测试网络输出#0:accuracy = 1 - Always- Caffe

Posted

技术标签:

【中文标题】测试网络输出#0:accuracy = 1 - Always- Caffe【英文标题】:Test net output #0: accuracy = 1 - Always- Caffe 【发布时间】:2020-03-08 20:00:17 【问题描述】:

我总是得到同样的准确性。当我运行分类时,它总是显示 1 个标签。我浏览了很多文章,每个人都建议对数据进行洗牌。我使用 random.shuffle 做到了这一点,也尝试了 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 中的 833 张图像,validation_lmdb 中的其余图像。

训练日志:

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"

【问题讨论】:

有人可以帮忙吗?卡在这一步 【参考方案1】:

尝试使用 CaffeNet 的原始 caffemodel 进行微调。 然后就解决了。

【讨论】:

我在这里没有使用任何权重。尝试使用我自己的数据集创建模型。 如果您在不改变模型结构的情况下进行训练,使用 caffemodel 进行微调会使训练变得更容易。 我无法下载经过训练的模型,似乎 url 已关闭。 wgetdl.caffe.berkeleyvision.org/bvlc_reference_caffenet.caffemodel。还尝试通过 caffe 根文件夹,python scripts/download_model_binary.py models/bvlc_reference_caffenet/ 但没有帮助。我最终得到 IOError: [Errno socket error] [Errno 113] No route to host 服务器现在确实宕机了。等待服务器打开或寻找其他方式下载caffemodel 看起来服务器已停机很长时间。我试图通过其他链接搜索原始模型,但没有运气。有没有其他下载方式?

以上是关于测试网络输出#0:accuracy = 1 - Always- Caffe的主要内容,如果未能解决你的问题,请参考以下文章

Python accuracy_check 为翻转分类给出 0 结果

TensorFlow中loss与val_lossaccuracy和val_accuracy分别是什么含义

理解准确率(accuracy)精度(precision)查全率(recall)F1

keras中accuracy是怎么算出来的,为啥loss下降,accuracy不变甚至减小

多个模型在测试集上的Accuracy以及AUC指标可视化对比实战

Traffic Signs Recognition with 95% Accuracy using CNN&Keras