caffe训练自己的数据集——2. 开始训练

最新推荐文章于 2024-04-04 09:33:28 发布

Kindle君

最新推荐文章于 2024-04-04 09:33:28 发布

阅读量599

点赞数

分类专栏： Caffe 文章标签： caffe 训练测试输出日志

本文链接：https://blog.csdn.net/yexiaogu1104/article/details/77979334

版权

Caffe 专栏收录该内容

4 篇文章 0 订阅

订阅专栏

一、配置文件

1. 网络结构

henet_car_train_test.prototxt

#name: "LeNet"
layer {
  name: "mnist"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "/home/datasets/carPlate/train_test_labels/train_10"
    batch_size: 64
    backend: LMDB
  }
}
layer {
  name: "mnist"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "/home/datasets/carPlate/train_test_labels/val_G5"
    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
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "group0_block0_conv0"
  type: "Convolution"
  bottom: "pool1"
  top: "group0_block0_conv0"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  convolution_param {
    num_output: 32
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "group0_block0_conv0_bn"
  type: "BatchNorm"
  bottom: "group0_block0_conv0"
  top: "group0_block0_conv0"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "group0_block0_conv0_scale"
  type: "Scale"
  bottom: "group0_block0_conv0"
  top: "group0_block0_conv0"
  scale_param {
    bias_term: true
  }
}
layer {
  name: "group0_block0_conv0_relu"
  type: "ReLU"
  bottom: "group0_block0_conv0"
  top: "group0_block0_conv0"
}
layer {
  name: "group0_block0_conv1"
  type: "Convolution"
  bottom: "group0_block0_conv0"
  top: "group0_block0_conv1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  convolution_param {
    num_output: 32
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "group0_block0_conv1_bn"
  type: "BatchNorm"
  bottom: "group0_block0_conv1"
  top: "group0_block0_conv1"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "group0_block0_conv1_scale"
  type: "Scale"
  bottom: "group0_block0_conv1"
  top: "group0_block0_conv1"
  scale_param {
    bias_term: true
  }
}



layer {
  name: "group1_block0_conv0"
  type: "Convolution"
  bottom: "group0_block0_conv1"
  top: "group1_block0_conv0"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  convolution_param {
    num_output: 32
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "group1_block0_conv0_bn"
  type: "BatchNorm"
  bottom: "group1_block0_conv0"
  top: "group1_block0_conv0"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "group1_block0_conv0_scale"
  type: "Scale"
  bottom: "group1_block0_conv0"
  top: "group1_block0_conv0"
  scale_param {
    bias_term: true
  }
}
layer {
  name: "group1_block0_conv0_relu"
  type: "ReLU"
  bottom: "group1_block0_conv0"
  top: "group1_block0_conv0"
}
layer {
  name: "group1_block0_conv1"
  type: "Convolution"
  bottom: "group1_block0_conv0"
  top: "group1_block0_conv1"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  convolution_param {
    num_output: 32
    pad: 1
    kernel_size: 3
    stride: 1
    weight_filler {
      type: "msra"
    }
  }
}
layer {
  name: "group1_block0_conv1_bn"
  type: "BatchNorm"
  bottom: "group1_block0_conv1"
  top: "group1_block0_conv1"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
}
layer {
  name: "group1_block0_conv1_scale"
  type: "Scale"
  bottom: "group1_block0_conv1"
  top: "group1_block0_conv1"
  scale_param {
    bias_term: true
  }
}
layer {
  name: "group1_block0_sum"
  type: "Eltwise"
  bottom: "group0_block0_conv1"
  bottom: "group1_block0_conv1"
  top: "group1_block0_sum"
  eltwise_param {
    operation: SUM
  }
}
layer {
  name: "group0_block0_sum"
  type: "Eltwise"
  bottom: "group1_block0_sum"
  bottom: "pool1"
  top: "group0_block0_sum"
  eltwise_param {
    operation: SUM
  }
}




layer {
  name: "conv2"
  type: "Convolution"
  bottom: "group0_block0_sum"
  top: "conv2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 50
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool2"
  top: "ip1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "ip1"
  top: "ip1"
}
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: "xavier"
    }
    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: "lab`}}}}}}}}
``
l"
  top: "loss"
}
_product_param {
    num_output: 10
    weight_filler {
      type: "xavier"
    }
    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"
}

2. 超参数

lenet_solver.prototxt

# The train/test net protocol buffer definition
net:  "henet_car_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: 0.0005
# The learning rate policy
lr_policy: "inv"
gamma: 0.0001
power: 0.75
# Display every 100 iterations
display: 100
# The maximum number of iterations
max_iter: 10000
# snapshot intermediate results
snapshot: 5000
snapshot_prefix: "/home/datasets/carPlate/train_test_labels/train_10/train_10"  #前一个train_10是制定路径，最后一个表示模型文件的前缀
# solver mode: CPU or 
GPU
solver_mode: GPU

二、开始训练

1. 训练并输出日志

1. 无预训练
/opt/caffe/build/tools/caffe train \
--solver=/home/datasets/carPlate/train_test_labels/henet_solver.prototxt 2>&1 | tee /home/datasets/carPlate/train_test_labels/train_10/train_10_henet_Res2order.log
2. 加载预训练模型
/opt/caffe/build/tools/caffe train \
--solver=/home/datasets/carPlate/train_test_labels/henet_solver.prototxt \
--weights=/home/datasets/carPlate/train_test_labels/train_10/train_10_iter_45000.caffemodel \
2>&1 | tee /home/datasets/carPlate/train_test_labels/train_30/train_30_henet_Res2order.log
3.

2. 输出数值信息

/opt/caffe/tools/extra/parse_log.py \
/home/datasets/carPlate/train_test_labels/train_10/train_10_henet_Res2order.log \#前一个步骤保存的日志文件
/home/datasets/carPlate/train_test_labels/train_10/ \#数值信息的保存路径
#生成henet_Res2order.log.test 和henet_Res2order.log.train两个文件

3. 绘制loss&accuracy曲线

4.测试数据

/opt/caffe/build/tools/caffe test \
--model=/home/datasets/carPlate/train_test_labels/henet_car_train_test.prototxt \
--weights=/home/datasets/carPlate/train_test_labels/train_30/train_30_iter_45000.caffemodel \
2>&1 | tee /home/datasets/carPlate/train_test_labels/train_30/test_30_henet_Res2order.log

5. 失败记录

文件名	0	1	2	3	共计
G1	742	41	25	673	1481
G2	642	39	19	571	1271
G3	639	83	16	659	1397
G4	244	319	0	1187	1750
G5	1360	57	6	1556	2979

a. 第一次：从头开始训练

1. 网络结构：caffe自带```lenet_car_train_test.prototx```
2. 超参数:上面的```lenet_solver.prototxt```
3. 训练数据：train_100 (100%的训练数据），总的数据说明参见前文。
4. 测试结果：train_100_lenet_iter_10000.caffemodel
5. 测试分析：G4可能因为黄牌比例较大，所以效果较差；single_2是白色车牌，效果较差；其余效果也未达到99%

G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
97.4342%	98.741%	98.7831%	31.6571%	91.0708%	93.6035%	96.846%	56.0606%	98.712%

b. 第二次：单独训练白色和黄色车牌

1. 网络结构：train_batch_size:128->64
2. 超参数：base_lr: 0.001->0.001，weight_decay: 0.0005->0.0005
3. 预训练模型：train_100_lenet_iter_10000.caffemodel 
4. 训练数据：train_100_yellow_white
5. 测试结果：白牌和黄牌效果确实提升了，但是蓝牌和非车牌很差了，应该是迭代次数过多。

G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
97.4342%	98.741%	98.7831%	31.6571%	91.0708%	93.6035%	96.846%	56.0606%	98.712%
————	————	————	————	————	8.54701%	99.6289%	98.4848%	21.3892%

c. 第三次：单独训练白色和黄色车牌

1. 网络结构：train_batch_size:128->64, 2个conv层的学习率设为0，ip3学习率缩小100倍：0.01，0.02，
2. 超参数：base_lr: 0.001->0.001，weight_decay: 0.0005->0.0005
3. 预训练模型：train_100_lenet_iter_10000.caffemodel （从第一次开始）
4. 训练数据：train_100_yellow_white
5. 测试结果：4类别单独测试效果都上了90%，尤其是白色从56.0606%提升到97.192%，但蓝色略有下降，怀疑主要是由于蓝色和非车牌的误判导致G4效果不理想

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
train_100_lenet_iter_10000.caffemodel	97.4342%	98.741%	98.7831%	31.6571%	91.0708%	93.6035%	96.846%	56.0606%	98.712%
non		————	————	————	————	8.54701%	99.6289%	98.4848%	21.3892%
train_100_lenet_yellow_white_iter_10.caffemodel	97.4342%	98.7411%	98.8547%	31.7143%	91.0708%	93.5484%	97.2171%	97.192%	98.7209%

c. 第四次：单独训练蓝色车牌

1. 网络结构：train_batch_size:128->64, 2个conv层的学习率设为0，ip3学习率缩小100倍：0.01，0.02，
2. 超参数：base_lr: 0.001->0.001，weight_decay: 0.0005->0.0005
3. 预训练模型：train_100_lenet_iter_10000.caffemodel （从第一次开始）
4. 训练数据：train_100_blue_non500
5. 测试结果：白牌和黄牌效果确实提升了，但是蓝牌和非车牌很差了，应该是迭代次数过多。

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
97.4342%	98.741%	98.7831%	31.6571%	91.0708%	93.6035%	96.846%	56.0606%	98.712%
non			————	————	————	————	8.54701%	99.6289%	98.4848%
train_100_lenet_yellow_white_iter_10.caffemodel	97.4342%	98.7411%	98.8547%	31.7143%	91.0708%	93.5484%	57.6994%	57.5758%	98.7209%
train_100_lenet_blue_non500_iter_100.caffemodel	97.5017%	98.4264%	98.4968%	31.8857%	91.8765：%	94.5409%	86.6419%	86.3636%	97.8593%

结论：妈的数据集做错了，一定不能有文件夹为空！！！！！

6. Lenet重新训练

常用vim命令：

替换：
:%s/abc/def/g

1. 原始Lenet训练

1. 网络结构：train_batch_size=64
2. 超参数：base_lr: 0.0001，weight_decay: 0.0005->0.0005
3. 预训练模型：从零开始
4. 训练数据：train_100_all
5. 测试结果：这里只分为2类，每50000次进行重新训练(使用snapshot参数)。

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
train_100_lenet_iter_50000.caffemodel	98.7846%	99.6066%	99.3558%	97.8286%	96.811%	97.9597%	97.9592%	87.8788%	99.0584%
train_100_lenet_iter_100000.caffemodel	99.1222%	99.764%	99.4273%	98.3428%	97.5495%	98.4836%	97.957%	98.4848%	99.165%
train_100_lenet_iter_150000.caffemodel	99.1222	99.764	99.4989%	98.7429%	97.7845	98.5663%	98.1447%	100%	99.2627%
train_100_lenet_iter_150000.caffemodel	99.1897	99.6853	99.4989%	98.8571%	97.7845	98.5387%	98.3302%	100%	99.316%

# The train/test net protocol buffer definition
net: "lenet_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: 0.0001
momentum: 0.9
weight_decay: 0.0005
# The learning rate policy
lr_policy: "inv"
gamma: 0.0001
power: 0.75
# Display every 100 iterations
display: 100
# The maximum number of iterations
max_iter: 50000
# snapshot intermediate results
snapshot: 5000
snapshot_prefix: "/home/datasets/carPlate/train_test_2_class/train_100/train_100_lenet"
# solver mode: CPU or GPU
solver_mode: GPU

2. Lenet全连接层的裁剪

第一次

1. 网络结构：train_batch_size=64，修改ip1_400 ->ip1_400，对应的num_oputput 500 ->400， 
2. 超参数：base_lr: 0.0001，weight_decay: 0.0005->0.0005, max_iter:50000
3. 预训练模型：train_100_lenet_iter_200000.caffemodel（前一个小节得到的模型）
4. 训练数据：train_100_all
5. 测试结果：这里只分为2类，每50000次进行重新训练(使用snapshot参数)。越往后训练，对负样本的准确率越高，模型大小：1.05Mb

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
train_100_lenet_iter_50000.caffemodel	98.7846%	99.6066%	99.3558%	97.8286%	96.811%	97.9597%	97.9592%	87.8788%	99.0584%
train_100_lenet_iter_100000.caffemodel	99.1222%	99.764%	99.4273%	98.3428%	97.5495%	98.4836%	97.957%	98.4848%	99.165%
train_100_lenet_iter_150000.caffemodel	99.1222	99.764	99.4989%	98.7429%	97.7845	98.5663%	98.1447%	100%	99.2627%
train_100_lenet_iter_150000.caffemodel	99.1897	99.6853	99.4989%	98.8571%	97.7845	98.5387%	98.3302%	100%	99.316%
train_100_lenet_zip_0_iter_50000.caffemodel	99.3248	99.6853	99.4273%	98.8%	97.6838	98.5112%	98.3302%	100%	99.2095%
train_100_lenet_zip_0_iter_100000.caffemodel	99.2573	99.5279	99.3558%	98.87429%	97.5831	98.3182%	98.1447%	100%	99.2361%

第二次

1. 网络结构：train_batch_size=64，修改ip1_400 ->ip1_200，对应的num_oputput 400 ->200， 
2. 超参数：base_lr: 0.0001，weight_decay: 0.0005->0.0005, max_iter:100000
3. 预训练模型：train_100_lenet_iter_200000.caffemodel（前一个小节得到的模型）
4. 训练数据：train_100_all
5. 测试结果：这里只分为2类，每50000次进行重新训练(使用snapshot参数)。越往后训练，对负样本的准确率越高，模型大小349k

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
train_100_lenet_iter_50000.caffemodel	98.7846%	99.6066%	99.3558%	97.8286%	96.811%	97.9597%	97.9592%	87.8788%	99.0584%
train_100_lenet_iter_100000.caffemodel	99.1222%	99.764%	99.4273%	98.3428%	97.5495%	98.4836%	97.957%	98.4848%	99.165%
train_100_lenet_iter_150000.caffemodel	99.1222	99.764	99.4989%	98.7429%	97.7845	98.5663%	98.1447%	100%	99.2627%
train_100_lenet_iter_150000.caffemodel	99.1897	99.6853	99.4989%	98.8571%	97.7845	98.5387%	98.3302%	100%	99.316%
train_100_lenet_zip_0_iter_50000.caffemodel	99.3248	99.6853	99.4273%	98.8%	97.6838	98.5112%	98.3302%	100%	99.2095%
train_100_lenet_zip_0_iter_100000.caffemodel	99.2573	99.5279	99.3558%	98.87429%	97.5831	98.3182%	98.1447%	100%	99.2361%
train_100_lenet_zip_1_iter_50000.caffemodel	98.9872	99.6853	99.4989%	98.85719%	97.7174	98.4836%	98.3302%	100%	99.2095%
train_100_lenet_zip_1_iter_50000.caffemodel	99.0547	99.6066	99.4273%	98.97149%	97.6838	98.456%	98.3302%	100%	99.2272%

第三次

1. 网络结构：train_batch_size=64，修改ip1_200 ->ip1_50，对应的num_oputput 200 ->50， 
2. 超参数：base_lr: 0.0001，weight_decay: 0.0005->0.0005, max_iter:100000
3. 预训练模型：train_100_lenet_iter_200000.caffemodel（前一个小节得到的模型）
4. 训练数据：train_100_all
5. 测试结果：这里只分为2类。模型大小152k

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
train_100_lenet_iter_50000.caffemodel	98.7846%	99.6066%	99.3558%	97.8286%	96.811%	97.9597%	97.9592%	87.8788%	99.0584%
train_100_lenet_iter_100000.caffemodel	99.1222%	99.764%	99.4273%	98.3428%	97.5495%	98.4836%	97.957%	98.4848%	99.165%
train_100_lenet_iter_150000.caffemodel	99.1222	99.764	99.4989%	98.7429%	97.7845	98.5663%	98.1447%	100%	99.2627%
train_100_lenet_iter_150000.caffemodel	99.1897	99.6853	99.4989%	98.8571%	97.7845	98.5387%	98.3302%	100%	99.316%
train_100_lenet_zip_0_iter_50000.caffemodel	99.3248	99.6853	99.4273%	98.8%	97.6838	98.5112%	98.3302%	100%	99.2095%
train_100_lenet_zip_0_iter_100000.caffemodel	99.2573	99.5279	99.3558%	98.87429%	97.5831	98.3182%	98.1447%	100%	99.2361%
train_100_lenet_zip_1_iter_50000.caffemodel	98.9872	99.6853	99.4989%	98.85719%	97.7174	98.4836%	98.3302%	100%	99.2095%
train_100_lenet_zip_1_iter_100000.caffemodel	99.0547	99.6066	99.4273%	98.97149%	97.6838	98.456%	98.3302%	100%	99.2272%
train_100_lenet_zip_2_iter_60000.caffemodel	99.3248	99.764	99.4989%	98.8%	97.8181	98.6215%	98.5158%	100%	99.2183%
train_100_lenet_zip_2_iter_100000.caffemodel	99.1897	99.6853	99.4273%	98.8%	97.6838	98.4285%	98.5158%	100%	99.1917%

第四次

1. 网络结构：train_batch_size=64，修改ip1_50 ->ip1_10，对应的num_oputput 50 ->10， 
2. 超参数：base_lr: 0.0001，weight_decay: 0.0005->0.0005, max_iter:100000
3. 预训练模型：train_100_lenet_iter_200000.caffemodel（前一个小节得到的模型）
4. 训练数据：train_100_all
5. 测试结果：这里只分为2类。模型大小126k

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
train_100_lenet_iter_50000.caffemodel	98.7846%	99.6066%	99.3558%	97.8286%	96.811%	97.9597%	97.9592%	87.8788%	99.0584%
train_100_lenet_iter_100000.caffemodel	99.1222%	99.764%	99.4273%	98.3428%	97.5495%	98.4836%	97.957%	98.4848%	99.165%
train_100_lenet_iter_150000.caffemodel	99.1222	99.764	99.4989%	98.7429%	97.7845	98.5663%	98.1447%	100%	99.2627%
train_100_lenet_iter_150000.caffemodel	99.1897	99.6853	99.4989%	98.8571%	97.7845	98.5387%	98.3302%	100%	99.316%
train_100_lenet_zip_0_iter_50000.caffemodel	99.3248	99.6853	99.4273%	98.8%	97.6838	98.5112%	98.3302%	100%	99.2095%
train_100_lenet_zip_0_iter_100000.caffemodel	99.2573	99.5279	99.3558%	98.87429%	97.5831	98.3182%	98.1447%	100%	99.2361%
train_100_lenet_zip_1_iter_50000.caffemodel	98.9872	99.6853	99.4989%	98.85719%	97.7174	98.4836%	98.3302%	100%	99.2095%
train_100_lenet_zip_1_iter_100000.caffemodel	99.0547	99.6066	99.4273%	98.97149%	97.6838	98.456%	98.3302%	100%	99.2272%
train_100_lenet_zip_2_iter_60000.caffemodel	99.3248	99.764	99.4989%	98.8%	97.8181	98.6215%	98.5158%	100%	99.2183%
train_100_lenet_zip_2_iter_100000.caffemodel	99.1897	99.6853	99.4273%	98.8%	97.6838	98.4285%	98.5158%	100%	99.1917%
train_100_lenet_zip_3_iter_50000.caffemodel	99.4598	99.764	99.141%	98.8571%	98.0866	98.9247%	98.3302%	100%	99.165%
train_100_lenet_zip_3_iter_50000.caffemodel	99.3248	99.6853	99.3558%	98.8571%	97.8852	98.649%	98.1447%	100%	99.245%

第五次

1. 网络结构：train_batch_size=64，修改ip1_10 ->ip1_4，对应的num_oputput 10 ->4， 
2. 超参数：base_lr: 0.0001，weight_decay: 0.0005->0.0005, max_iter:100000
3. 预训练模型：train_100_lenet_iter_200000.caffemodel（前一个小节得到的模型）
4. 训练数据：train_100_all
5. 测试结果：这里只分为2类。模型大小116k

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
train_100_lenet_iter_50000.caffemodel	98.7846%	99.6066%	99.3558%	97.8286%	96.811%	97.9597%	97.9592%	87.8788%	99.0584%
train_100_lenet_iter_100000.caffemodel	99.1222%	99.764%	99.4273%	98.3428%	97.5495%	98.4836%	97.957%	98.4848%	99.165%
train_100_lenet_iter_150000.caffemodel	99.1222	99.764	99.4989%	98.7429%	97.7845	98.5663%	98.1447%	100%	99.2627%
train_100_lenet_iter_150000.caffemodel	99.1897	99.6853	99.4989%	98.8571%	97.7845	98.5387%	98.3302%	100%	99.316%
train_100_lenet_zip_0_iter_50000.caffemodel	99.3248	99.6853	99.4273%	98.8%	97.6838	98.5112%	98.3302%	100%	99.2095%
train_100_lenet_zip_0_iter_100000.caffemodel	99.2573	99.5279	99.3558%	98.87429%	97.5831	98.3182%	98.1447%	100%	99.2361%
train_100_lenet_zip_1_iter_50000.caffemodel	98.9872	99.6853	99.4989%	98.85719%	97.7174	98.4836%	98.3302%	100%	99.2095%
train_100_lenet_zip_1_iter_100000.caffemodel	99.0547	99.6066	99.4273%	98.97149%	97.6838	98.456%	98.3302%	100%	99.2272%
train_100_lenet_zip_2_iter_60000.caffemodel	99.3248	99.764	99.4989%	98.8%	97.8181	98.6215%	98.5158%	100%	99.2183%
train_100_lenet_zip_2_iter_100000.caffemodel	99.1897	99.6853	99.4273%	98.8%	97.6838	98.4285%	98.5158%	100%	99.1917%
train_100_lenet_zip_3_iter_50000.caffemodel	99.4598	99.764	99.141%	98.8571%	98.0866	98.9247%	98.3302%	100%	99.165%
train_100_lenet_zip_3_iter_50000.caffemodel	99.3248	99.6853	99.3558%	98.8571%	97.8852	98.649%	98.1447%	100%	99.245%
train_100_lenet_zip_4_iter_50000.caffemodel	99.1897	99.5279	98.9979%	98.8571%	98.3552	98.9799%	98.1447%	98.4848%	99.1473%
train_100_lenet_zip_4_iter_100000.caffemodel	99.3923	99.6066	99.0694%	98.8571%	98.1202	98.842%	98.1447%	100%	99.2006 %

第五次

1. 网络结构：train_batch_size=64，修改ip1_4 ->ip1_2，对应的num_oputput 4 ->2，去掉最后一层全连接层 
2. 超参数：base_lr: 0.0001，weight_decay: 0.0005->0.0005, max_iter:100000
3. 预训练模型：train_100_lenet_iter_200000.caffemodel（前一个小节得到的模型）
4. 训练数据：train_100_all
5. 测试结果：至少需要两个全连接层。

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
train_100_lenet_iter_50000.caffemodel	98.7846%	99.6066%	99.3558%	97.8286%	96.811%	97.9597%	97.9592%	87.8788%	99.0584%
train_100_lenet_iter_100000.caffemodel	99.1222%	99.764%	99.4273%	98.3428%	97.5495%	98.4836%	97.957%	98.4848%	99.165%
train_100_lenet_iter_150000.caffemodel	99.1222	99.764	99.4989%	98.7429%	97.7845	98.5663%	98.1447%	100%	99.2627%
train_100_lenet_iter_150000.caffemodel	99.1897	99.6853	99.4989%	98.8571%	97.7845	98.5387%	98.3302%	100%	99.316%
train_100_lenet_zip_0_iter_50000.caffemodel	99.3248	99.6853	99.4273%	98.8%	97.6838	98.5112%	98.3302%	100%	99.2095%
train_100_lenet_zip_0_iter_100000.caffemodel	99.2573	99.5279	99.3558%	98.87429%	97.5831	98.3182%	98.1447%	100%	99.2361%
train_100_lenet_zip_1_iter_50000.caffemodel	98.9872	99.6853	99.4989%	98.85719%	97.7174	98.4836%	98.3302%	100%	99.2095%
train_100_lenet_zip_1_iter_100000.caffemodel	99.0547	99.6066	99.4273%	98.97149%	97.6838	98.456%	98.3302%	100%	99.2272%
train_100_lenet_zip_2_iter_60000.caffemodel	99.3248	99.764	99.4989%	98.8%	97.8181	98.6215%	98.5158%	100%	99.2183%
train_100_lenet_zip_2_iter_100000.caffemodel	99.1897	99.6853	99.4273%	98.8%	97.6838	98.4285%	98.5158%	100%	99.1917%
train_100_lenet_zip_3_iter_50000.caffemodel	99.4598	99.764	99.141%	98.8571%	98.0866	98.9247%	98.3302%	100%	99.165%
train_100_lenet_zip_3_iter_100000.caffemodel	99.3248	99.6853	99.3558%	98.8571%	97.8852	98.649%	98.1447%	100%	99.245%
train_100_lenet_zip_4_iter_50000.caffemodel	99.1897	99.5279	98.9979%	98.8571%	98.3552	98.9799%	98.1447%	98.4848%	99.1473%
train_100_lenet_zip_4_iter_100000.caffemodel	99.3923	99.6066	99.0694%	98.8571%	98.1202	98.842%	98.1447%	100%	99.2006 %
train_100_lenet_zip_5_iter_50000.caffemodel	99.1897	99.5279	98.9979%	98.8571%	98.3552	98.9799%	3.71058%	98.4848%	99.1473%
train_100_lenet_zip_5_iter_50000.caffemodel	96.4889	96.5382	93.4145%	80.9714%	96.4082	98.9799%	3.71058%	96.9697%	99.2006%

3. Lenet卷积层的裁剪

name: "LeNet"
layer {
  name: "mnist"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "train_100_all"
    batch_size: 64
    backend: LMDB
  }
}
layer {
  name: "mnist"
  type: "Data"
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
  transform_param {
    scale: 0.00390625
  }
  data_param {
    source: "val_G1"
    batch_size:1 
    backend: LMDB
  }
}
layer {
  name: "conv3"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 20
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv2_40"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  propagate_down:false
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 40
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "ip1_4_40"
  type: "InnerProduct"
  bottom: "pool2"
  top: "ip1"
  propagate_down:true
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 4
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "ip1"
  top: "ip1"
}
layer {
  name: "ip3_4"
  type: "InnerProduct"
  bottom: "ip1"
  top: "ip2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 2
    weight_filler {
      type: "xavier"
    }
    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"
}

第6次

1. 网络结构：train_batch_size=64，修改ip1_10 ->ip1_4，对应的num_oputput 10 ->4， conv2:50->40, ip1到ip3的参数不变
2. 超参数：base_lr: 0.0001，weight_decay: 0.0005->0.0005, max_iter:100000，再增加到150000次（因为测试发现，对于白牌仍然存在提升空间）
3. 预训练模型：train_100_lenet_zip_4_iter_100000.caffemodel（前一个小节得到的模型）
4. 训练数据：train_100_all
5. 测试结果：这里只分为2类。模型大小102k

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
train_100_lenet_zip_4_iter_50000.caffemodel	99.1897	99.5279	98.9979%	98.8571%	98.3552	98.9799%	98.1447%	98.4848%	99.1473%
train_100_lenet_zip_4_iter_100000.caffemodel	99.3923	99.6066	99.0694%	98.8571%	98.1202	98.842%	98.1447%	100%	99.2006 %
train_100_lenet_zip_6_iter_50000.caffemodel	99.5273	99.5279	99.141%	99.0286%	97.9523	98.7869%	99.0724%	93.9394%	99.1206%
train_100_lenet_zip_6_iter_100000.caffemodel	99.5273	99.6066	99.3558%	98.9143%	98.053	98.8144%	98.8868%	98.4848%	99.165%
train_100_lenet_zip_6_iter_150000.caffemodel	99.5949	99.6853	99.4273%	99.0286%	97.8181	98.6215%	98.8868%	98.4848%	99.2983%

第7次

1. 网络结构：train_batch_size=64，修改ip1_10 ->ip1_4，对应的num_oputput 10 ->4， conv2:40->30, ip1到ip3的参数不变
2. 超参数：base_lr: 0.0001，weight_decay: 0.0005->0.0005, max_iter:100000，再增加到150000次（因为测试发现，对于白牌仍然存在提升空间）
3. 预训练模型：train_100_lenet_zip_4_iter_100000.caffemodel（前一个小节得到的模型）
4. 训练数据：train_100_all
5. 测试结果：这里只分为2类。模型大小79k

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
train_100_lenet_zip_4_iter_50000.caffemodel	99.1897	99.5279	98.9979%	98.8571%	98.3552	98.9799%	98.1447%	98.4848%	99.1473%
train_100_lenet_zip_4_iter_100000.caffemodel	99.3923	99.6066	99.0694%	98.8571%	98.1202	98.842%	98.1447%	100%	99.2006 %
train_100_lenet_zip_6_iter_50000.caffemodel	99.5273	99.5279	99.141%	99.0286%	97.9523	98.7869%	99.0724%	93.9394%	99.1206%
train_100_lenet_zip_6_iter_100000.caffemodel	99.5273	99.6066	99.3558%	98.9143%	98.053	98.8144%	98.8868%	98.4848%	99.165%
train_100_lenet_zip_6_iter_150000.caffemodel	99.5949	99.6853	99.4273%	99.0286%	97.8181	98.6215%	98.8868%	98.4848%	99.2983%
train_100_lenet_zip_7_iter_50000.caffemodel	99.1897	99.6853	99.2126%	98.5143%	97.8516	98.7869%	98.1447%	93.9394%	99.0762%
train_100_lenet_zip_7_iter_100000.caffemodel	99.3248	99.6853	99.3558%	98.6286%	97.9859	98.8144%	98.7013%	95.4545%	99.1384%
train_100_lenet_zip_7_iter_150000.caffemodel	99.1897	99.6066	99.4989%	98.9143%	97.8516	98.4285%	98.7013%	93.9394%	99.2983%

第8次

1. 网络结构：train_batch_size=64，修改ip1_10 ->ip1_4，对应的num_oputput 4 ->4， conv2:30->20, ip1到ip3的参数不变
2. 超参数：base_lr: 0.0001，weight_decay: 0.0005->0.0005, max_iter:100000，再增加到150000次（因为测试发现，对于白牌仍然存在提升空间）
3. 预训练模型：train_100_lenet_zip_4_iter_100000.caffemodel（前一个小节得到的模型）
4. 训练数据：train_100_all
5. 测试结果：这里只分为2类。模型大小54k

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
train_100_lenet_zip_4_iter_50000.caffemodel	99.1897	99.5279	98.9979%	98.8571%	98.3552	98.9799%	98.1447%	98.4848%	99.1473%
train_100_lenet_zip_4_iter_100000.caffemodel	99.3923	99.6066	99.0694%	98.8571%	98.1202	98.842%	98.1447%	100%	99.2006 %
train_100_lenet_zip_6_iter_50000.caffemodel	99.5273	99.5279	99.141%	99.0286%	97.9523	98.7869%	99.0724%	93.9394%	99.1206%
train_100_lenet_zip_6_iter_100000.caffemodel	99.5273	99.6066	99.3558%	98.9143%	98.053	98.8144%	98.8868%	98.4848%	99.165%
train_100_lenet_zip_6_iter_150000.caffemodel	99.5949	99.6853	99.4273%	99.0286%	97.8181	98.6215%	98.8868%	98.4848%	99.2983%
train_100_lenet_zip_7_iter_50000.caffemodel	99.1897	99.6853	99.2126%	98.5143%	97.8516	98.7869%	98.1447%	93.9394%	99.0762%
train_100_lenet_zip_7_iter_100000.caffemodel	99.3248	99.6853	99.3558%	98.6286%	97.9859	98.8144%	98.7013%	95.4545%	99.1384%
train_100_lenet_zip_7_iter_150000.caffemodel	99.1897	99.6066	99.4989%	98.9143%	97.8516	98.4285%	98.7013%	93.9394%	99.2983%
train_100_lenet_zip_8_iter_50000.caffemodel	99.3923	99.3706	98.9979%	98.7429%	98.1537	98.9247%	98.5158%	93.9394%	99.0496%
train_100_lenet_zip_8_iter_100000.caffemodel	99.5273	99.6066	99.141%	98.6286%	98.1537	98.9523%	98.5158%	96.9697%	99.0673%
train_100_lenet_zip_8_iter_150000.caffemodel	99.4598	99.6853	99.4273%	98.7429%	97.9523	98.6766%	98.3302%	95.4545%	99.2361%

第9次

1. 网络结构：train_batch_size=64，修改ip1_10 ->ip1_4，对应的num_oputput 4 ->4， conv2:20->15, 增加group=5(输入和输出channel数量必须能被group整除),ip1到ip3的参数不变
2. 超参数：base_lr: 0.0001，weight_decay: 0.0005->0.0005, max_iter:100000，再增加到150000次（因为测试发现，对于白牌仍然存在提升空间）
3. 预训练模型：train_100_lenet_zip_4_iter_100000.caffemodel（前一个小节得到的模型）
4. 训练数据：train_100_all
5. 测试结果：这里只分为2类。模型大小18k

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
train_100_lenet_zip_4_iter_50000.caffemodel	99.1897	99.5279	98.9979%	98.8571%	98.3552	98.9799%	98.1447%	98.4848%	99.1473%
train_100_lenet_zip_4_iter_100000.caffemodel	99.3923	99.6066	99.0694%	98.8571%	98.1202	98.842%	98.1447%	100%	99.2006 %
train_100_lenet_zip_6_iter_50000.caffemodel	99.5273	99.5279	99.141%	99.0286%	97.9523	98.7869%	99.0724%	93.9394%	99.1206%
train_100_lenet_zip_6_iter_100000.caffemodel	99.5273	99.6066	99.3558%	98.9143%	98.053	98.8144%	98.8868%	98.4848%	99.165%
train_100_lenet_zip_6_iter_150000.caffemodel	99.5949	99.6853	99.4273%	99.0286%	97.8181	98.6215%	98.8868%	98.4848%	99.2983%
train_100_lenet_zip_7_iter_50000.caffemodel	99.1897	99.6853	99.2126%	98.5143%	97.8516	98.7869%	98.1447%	93.9394%	99.0762%
train_100_lenet_zip_7_iter_100000.caffemodel	99.3248	99.6853	99.3558%	98.6286%	97.9859	98.8144%	98.7013%	95.4545%	99.1384%
train_100_lenet_zip_7_iter_150000.caffemodel	99.1897	99.6066	99.4989%	98.9143%	97.8516	98.4285%	98.7013%	93.9394%	99.2983%
train_100_lenet_zip_8_iter_50000.caffemodel	99.3923	99.3706	98.9979%	98.7429%	98.1537	98.9247%	98.5158%	93.9394%	99.0496%
train_100_lenet_zip_8_iter_100000.caffemodel	99.5273	99.6066	99.141%	98.6286%	98.1537	98.9523%	98.5158%	96.9697%	99.0673%
train_100_lenet_zip_8_iter_150000.caffemodel	99.4598	99.6853	99.4273%	98.7429%	97.9523	98.6766%	98.3302%	95.4545%	99.2361%
train_100_lenet_zip_9_iter_50000.caffemodel	99.5273	99.3706	98.9263%	98.5143%	98.1537	98.9247%	98.3302%	98.4848%	98.9696%
train_100_lenet_zip_9_iter_100000.caffemodel	99.4598	99.4493	99.141%	98.3429%	97.7845	98.8972%	97.9592%	96.9697%	98.9785%
train_100_lenet_zip_9_iter_150000.caffemodel	99.3923	99.3706	99.2126%	98.3429%	97.7174	98.6766%	97.5881%	96.9697%	99.1473%

第10次

1. 网络结构：train_batch_size=64，修改ip1_10 ->ip1_4，对应的num_oputput 4 ->4，conv1:20->15 conv2:20->15, 增加group=3(输入和输出channel数量必须能被group整除，记得更改conv1,conv2的name),ip1到ip3的参数不变
2. 超参数：base_lr: 0.0001，weight_decay: 0.0005->0.0005, max_iter:100000，再增加到150000次（因为测试发现，对于白牌仍然存在提升空间）
3. 预训练模型：train_100_lenet_zip_9_iter_100000.caffemodel（前一个小节得到的模型）
4. 训练数据：train_100_all
5. 测试结果：这里只分为2类。模型大小18k

模型	G1（1481）	G2（1271）	G3（1397）	G4（1750）	G5（2979）	single_0(蓝色3627)	single_1(黄色539）	single_2(白色66)	single_3(非11258)
train_100_lenet_zip_4_iter_50000.caffemodel	99.1897	99.5279	98.9979%	98.8571%	98.3552	98.9799%	98.1447%	98.4848%	99.1473%
train_100_lenet_zip_4_iter_100000.caffemodel	99.3923	99.6066	99.0694%	98.8571%	98.1202	98.842%	98.1447%	100%	99.2006 %
train_100_lenet_zip_6_iter_50000.caffemodel	99.5273	99.5279	99.141%	99.0286%	97.9523	98.7869%	99.0724%	93.9394%	99.1206%
train_100_lenet_zip_6_iter_100000.caffemodel	99.5273	99.6066	99.3558%	98.9143%	98.053	98.8144%	98.8868%	98.4848%	99.165%
train_100_lenet_zip_6_iter_150000.caffemodel	99.5949	99.6853	99.4273%	99.0286%	97.8181	98.6215%	98.8868%	98.4848%	99.2983%
train_100_lenet_zip_7_iter_50000.caffemodel	99.1897	99.6853	99.2126%	98.5143%	97.8516	98.7869%	98.1447%	93.9394%	99.0762%
train_100_lenet_zip_7_iter_100000.caffemodel	99.3248	99.6853	99.3558%	98.6286%	97.9859	98.8144%	98.7013%	95.4545%	99.1384%
train_100_lenet_zip_7_iter_150000.caffemodel	99.1897	99.6066	99.4989%	98.9143%	97.8516	98.4285%	98.7013%	93.9394%	99.2983%
train_100_lenet_zip_8_iter_50000.caffemodel	99.3923	99.3706	98.9979%	98.7429%	98.1537	98.9247%	98.5158%	93.9394%	99.0496%
train_100_lenet_zip_8_iter_100000.caffemodel	99.5273	99.6066	99.141%	98.6286%	98.1537	98.9523%	98.5158%	96.9697%	99.0673%
train_100_lenet_zip_8_iter_150000.caffemodel	99.4598	99.6853	99.4273%	98.7429%	97.9523	98.6766%	98.3302%	95.4545%	99.2361%
train_100_lenet_zip_9_iter_50000.caffemodel	99.5273	99.3706	98.9263%	98.5143%	98.1537	98.9247%	98.3302%	98.4848%	98.9696%
train_100_lenet_zip_9_iter_100000.caffemodel	99.4598	99.4493	99.141%	98.3429%	97.7845	98.8972%	97.9592%	96.9697%	98.9785%
train_100_lenet_zip_9_iter_150000.caffemodel	99.3923	99.3706	99.2126%	98.3429%	97.7174	98.6766%	97.5881%	96.9697%	99.1473%

Kindle君

关注

0
点赞
踩
1

收藏

觉得还不错? 一键收藏
0
评论
caffe训练自己的数据集——2. 开始训练

一、配置文件1. 网络结构henet_car_train_test.prototxt#name: "LeNet"layer { name: "mnist" type: "Data" top: "data" top: "label" include { phase: TRAIN } transform_param { scale: 0.00390625
复制链接

扫一扫