    name: "ip1"
    type: "innerproduct"
    num_output: 100
    weight_filler {
      type: "gaussian"
      std: 0.0001
    }
    bias_filler {
      type: "constant"
      value: 0.
    }
    blobs_lr: 1.
    blobs_lr: 1.
    weight_decay: 0.001
    weight_decay: 0.
  }
  bottom: "pool2"
  top: "ip1"
}

layers {
  layer {
    name: "ip2"
    type: "innerproduct"
    num_output: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0.
    }
    blobs_lr: 1.
    blobs_lr: 1.
    weight_decay: 0.001
    weight_decay: 0.
  }
  bottom: "ip1"
  top: "ip2"
}

#-----------------------output------------------------
layers {
 layer {
   name: "loss"
   type: "softmax_loss"
 }
 bottom: "ip2"
 bottom: "label"
}



name: "CIFAR10_full_test"
layers {
 layer {
   name: "cifar"
   type: "data"
   #source: "/home/linger/linger/testfile/collar_test_db"
   #source: "/home/linger/linger/testfile/crop_test_db"
   source: "/home/linger/linger/testfile/skirt_test_db"
   #source: "/home/linger/linger/testfile/pattern_test_db"
   meanfile: "/home/linger/linger/testfile/skirt_test_mean.binaryproto"
   #cropsize: 200
   batchsize: 10
 }
 top: "data"
 top: "label"
}

layers {
  layer {
    name: "conv1"
    type: "conv"
    num_output: 16
    kernelsize: 5
    stride:1 
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0.
    }
    blobs_lr: 1.
    blobs_lr: 1.
    weight_decay: 0.001
    weight_decay: 0.
  }
  bottom: "data"
  top: "conv1"
}
layers {
  layer {
    name: "relu1"
    type: "relu"
  }
  bottom: "conv1"
  top: "conv1"
}
layers {
  layer {
    name: "pool1"
    type: "pool"
    pool: MAX
    kernelsize: 2
    stride:1 
  }
  bottom: "conv1"
  top: "pool1"
}
layers {
  layer {
    name: "conv2"
    type: "conv"
    num_output: 16
    group: 2
    kernelsize: 5
    stride:1 
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0.
    }
    blobs_lr: 1.
    blobs_lr: 1.
    weight_decay: 0.001
    weight_decay: 0.
  }
  bottom: "pool1"
  top: "conv2"
}
layers {
  layer {
    name: "relu2"
    type: "relu"
  }
  bottom: "conv2"
  top: "conv2"
}
layers {
  layer {
    name: "pool2"
    type: "pool"
    pool: MAX
    kernelsize: 2
    stride: 1
  }
  bottom: "conv2"
  top: "pool2"
}
layers {
  layer {
    name: "ip1"
    type: "innerproduct"
    num_output: 100
    weight_filler {
      type: "gaussian"
      std: 0.0001
    }
    bias_filler {
      type: "constant"
      value: 0.
    }
    blobs_lr: 1.
    blobs_lr: 1.
    weight_decay: 0.001
    weight_decay: 0.
  }
  bottom: "pool2"
  top: "ip1"
}

layers {
  layer {
    name: "ip2"
    type: "innerproduct"
    num_output: 2
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0.
    }
    blobs_lr: 1.
    blobs_lr: 1.
    weight_decay: 0.001
    weight_decay: 0.
  }
  bottom: "ip1"
  top: "ip2"
}

#-----------------------output------------------------
layers {
 layer {
   name: "prob"
   type: "softmax"
 }
 bottom: "ip2"
 top: "prob"
}
layers {
  layer {
    name: "accuracy"
    type: "accuracy"
  }
  bottom: "prob"
  bottom: "label"
  top: "accuracy"
}


# reduce learning rate after 120 epochs (60000 iters) by factor 0f 10
# then another factor of 10 after 10 more epochs (5000 iters)

# The training protocol buffer definition
train_net: "cifar10_full_train.prototxt"
# The testing protocol buffer definition
test_net: "cifar10_full_test.prototxt"
# test_iter specifies how many forward passes the test should carry out.
# In the case of CIFAR10, we have test batch size 100 and 100 test iterations,
# covering the full 10,000 testing images.
test_iter: 20
# Carry out testing every 1000 training iterations.
test_interval: 100
# The base learning rate, momentum and the weight decay of the network.
base_lr: 0.00001
momentum: 0.9
weight_decay: 0.004
# The learning rate policy
lr_policy: "fixed"
# Display every 200 iterations
display: 20
# The maximum number of iterations
max_iter: 60000
# snapshot intermediate results
snapshot: 1000
snapshot_prefix: "cifar10_full"
# solver mode: 0 for CPU and 1 for GPU
solver_mode: 1


真的是多玩数据,才会对数据形成一种感觉啊。

下次玩3类的。敬请期待!





deep learning实践经验总结2--准确率再次提升,到达0.8,再来总结一下,布布扣,bubuko.com

deep learning实践经验总结2--准确率再次提升,到达0.8,再来总结一下

标签:deep learning   机器学习   caffe   图像处理   

原文地址:http://blog.csdn.net/lingerlanlan/article/details/32329761

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!