Question

我总是得到相同的精度。当我运行分类时，它总是显示1标签。我浏览了许多文章，每个人都建议改组数据。我使用random.shuffle做到了这一点，还尝试了convert_imageset脚本，但没有帮助。请在下面找到我的Solver.protoxt和caffenet_train.prototxt。我的数据集中有1000张图像。 train_lmdb中有833张图片，其余的则是validate_lmdb中的图片。

培训日志：

I1112 22:41:26.373661 10633 solver.cpp:347] Iteration 1184, Testing net (#0)
I1112 22:41:26.828955 10633 solver.cpp:414]     Test net output #0: accuracy = 1
I1112 22:41:26.829105 10633 solver.cpp:414]     Test net output #1: loss = 4.05117e-05 (* 1 = 4.05117e-05 loss)
I1112 22:41:26.952340 10656 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:28.697041 10655 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:30.889508 10655 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:32.288192 10633 solver.cpp:347] Iteration 1200, Testing net (#0)
I1112 22:41:32.716845 10633 solver.cpp:414]     Test net output #0: accuracy = 1
I1112 22:41:32.716941 10633 solver.cpp:414]     Test net output #1: loss = 4.08e-05 (* 1 = 4.08e-05 loss)
I1112 22:41:32.861697 10655 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:33.050954 10633 solver.cpp:239] Iteration 1200 (2.6885 iter/s, 18.5978s/50 iters), loss = 0.000119432
I1112 22:41:33.051054 10633 solver.cpp:258]     Train net output #0: loss = 0.000119432 (* 1 = 0.000119432 loss)
I1112 22:41:33.051067 10633 sgd_solver.cpp:112] Iteration 1200, lr = 1e-15
I1112 22:41:35.700759 10655 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:37.869782 10655 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:38.169018 10633 solver.cpp:347] Iteration 1216, Testing net (#0)
I1112 22:41:38.396162 10656 data_layer.cpp:73] Restarting data prefetching from start.
I1112 22:41:38.613301 10633 solver.cpp:414]     Test net output #0: accuracy = 1
I1112 22:41:38.613348 10633 solver.cpp:414]     Test net output #1: loss = 4.09327e-05 (* 1 = 4.09327e-05 loss)

solver.prototxt：

net: "caffenet_train.prototxt"
test_iter: 16
test_interval: 16
base_lr: 0.001
lr_policy: "step"
gamma: 0.1
stepsize: 100
display: 50
max_iter: 2000
momentum: 0.9
weight_decay: 0.0005
snapshot: 500
snapshot_prefix: "output/caffe_model"
solver_mode: GPU

caffenet_train.prototxt

name: "CaffeNet"
layer {
 name: "data"
 type: "Data"
 top: "data"
 top: "label"
 include {
   phase: TRAIN
 }
 transform_param {
   mirror: true
   crop_size: 227
   mean_file: "output/mean.binaryproto"
 }
 data_param {
   source: "output/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: "output/mean.binaryproto"
 }
 data_param {
   source: "output/validation_lmdb"
   batch_size: 10
   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: 2
   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"
}

Answer 1

尝试使用CaffeNet的原始caffemodel进行微调。然后它将解决。

测试净输出＃0：精度= 1-始终-Caffe

1 个答案: