caffe基础-14cifar10数据集的训练

最新推荐文章于 2024-08-03 10:47:10 发布
最新推荐文章于 2024-08-03 10:47:10 发布
阅读量782 收藏
点赞数
文章标签： cifar10
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/Terrenceyuu/article/details/78075150
版权

准备数据集

  • cifar10的数据集介绍见官网：https://www.cs.toronto.edu/~kriz/cifar.html
  • 它是个小的数据集，有10个类。每张图片的size是33*32*3，一共有60000张图片。
  • 我们可以在官网下载其二进制的版本，放到~/caffe/data/cifar10文件夹下。
  • 执行脚本：get_cifar10.sh，其内容如下，要注意注释掉wget
    命令（因为已经下载过了）。
#!/usr/bin/env sh
# This scripts downloads the CIFAR10 (binary version) data and unzips it.

DIR="$( cd "$(dirname "$0")" ; pwd -P )"
cd "$DIR"

echo "Downloading..."

#wget --no-check-certificate http://www.cs.toronto.edu/~kriz/cifar-10-binary.tar.gz

echo "Unzipping..."

tar -xf cifar-10-binary.tar.gz && rm -f cifar-10-binary.tar.gz
mv cifar-10-batches-bin/* . && rm -rf cifar-10-batches-bin

# Creation is split out because leveldb sometimes causes segfault
# and needs to be re-created.

echo "Done."
  • 这样在该文件夹下就多了一些bin文件了。

这里写图片描述

制作lmdb数据源

  • 制作数据源的命令已经提供，在~/caffe/examples/cifar10有个create_cifar10.sh文件：
#!/usr/bin/env sh
# This script converts the cifar data into leveldb format.
set -e

EXAMPLE=/home/terrence/caffe/examples/cifar10
DATA=/home/terrence/caffe/data/cifar10
DBTYPE=lmdb

echo "Creating $DBTYPE..."

rm -rf $EXAMPLE/cifar10_train_$DBTYPE $EXAMPLE/cifar10_test_$DBTYPE

/home/terrence/caffe/build/examples/cifar10/convert_cifar_data.bin $DATA $EXAMPLE $DBTYPE

echo "Computing image mean..."

/home/terrence/caffe/build/tools/compute_image_mean -backend=$DBTYPE \
  $EXAMPLE/cifar10_train_$DBTYPE $EXAMPLE/mean.binaryproto

echo "Done."
  • 可见，已经做了去均值的操作了。
  • 执行指令后，文件夹下多出了两个lmdb文件：
    这里写图片描述

训练数据

  • ~/caffe/examples/cifar10/ 文件夹下有快速训练指令，打开文件: train_quick.sh
#!/usr/bin/env sh
set -e

TOOLS=./build/tools

$TOOLS/caffe train \
  --solver=examples/cifar10/cifar10_quick_solver.prototxt $@

# reduce learning rate by factor of 10 after 8 epochs
$TOOLS/caffe train \
  --solver=examples/cifar10/cifar10_quick_solver_lr1.prototxt \
  --snapshot=examples/cifar10/cifar10_quick_iter_4000.solverstate $@
  • 找到 cifar10_quick_solver.prototxt文件，其内容如下：
# reduce the learning rate after 8 epochs (4000 iters) by a factor of 10

# The train/test net protocol buffer definition
net: "examples/cifar10/cifar10_quick_train_test.prototxt"
# test_iter specifies how many forward passes the test should carry out.
# In the case of MNIST, we have test batch size 100 and 100 test iterations,
# covering the full 10,000 testing images.
test_iter: 100
# Carry out testing every 500 training iterations.
test_interval: 500
# The base learning rate, momentum and the weight decay of the network.
base_lr: 0.001
momentum: 0.9
weight_decay: 0.004
# The learning rate policy
lr_policy: "fixed"
# Display every 100 iterations
display: 100
# The maximum number of iterations
max_iter: 4000
# snapshot intermediate results
snapshot: 4000
snapshot_prefix: "examples/cifar10/cifar10_quick"
# solver mode: CPU or GPU
solver_mode: GPU
  • 接下来打开其模型描述文件examples/cifar10/cifar10_quick_train_test.prototxt
name: "CIFAR10_quick"
layer {
  name: "cifar"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mean_file: "examples/cifar10/mean.binaryproto"
  }
  data_param {
    source: "examples/cifar10/cifar10_train_lmdb"
    batch_size: 100
    backend: LMDB
  }
}
layer {
  name: "cifar"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param {
    mean_file: "examples/cifar10/mean.binaryproto"
  }
  data_param {
    source: "examples/cifar10/cifar10_test_lmdb"
    batch_size: 100
    backend: LMDB
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 32
    pad: 2
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "gaussian"
      std: 0.0001
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "pool1"
  top: "pool1"
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 32
    pad: 2
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu2"
  type: "ReLU"
  bottom: "conv2"
  top: "conv2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: AVE
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 64
    pad: 2
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu3"
  type: "ReLU"
  bottom: "conv3"
  top: "conv3"
}
layer {
  name: "pool3"
  type: "Pooling"
  bottom: "conv3"
  top: "pool3"
  pooling_param {
    pool: AVE
    kernel_size: 3
    stride: 2
  }
}
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool3"
  top: "ip1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 64
    weight_filler {
      type: "gaussian"
      std: 0.1
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "ip2"
  type: "InnerProduct"
  bottom: "ip1"
  top: "ip2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 10
    weight_filler {
      type: "gaussian"
      std: 0.1
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "accuracy"
  type: "Accuracy"
  bottom: "ip2"
  bottom: "label"
  top: "accuracy"
  include {
    phase: TEST
  }
}
layer {
  name: "loss"
  type: "SoftmaxWithLoss"
  bottom: "ip2"
  bottom: "label"
  top: "loss"
}
  • 具体关于这个模型的介绍我会在后面的文章做一个总结，这里就不再多说。

  • 最后，转到caffe根目录，运行超参数文件：sudo time sh examples/cifar10/train_quick.sh 即可训练数据。

  • 训练完成，log打印如下：

I0924 10:33:24.523983  3531 layer_factory.hpp:77] Creating layer cifar
I0924 10:33:24.524039  3531 db_lmdb.cpp:35] Opened lmdb examples/cifar10/cifar10_test_lmdb
I0924 10:33:24.524055  3531 net.cpp:84] Creating Layer cifar
I0924 10:33:24.524075  3531 net.cpp:380] cifar -> data
I0924 10:33:24.524097  3531 net.cpp:380] cifar -> label
I0924 10:33:24.524119  3531 data_transformer.cpp:25] Loading mean file from: examples/cifar10/mean.binaryproto
I0924 10:33:24.524245  3531 data_layer.cpp:45] output data size: 100,3,32,32
I0924 10:33:24.527096  3531 net.cpp:122] Setting up cifar
I0924 10:33:24.527137  3531 net.cpp:129] Top shape: 100 3 32 32 (307200)
I0924 10:33:24.527156  3531 net.cpp:129] Top shape: 100 (100)
I0924 10:33:24.527161  3531 net.cpp:137] Memory required for data: 1229200
I0924 10:33:24.527168  3531 layer_factory.hpp:77] Creating layer label_cifar_1_split
I0924 10:33:24.527191  3531 net.cpp:84] Creating Layer label_cifar_1_split
I0924 10:33:24.527212  3531 net.cpp:406] label_cifar_1_split <- label
I0924 10:33:24.527220  3531 net.cpp:380] label_cifar_1_split -> label_cifar_1_split_0
I0924 10:33:24.527242  3531 net.cpp:380] label_cifar_1_split -> label_cifar_1_split_1
I0924 10:33:24.527304  3531 net.cpp:122] Setting up label_cifar_1_split
I0924 10:33:24.527313  3531 net.cpp:129] Top shape: 100 (100)
I0924 10:33:24.527318  3531 net.cpp:129] Top shape: 100 (100)
I0924 10:33:24.527323  3531 net.cpp:137] Memory required for data: 1230000
I0924 10:33:24.527341  3531 layer_factory.hpp:77] Creating layer conv1
I0924 10:33:24.527353  3531 net.cpp:84] Creating Layer conv1
I0924 10:33:24.527371  3531 net.cpp:406] conv1 <- data
I0924 10:33:24.527379  3531 net.cpp:380] conv1 -> conv1
I0924 10:33:24.527643  3531 net.cpp:122] Setting up conv1
I0924 10:33:24.527654  3531 net.cpp:129] Top shape: 100 32 32 32 (3276800)
I0924 10:33:24.527660  3531 net.cpp:137] Memory required for data: 14337200
I0924 10:33:24.527671  3531 layer_factory.hpp:77] Creating layer pool1
I0924 10:33:24.527681  3531 net.cpp:84] Creating Layer pool1
I0924 10:33:24.527688  3531 net.cpp:406] pool1 <- conv1
I0924 10:33:24.527720  3531 net.cpp:380] pool1 -> pool1
I0924 10:33:24.527752  3531 net.cpp:122] Setting up pool1
I0924 10:33:24.527761  3531 net.cpp:129] Top shape: 100 32 16 16 (819200)
I0924 10:33:24.527766  3531 net.cpp:137] Memory required for data: 17614000
I0924 10:33:24.527772  3531 layer_factory.hpp:77] Creating layer relu1
I0924 10:33:24.527779  3531 net.cpp:84] Creating Layer relu1
I0924 10:33:24.527786  3531 net.cpp:406] relu1 <- pool1
I0924 10:33:24.527792  3531 net.cpp:367] relu1 -> pool1 (in-place)
I0924 10:33:24.527801  3531 net.cpp:122] Setting up relu1
I0924 10:33:24.527807  3531 net.cpp:129] Top shape: 100 32 16 16 (819200)
I0924 10:33:24.527813  3531 net.cpp:137] Memory required for data: 20890800
I0924 10:33:24.527819  3531 layer_factory.hpp:77] Creating layer conv2
I0924 10:33:24.527827  3531 net.cpp:84] Creating Layer conv2
I0924 10:33:24.527833  3531 net.cpp:406] conv2 <- pool1
I0924 10:33:24.527858  3531 net.cpp:380] conv2 -> conv2
I0924 10:33:24.528939  3531 net.cpp:122] Setting up conv2
I0924 10:33:24.528959  3531 net.cpp:129] Top shape: 100 32 16 16 (819200)
I0924 10:33:24.528966  3531 net.cpp:137] Memory required for data: 24167600
I0924 10:33:24.528976  3531 layer_factory.hpp:77] Creating layer relu2
I0924 10:33:24.528985  3531 net.cpp:84] Creating Layer relu2
I0924 10:33:24.528991  3531 net.cpp:406] relu2 <- conv2
I0924 10:33:24.529000  3531 net.cpp:367] relu2 -> conv2 (in-place)
I0924 10:33:24.529009  3531 net.cpp:122] Setting up relu2
I0924 10:33:24.529016  3531 net.cpp:129] Top shape: 100 32 16 16 (819200)
I0924 10:33:24.529022  3531 net.cpp:137] Memory required for data: 27444400
I0924 10:33:24.529028  3531 layer_factory.hpp:77] Creating layer pool2
I0924 10:33:24.529036  3531 net.cpp:84] Creating Layer pool2
I0924 10:33:24.529042  3531 net.cpp:406] pool2 <- conv2
I0924 10:33:24.529049  3531 net.cpp:380] pool2 -> pool2
I0924 10:33:24.529065  3531 net.cpp:122] Setting up pool2
I0924 10:33:24.529073  3531 net.cpp:129] Top shape: 100 32 8 8 (204800)
I0924 10:33:24.529079  3531 net.cpp:137] Memory required for data: 28263600
I0924 10:33:24.529084  3531 layer_factory.hpp:77] Creating layer conv3
I0924 10:33:24.529094  3531 net.cpp:84] Creating Layer conv3
I0924 10:33:24.529101  3531 net.cpp:406] conv3 <- pool2
I0924 10:33:24.529110  3531 net.cpp:380] conv3 -> conv3
I0924 10:33:24.530513  3531 net.cpp:122] Setting up conv3
I0924 10:33:24.530524  3531 net.cpp:129] Top shape: 100 64 8 8 (409600)
I0924 10:33:24.530529  3531 net.cpp:137] Memory required for data: 29902000
I0924 10:33:24.530544  3531 layer_factory.hpp:77] Creating layer relu3
I0924 10:33:24.530555  3531 net.cpp:84] Creating Layer relu3
I0924 10:33:24.530560  3531 net.cpp:406] relu3 <- conv3
I0924 10:33:24.530567  3531 net.cpp:367] relu3 -> conv3 (in-place)
I0924 10:33:24.530575  3531 net.cpp:122] Setting up relu3
I0924 10:33:24.530583  3531 net.cpp:129] Top shape: 100 64 8 8 (409600)
I0924 10:33:24.530589  3531 net.cpp:137] Memory required for data: 31540400
I0924 10:33:24.530596  3531 layer_factory.hpp:77] Creating layer pool3
I0924 10:33:24.530604  3531 net.cpp:84] Creating Layer pool3
I0924 10:33:24.530611  3531 net.cpp:406] pool3 <- conv3
I0924 10:33:24.530616  3531 net.cpp:380] pool3 -> pool3
I0924 10:33:24.530635  3531 net.cpp:122] Setting up pool3
I0924 10:33:24.530644  3531 net.cpp:129] Top shape: 100 64 4 4 (102400)
I0924 10:33:24.530649  3531 net.cpp:137] Memory required for data: 31950000
I0924 10:33:24.530655  3531 layer_factory.hpp:77] Creating layer ip1
I0924 10:33:24.530663  3531 net.cpp:84] Creating Layer ip1
I0924 10:33:24.530669  3531 net.cpp:406] ip1 <- pool3
I0924 10:33:24.530678  3531 net.cpp:380] ip1 -> ip1
I0924 10:33:24.532598  3531 net.cpp:122] Setting up ip1
I0924 10:33:24.532613  3531 net.cpp:129] Top shape: 100 64 (6400)
I0924 10:33:24.532618  3531 net.cpp:137] Memory required for data: 31975600
I0924 10:33:24.532627  3531 layer_factory.hpp:77] Creating layer ip2
I0924 10:33:24.532635  3531 net.cpp:84] Creating Layer ip2
I0924 10:33:24.532644  3531 net.cpp:406] ip2 <- ip1
I0924 10:33:24.532662  3531 net.cpp:380] ip2 -> ip2
I0924 10:33:24.532747  3531 net.cpp:122] Setting up ip2
I0924 10:33:24.532755  3531 net.cpp:129] Top shape: 100 10 (1000)
I0924 10:33:24.532762  3531 net.cpp:137] Memory required for data: 31979600
I0924 10:33:24.532770  3531 layer_factory.hpp:77] Creating layer ip2_ip2_0_split
I0924 10:33:24.532778  3531 net.cpp:84] Creating Layer ip2_ip2_0_split
I0924 10:33:24.532784  3531 net.cpp:406] ip2_ip2_0_split <- ip2
I0924 10:33:24.532790  3531 net.cpp:380] ip2_ip2_0_split -> ip2_ip2_0_split_0
I0924 10:33:24.532799  3531 net.cpp:380] ip2_ip2_0_split -> ip2_ip2_0_split_1
I0924 10:33:24.532826  3531 net.cpp:122] Setting up ip2_ip2_0_split
I0924 10:33:24.532835  3531 net.cpp:129] Top shape: 100 10 (1000)
I0924 10:33:24.532846  3531 net.cpp:129] Top shape: 100 10 (1000)
I0924 10:33:24.532852  3531 net.cpp:137] Memory required for data: 31987600
I0924 10:33:24.532858  3531 layer_factory.hpp:77] Creating layer accuracy
I0924 10:33:24.532881  3531 net.cpp:84] Creating Layer accuracy
I0924 10:33:24.532888  3531 net.cpp:406] accuracy <- ip2_ip2_0_split_0
I0924 10:33:24.532909  3531 net.cpp:406] accuracy <- label_cifar_1_split_0
I0924 10:33:24.532929  3531 net.cpp:380] accuracy -> accuracy
I0924 10:33:24.532938  3531 net.cpp:122] Setting up accuracy
I0924 10:33:24.532945  3531 net.cpp:129] Top shape: (1)
I0924 10:33:24.532951  3531 net.cpp:137] Memory required for data: 31987604
I0924 10:33:24.532956  3531 layer_factory.hpp:77] Creating layer loss
I0924 10:33:24.532964  3531 net.cpp:84] Creating Layer loss
I0924 10:33:24.532970  3531 net.cpp:406] loss <- ip2_ip2_0_split_1
I0924 10:33:24.532976  3531 net.cpp:406] loss <- label_cifar_1_split_1
I0924 10:33:24.532984  3531 net.cpp:380] loss -> loss
I0924 10:33:24.532992  3531 layer_factory.hpp:77] Creating layer loss
I0924 10:33:24.533048  3531 net.cpp:122] Setting up loss
I0924 10:33:24.533059  3531 net.cpp:129] Top shape: (1)
I0924 10:33:24.533066  3531 net.cpp:132]     with loss weight 1
I0924 10:33:24.533083  3531 net.cpp:137] Memory required for data: 31987608
I0924 10:33:24.533089  3531 net.cpp:198] loss needs backward computation.
I0924 10:33:24.533095  3531 net.cpp:200] accuracy does not need backward computation.
I0924 10:33:24.533103  3531 net.cpp:198] ip2_ip2_0_split needs backward computation.
I0924 10:33:24.533109  3531 net.cpp:198] ip2 needs backward computation.
I0924 10:33:24.533114  3531 net.cpp:198] ip1 needs backward computation.
I0924 10:33:24.533119  3531 net.cpp:198] pool3 needs backward computation.
I0924 10:33:24.533125  3531 net.cpp:198] relu3 needs backward computation.
I0924 10:33:24.533131  3531 net.cpp:198] conv3 needs backward computation.
I0924 10:33:24.533136  3531 net.cpp:198] pool2 needs backward computation.
I0924 10:33:24.533143  3531 net.cpp:198] relu2 needs backward computation.
I0924 10:33:24.533149  3531 net.cpp:198] conv2 needs backward computation.
I0924 10:33:24.533154  3531 net.cpp:198] relu1 needs backward computation.
I0924 10:33:24.533162  3531 net.cpp:198] pool1 needs backward computation.
I0924 10:33:24.533167  3531 net.cpp:198] conv1 needs backward computation.
I0924 10:33:24.533174  3531 net.cpp:200] label_cifar_1_split does not need backward computation.
I0924 10:33:24.533180  3531 net.cpp:200] cifar does not need backward computation.
I0924 10:33:24.533186  3531 net.cpp:242] This network produces output accuracy
I0924 10:33:24.533192  3531 net.cpp:242] This network produces output loss
I0924 10:33:24.533205  3531 net.cpp:255] Network initialization done.
I0924 10:33:24.533248  3531 solver.cpp:56] Solver scaffolding done.
I0924 10:33:24.533486  3531 caffe.cpp:242] Resuming from examples/cifar10/cifar10_quick_iter_4000.solverstate
I0924 10:33:24.534968  3531 sgd_solver.cpp:318] SGDSolver: restoring history
I0924 10:33:24.535162  3531 caffe.cpp:248] Starting Optimization
I0924 10:33:24.535171  3531 solver.cpp:272] Solving CIFAR10_quick
I0924 10:33:24.535177  3531 solver.cpp:273] Learning Rate Policy: fixed
I0924 10:33:24.535706  3531 solver.cpp:330] Iteration 4000, Testing net (#0)
I0924 10:33:26.685408  3536 data_layer.cpp:73] Restarting data prefetching from start.
I0924 10:33:26.773063  3531 solver.cpp:397]     Test net output #0: accuracy = 0.7168
I0924 10:33:26.773087  3531 solver.cpp:397]     Test net output #1: loss = 0.848362 (* 1 = 0.848362 loss)
I0924 10:33:26.831161  3531 solver.cpp:218] Iteration 4000 (1742.17 iter/s, 2.29599s/100 iters), loss = 0.583209
I0924 10:33:26.831185  3531 solver.cpp:237]     Train net output #0: loss = 0.583209 (* 1 = 0.583209 loss)
I0924 10:33:26.831209  3531 sgd_solver.cpp:105] Iteration 4000, lr = 0.0001
I0924 10:33:32.549178  3531 solver.cpp:218] Iteration 4100 (17.4885 iter/s, 5.71804s/100 iters), loss = 0.621489
I0924 10:33:32.549214  3531 solver.cpp:237]     Train net output #0: loss = 0.621489 (* 1 = 0.621489 loss)
I0924 10:33:32.549237  3531 sgd_solver.cpp:105] Iteration 4100, lr = 0.0001
I0924 10:33:38.263624  3531 solver.cpp:218] Iteration 4200 (17.4995 iter/s, 5.71446s/100 iters), loss = 0.511802
I0924 10:33:38.263659  3531 solver.cpp:237]     Train net output #0: loss = 0.511802 (* 1 = 0.511802 loss)
I0924 10:33:38.263682  3531 sgd_solver.cpp:105] Iteration 4200, lr = 0.0001
I0924 10:33:43.976765  3531 solver.cpp:218] Iteration 4300 (17.5035 iter/s, 5.71316s/100 iters), loss = 0.478999
I0924 10:33:43.976801  3531 solver.cpp:237]     Train net output #0: loss = 0.478999 (* 1 = 0.478999 loss)
I0924 10:33:43.976824  3531 sgd_solver.cpp:105] Iteration 4300, lr = 0.0001
I0924 10:33:49.691663  3531 solver.cpp:218] Iteration 4400 (17.4981 iter/s, 5.71491s/100 iters), loss = 0.53704
I0924 10:33:49.691699  3531 solver.cpp:237]     Train net output #0: loss = 0.53704 (* 1 = 0.53704 loss)
I0924 10:33:49.691722  3531 sgd_solver.cpp:105] Iteration 4400, lr = 0.0001
I0924 10:33:55.126360  3535 data_layer.cpp:73] Restarting data prefetching from start.
I0924 10:33:55.325109  3531 solver.cpp:330] Iteration 4500, Testing net (#0)
I0924 10:33:57.500412  3536 data_layer.cpp:73] Restarting data prefetching from start.
I0924 10:33:57.588099  3531 solver.cpp:397]     Test net output #0: accuracy = 0.7539
I0924 10:33:57.588124  3531 solver.cpp:397]     Test net output #1: loss = 0.759468 (* 1 = 0.759468 loss)
I0924 10:33:57.645143  3531 solver.cpp:218] Iteration 4500 (12.573 iter/s, 7.95352s/100 iters), loss = 0.504953
I0924 10:33:57.645170  3531 solver.cpp:237]     Train net output #0: loss = 0.504953 (* 1 = 0.504953 loss)
I0924 10:33:57.645193  3531 sgd_solver.cpp:105] Iteration 4500, lr = 0.0001
I0924 10:34:03.363797  3531 solver.cpp:218] Iteration 4600 (17.4866 iter/s, 5.71868s/100 iters), loss = 0.539086
I0924 10:34:03.363833  3531 solver.cpp:237]     Train net output #0: loss = 0.539086 (* 1 = 0.539086 loss)
I0924 10:34:03.363857  3531 sgd_solver.cpp:105] Iteration 4600, lr = 0.0001
I0924 10:34:09.086326  3531 solver.cpp:218] Iteration 4700 (17.4747 iter/s, 5.72254s/100 iters), loss = 0.479981
I0924 10:34:09.086364  3531 solver.cpp:237]     Train net output #0: loss = 0.479981 (* 1 = 0.479981 loss)
I0924 10:34:09.086372  3531 sgd_solver.cpp:105] Iteration 4700, lr = 0.0001
I0924 10:34:14.808562  3531 solver.cpp:218] Iteration 4800 (17.4756 iter/s, 5.72225s/100 iters), loss = 0.448841
I0924 10:34:14.808598  3531 solver.cpp:237]     Train net output #0: loss = 0.448841 (* 1 = 0.448841 loss)
I0924 10:34:14.808605  3531 sgd_solver.cpp:105] Iteration 4800, lr = 0.0001
I0924 10:34:20.530061  3531 solver.cpp:218] Iteration 4900 (17.4779 iter/s, 5.72152s/100 iters), loss = 0.514297
I0924 10:34:20.530097  3531 solver.cpp:237]     Train net output #0: loss = 0.514297 (* 1 = 0.514297 loss)
I0924 10:34:20.530119  3531 sgd_solver.cpp:105] Iteration 4900, lr = 0.0001
I0924 10:34:25.963594  3535 data_layer.cpp:73] Restarting data prefetching from start.
I0924 10:34:26.162818  3531 solver.cpp:457] Snapshotting to HDF5 file examples/cifar10/cifar10_quick_iter_5000.caffemodel.h5
I0924 10:34:26.193091  3531 sgd_solver.cpp:283] Snapshotting solver state to HDF5 file examples/cifar10/cifar10_quick_iter_5000.solverstate.h5
I0924 10:34:26.216594  3531 solver.cpp:310] Iteration 5000, loss = 0.48887
I0924 10:34:26.216617  3531 solver.cpp:330] Iteration 5000, Testing net (#0)
I0924 10:34:28.371587  3536 data_layer.cpp:73] Restarting data prefetching from start.
I0924 10:34:28.459497  3531 solver.cpp:397]     Test net output #0: accuracy = 0.7525
I0924 10:34:28.459523  3531 solver.cpp:397]     Test net output #1: loss = 0.756179 (* 1 = 0.756179 loss)
I0924 10:34:28.459530  3531 solver.cpp:315] Optimization Done.
I0924 10:34:28.459550  3531 caffe.cpp:259] Optimization Done.
  • 最后，达到的acc是75%左右。caffe还提供了full_train的方法，只需要修改文件名即可，这里就不在赘述。
跬步千里OvO
关注
专栏目录
LeNet训练cifar-10数据集
weixin_55674882的博客
05-12 262
一些学习笔记(实时更新)
Caffe代码学习及cifar-10数据集解析
计算机的专栏
04-13 729
Caffe代码学习及cifar-10数据集解析Caffe代码CIFAR-10是什么？Cifar-10是由Hinton的两个大弟子AlexKrizhevsky和llyaSutskever收集的一个用于普通物体识别的数据集。CIFAR是由加拿大牵头投资的一个先进的科学项目研究所。Hinton和Bengio以及他的学生在2004年拿到了CIFAR项目投资少量的资金，建立了神经计算和自适应感知项目。这个项...
cifar10数据集训练
。
06-04 1675
有关CIFAR-10数据集 （1）CIFAR-10数据集由10个类的60000个32x32彩色图像组成，每个类有6000个图像。有50000个训 练图像和10000个测试图像。 （2）数据集分为五个训练批次和一个测试批次，每个批次有10000个图像。测试批次包含来自每个类别 的恰好1000个随机选择的图像。 （3）第一部分是特征部分，使用一个[10000,3072的uint8的矩阵进行存储，每一行向量都是3X3大小的 3通道图片，构成的格式类似于[3,3,3]；第二部分为标签部分，使用一个10000.
【卷积神经网络】基于CIFAR10数据集实现图像分类【构建、训练、预测】
最新发布
逐梦苍穹的博客
08-03 920
卷积神经网络的实操案例，基于CIFAR10数据集进行网络构建、训练和预测，用python代码实现，讲解简单数学原理
CIFAR10数据集训练及测试
cy364328541的博客
04-09 7520
基于pytorch搭建CIFAR10网络模型后进行训练和预测。
CIFAR10数据集训练与测试
m0_46692607的博客
03-02 1027
诸：1和3主要由数据集决定，而2则是有模型的结构决定，需要计算。对于2的计算，如果模型很复杂，尤其网络特别深，我们要按照输入尺寸，从头到尾进行计算，这样太麻烦了。以前面的模型和参数作为 baseline，对其进行改进如下，目的是提高测试集准确度，减少泛化误差，模型参数量和运算量。分析：泛化误差为训练精度和验证精度的差值，观察上图可知，随着训练的进行，泛化误差在增加。设计函数如下，注意不同的模型有不同的特征提取过程，需要修改函数中的第二行代码。缺点：参数多，容易过拟合，对输入特征图的尺寸有要求，需要计算。
CIFAR10数据集训练及测试2
YZBFOREVERNB的博客
10-14 496
CIFAR10数据集训练及测试
caffe-cifar100数据集
12-26
使用转换后的LMDB数据集，用户可以轻松地在Caffe中构建和训练深度学习模型，对CIFAR-100数据集进行图像分类任务。这对于研究和开发新的卷积神经网络架构或比较不同方法的性能非常有用。 总之，这个压缩包提供的...
caffe学习笔记1CIFAR-10在caffe上进行训练与学习-薛开宇1
08-03
CIFAR-10是一个常用的计算机视觉数据集，包含60,000张32x32彩色图像，分为10个类别，其中50,000张用于训练，10,000张用于测试。在Caffe这一深度学习框架中对CIFAR-10进行训练与学习，可以帮助我们理解如何在实际中...
cifar-10-binary.tar.gz数据集
03-14
CIFAR-10二进制数据集（cifar-10-binary.tar.gz）是深度学习领域常用的图像识别数据集，特别适用于训练和测试各种计算机视觉模型，如卷积神经网络（CNN）。这个数据集由Caffe框架所采用，便于进行分类任务的实践和...
Caffe数据集：CIFAR10之一
12-01
在Caffe框架中，使用CIFAR10数据集进行训练时，你需要将这些二进制文件转换成Caffe可以识别的输入格式，如LMDB或HDF5。然后，你可以配置Caffe的 prototxt 文件定义网络架构（如LeNet、VGG、ResNet等）和训练参数，...
tensorflow训练CIFAR-10数据集源代码
05-09
tensorflow训练CIFAR-10源代码，可以直接运行使用，初学者的参考资料
cifar训练数据集
08-14
cifar训练数据集，详情请看http://www.cs.toronto.edu/~kriz/cifar.html。
来自cafar-10的深度学习数据集
10-23
用自己写的程序把cafar-10的二进制文件转化为jpg格式的图片，已经分好了文件夹放置，文件的文件名也是类如cat_10.jpg这样的。
CIFAR10_data
09-29
共享计算机视觉数据库。CIFAR-10是常用的计算机视觉数据库之一，包含最常见的十类自然事物，用于学习分类。
使用cifar10数据集进行训练和验证（pytorch）
skywuuu的博客
12-09 3000
使用cifar10数据集进行训练和验证（pytorch） import torch from torch.utils.data import DataLoader from torchvision import datasets, transforms from lenet5 import Lenet5 from ResNet import ResNet18 from AlexNet import AlexNet # from VGG import vgg16_bn from VGG_2 import vg
CIFAR-10数据集训练-Tensorflow1.0
hou9021的博客
02-24 1227
1.CIFAR-10数据集下载、解压 import urllib.request import os import tarfile 使用爬虫urlib库对网址 https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz 内容进行下载；tarfile库对压缩文件解压。 #下载 url = 'https://www.cs.toronto.edu/~...
[Pytorch] CIFAR-10数据集的训练和模型优化
qq_51533157的博客
01-30 7894
训练模型是个时间较长的过程，如果电脑中有cuda的支持，将可以使用GPU进行训练，减少一定的时间。在神经网络中，有三个部分可以放到GPU中分别是在模型、损失函数以及数据上。首先定义训练设备device然后在程序中模型、损失函数、和数据上使用to函数加入到GPU中。# 模型 model_u = model_u . to(device) # 损失函数 loss_fn = loss_fn . to(device) # 数据 imgs , targets = data。
caffe练习实例（2）——训练cifar10数据集
孤旅人。。。的博客
12-11 993
这个实例与mnist类似。操作步骤如下： 1. 下载数据： 执行get_cifar10.sh这个脚本文件进行下载数据，但是这个方法下载速度太慢了，cifar10的数据集180Mb左右。我把下载下来的存到微云里面了，我的CSDN资源里面也有一份. 2. 将数据转化为lmdb格式：./examples/mnist/create_cifar10.sh 3. 训练：.
Caffe实战：CIFAR-10数据集的训练与配置详解
本篇" caffe学习笔记1-7-完整版-薛开宇"主要介绍了在Caffe框架下进行CIFAR-10数据集训练与学习的过程。CIFAR-10是一个包含60000张32x32彩色图像的10类数据集，其中50000张用于训练，10000张用于测试。学习的关键步骤...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值