这是我在训练自己的模型时得到的结果
I0510 20:53:16.677439 3591 solver.cpp:337] Iteration 0, Testing net (#0)I0510 20:57:20.822933 3591 solver.cpp:404] Test net output #0: accuracy = 3.78788e-05I0510 20:57:20.823001 3591 solver.cpp:404] Test net output #1: loss = 9.27223 (* 1 = 9.27223 loss)I0510 20:57:21.423084 3591 solver.cpp:228] Iteration 0, loss = 9.29181I0510 20:57:21.423110 3591 solver.cpp:244] Train net output #0: loss = 9.29181 (* 1 = 9.29181 loss)I0510 20:57:21.423120 3591 sgd_solver.cpp:106] Iteration 0, lr = 0.001I0510 21:06:57.498831 3591 solver.cpp:337] Iteration 1000, Testing net (#0)I0510 21:10:59.477396 3591 solver.cpp:404] Test net output #0: accuracy = 0.00186553I0510 21:10:59.477463 3591 solver.cpp:404] Test net output #1: loss = 8.86572 (* 1 = 8.86572 loss)I0510 21:20:35.828510 3591 solver.cpp:337] Iteration 2000, Testing net (#0)I0510 21:24:42.838196 3591 solver.cpp:404] Test net output #0: accuracy = 0.00144886I0510 21:24:42.838245 3591 solver.cpp:404] Test net output #1: loss = 8.83859 (* 1 = 8.83859 loss)I0510 21:24:43.412120 3591 solver.cpp:228] Iteration 2000, loss = 8.81461I0510 21:24:43.412145 3591 solver.cpp:244] Train net output #0: loss = 8.81461 (* 1 = 8.81461 loss)I0510 21:24:43.412150 3591 sgd_solver.cpp:106] Iteration 2000, lr = 0.001I0510 21:38:50.990823 3591 solver.cpp:337] Iteration 3000, Testing net (#0)I0510 21:42:52.918418 3591 solver.cpp:404] Test net output #0: accuracy = 0.00140152I0510 21:42:52.918493 3591 solver.cpp:404] Test net output #1: loss = 8.81789 (* 1 = 8.81789 loss)I0510 22:00:09.519151 3591 solver.cpp:337] Iteration 4000, Testing net (#0)I0510 22:09:13.918016 3591 solver.cpp:404] Test net output #0: accuracy = 0.00149621I0510 22:09:13.918102 3591 solver.cpp:404] Test net output #1: loss = 8.80909 (* 1 = 8.80909 loss)I0510 22:09:15.127683 3591 solver.cpp:228] Iteration 4000, loss = 8.8597I0510 22:09:15.127722 3591 solver.cpp:244] Train net output #0: loss = 8.8597 (* 1 = 8.8597 loss)I0510 22:09:15.127729 3591 sgd_solver.cpp:106] Iteration 4000, lr = 0.001I0510 22:28:39.320019 3591 solver.cpp:337] Iteration 5000, Testing net (#0)I0510 22:37:43.847064 3591 solver.cpp:404] Test net output #0: accuracy = 0.00118371I0510 22:37:43.847173 3591 solver.cpp:404] Test net output #1: loss = 8.80527 (* 1 = 8.80527 loss)I0510 23:58:17.120088 3591 solver.cpp:454] Snapshotting to binary proto file /home/wang/caffe-master/examples/NN2_iter_10000.caffemodelI0510 23:58:17.238307 3591 sgd_solver.cpp:273] Snapshotting solver state to binary proto file /home/wang/caffe-master/examples/NN2_iter_10000.solverstateI0510 23:58:17.491825 3591 solver.cpp:337] Iteration 10000, Testing net (#0)I0511 00:02:19.412715 3591 solver.cpp:404] Test net output #0: accuracy = 0.00186553I0511 00:02:19.412762 3591 solver.cpp:404] Test net output #1: loss = 8.79114 (* 1 = 8.79114 loss)I0511 00:02:19.986547 3591 solver.cpp:228] Iteration 10000, loss = 8.83457I0511 00:02:19.986570 3591 solver.cpp:244] Train net output #0: loss = 8.83457 (* 1 = 8.83457 loss)I0511 00:02:19.986578 3591 sgd_solver.cpp:106] Iteration 10000, lr = 0.001I0511 00:11:55.546052 3591 solver.cpp:337] Iteration 11000, Testing net (#0)I0511 00:15:57.490486 3591 solver.cpp:404] Test net output #0: accuracy = 0.00164773I0511 00:15:57.490532 3591 solver.cpp:404] Test net output #1: loss = 8.78702 (* 1 = 8.78702 loss)I0511 00:25:33.666496 3591 solver.cpp:337] Iteration 12000, Testing net (#0)I0511 00:29:35.603062 3591 solver.cpp:404] Test net output #0: accuracy = 0.0016572I0511 00:29:35.603109 3591 solver.cpp:404] Test net output #1: loss = 8.7848 (* 1 = 8.7848 loss)I0511 00:29:36.177078 3591 solver.cpp:228] Iteration 12000, loss = 9.00561I0511 00:29:36.177105 3591 solver.cpp:244] Train net output #0: loss = 9.00561 (* 1 = 9.00561 loss)I0511 00:29:36.177114 3591 sgd_solver.cpp:106] Iteration 12000, lr = 0.001I0511 00:39:11.729369 3591 solver.cpp:337] Iteration 13000, Testing net (#0)I0511 00:43:13.678067 3591 solver.cpp:404] Test net output #0: accuracy = 0.001875I0511 00:43:13.678113 3591 solver.cpp:404] Test net output #1: loss = 8.78359 (* 1 = 8.78359 loss)I0511 00:52:49.851985 3591 solver.cpp:337] Iteration 14000, Testing net (#0)I0511 00:56:51.767343 3591 solver.cpp:404] Test net output #0: accuracy = 0.00154356I0511 00:56:51.767390 3591 solver.cpp:404] Test net output #1: loss = 8.77998 (* 1 = 8.77998 loss)I0511 00:56:52.341564 3591 solver.cpp:228] Iteration 14000, loss = 8.83385I0511 00:56:52.341591 3591 solver.cpp:244] Train net output #0: loss = 8.83385 (* 1 = 8.83385 loss)I0511 00:56:52.341598 3591 sgd_solver.cpp:106] Iteration 14000, lr = 0.001I0511 02:14:38.224290 3591 solver.cpp:454] Snapshotting to binary proto file /home/wang/caffe-master/examples/NN2_iter_20000.caffemodelI0511 02:14:38.735008 3591 sgd_solver.cpp:273] Snapshotting solver state to binary proto file /home/wang/caffe-master/examples/NN2_iter_20000.solverstateI0511 02:14:38.805809 3591 solver.cpp:337] Iteration 20000, Testing net (#0)I0511 02:18:40.681993 3591 solver.cpp:404] Test net output #0: accuracy = 0.00179924I0511 02:18:40.682086 3591 solver.cpp:404] Test net output #1: loss = 8.78129 (* 1 = 8.78129 loss)I0511 02:18:41.255969 3591 solver.cpp:228] Iteration 20000, loss = 8.82502I0511 02:18:41.255995 3591 solver.cpp:244] Train net output #0: loss = 8.82502 (* 1 = 8.82502 loss)I0511 02:18:41.256001 3591 sgd_solver.cpp:106] Iteration 20000, lr = 0.001I0511 04:30:58.924096 3591 solver.cpp:454] Snapshotting to binary proto file /home/wang/caffe-master/examples/NN2_iter_30000.caffemodelI0511 04:31:00.742739 3591 sgd_solver.cpp:273] Snapshotting solver state to binary proto file /home/wang/caffe-master/examples/NN2_iter_30000.solverstateI0511 04:31:01.151980 3591 solver.cpp:337] Iteration 30000, Testing net (#0)I0511 04:35:03.075263 3591 solver.cpp:404] Test net output #0: accuracy = 0.00186553I0511 04:35:03.075307 3591 solver.cpp:404] Test net output #1: loss = 8.77867 (* 1 = 8.77867 loss)I0511 04:35:03.649479 3591 solver.cpp:228] Iteration 30000, loss = 8.82915I0511 04:35:03.649507 3591 solver.cpp:244] Train net output #0: loss = 8.82915 (* 1 = 8.82915 loss)I0511 04:35:03.649513 3591 sgd_solver.cpp:106] Iteration 30000, lr = 0.001I0511 07:55:36.848265 3591 solver.cpp:337] Iteration 45000, Testing net (#0)I0511 07:59:38.834043 3591 solver.cpp:404] Test net output #0: accuracy = 0.00179924I0511 07:59:38.834095 3591 solver.cpp:404] Test net output #1: loss = 8.77432 (* 1 = 8.77432 loss)I0511 09:03:48.141854 3591 solver.cpp:454] Snapshotting to binary proto file /home/wang/caffe-master/examples/NN2_iter_50000.caffemodelI0511 09:03:49.736464 3591 sgd_solver.cpp:273] Snapshotting solver state to binary proto file /home/wang/caffe-master/examples/NN2_iter_50000.solverstateI0511 09:03:49.797582 3591 solver.cpp:337] Iteration 50000, Testing net (#0)I0511 09:07:51.777150 3591 solver.cpp:404] Test net output #0: accuracy = 0.001875I0511 09:07:51.777207 3591 solver.cpp:404] Test net output #1: loss = 8.77058 (* 1 = 8.77058 loss)I0511 09:07:52.351323 3591 solver.cpp:228] Iteration 50000, loss = 9.11435I0511 09:07:52.351351 3591 solver.cpp:244] Train net output #0: loss = 9.11435 (* 1 = 9.11435 loss)I0511 09:07:52.351357 3591 sgd_solver.cpp:106] Iteration 50000, lr = 0.001I0511 09:17:28.188742 3591 solver.cpp:337] Iteration 51000, Testing net (#0)I0511 09:21:30.200623 3591 solver.cpp:404] Test net output #0: accuracy = 0.00186553I0511 09:21:30.200716 3591 solver.cpp:404] Test net output #1: loss = 8.77026 (* 1 = 8.77026 loss)I0511 09:31:06.596501 3591 solver.cpp:337] Iteration 52000, Testing net (#0)I0511 09:35:08.580215 3591 solver.cpp:404] Test net output #0: accuracy = 0.00182765I0511 09:35:08.580313 3591 solver.cpp:404] Test net output #1: loss = 8.76917 (* 1 = 8.76917 loss)I0511 09:35:09.154428 3591 solver.cpp:228] Iteration 52000, loss = 8.89758I0511 09:35:09.154453 3591 solver.cpp:244] Train net output #0: loss = 8.89758 (* 1 = 8.89758 loss)I0511 09:35:09.154459 3591 sgd_solver.cpp:106] Iteration 52000, lr = 0.001I0511 09:44:44.906309 3591 solver.cpp:337] Iteration 53000, Testing net (#0)I0511 09:48:46.866353 3591 solver.cpp:404] Test net output #0: accuracy = 0.00185606I0511 09:48:46.866430 3591 solver.cpp:404] Test net output #1: loss = 8.7708 (* 1 = 8.7708 loss)I0511 09:58:23.097244 3591 solver.cpp:337] Iteration 54000, Testing net (#0)I0511 10:02:25.056555 3591 solver.cpp:404] Test net output #0: accuracy = 0.00192235I0511 10:02:25.056605 3591 solver.cpp:404] Test net output #1: loss = 8.76884 (* 1 = 8.76884 loss)I0511 10:02:25.630312 3591 solver.cpp:228] Iteration 54000, loss = 8.90552I0511 10:02:25.630337 3591 solver.cpp:244] Train net output #0: loss = 8.90552 (* 1 = 8.90552 loss)I0511 10:02:25.630342 3591 sgd_solver.cpp:106] Iteration 54000, lr = 0.001I0511 14:44:51.563555 3591 solver.cpp:337] Iteration 75000, Testing net (#0)I0511 14:48:53.573640 3591 solver.cpp:404] Test net output #0: accuracy = 0.0016572I0511 14:48:53.573724 3591 solver.cpp:404] Test net output #1: loss = 8.76967 (* 1 = 8.76967 loss)I0511 14:58:30.080453 3591 solver.cpp:337] Iteration 76000, Testing net (#0)I0511 15:02:32.076011 3591 solver.cpp:404] Test net output #0: accuracy = 0.001875I0511 15:02:32.076077 3591 solver.cpp:404] Test net output #1: loss = 8.7695 (* 1 = 8.7695 loss)I0511 15:02:32.650342 3591 solver.cpp:228] Iteration 76000, loss = 9.0084I0511 15:02:32.650367 3591 solver.cpp:244] Train net output #0: loss = 9.0084 (* 1 = 9.0084 loss)I0511 15:02:32.650373 3591 sgd_solver.cpp:106] Iteration 76000, lr = 0.001I0511 15:12:08.597450 3591 solver.cpp:337] Iteration 77000, Testing net (#0)I0511 15:16:10.636613 3591 solver.cpp:404] Test net output #0: accuracy = 0.00181818I0511 15:16:10.636693 3591 solver.cpp:404] Test net output #1: loss = 8.76889 (* 1 = 8.76889 loss)I0511 15:25:47.167667 3591 solver.cpp:337] Iteration 78000, Testing net (#0)I0511 15:29:49.204596 3591 solver.cpp:404] Test net output #0: accuracy = 0.00185606I0511 15:29:49.204649 3591 solver.cpp:404] Test net output #1: loss = 8.77059 (* 1 = 8.77059 loss)I0511 15:29:49.779094 3591 solver.cpp:228] Iteration 78000, loss = 8.73139I0511 15:29:49.779119 3591 solver.cpp:244] Train net output #0: loss = 8.73139 (* 1 = 8.73139 loss)I0511 15:29:49.779124 3591 sgd_solver.cpp:106] Iteration 78000, lr = 0.001I0511 15:39:25.730358 3591 solver.cpp:337] Iteration 79000, Testing net (#0)I0511 15:43:27.756417 3591 solver.cpp:404] Test net output #0: accuracy = 0.00192235I0511 15:43:27.756485 3591 solver.cpp:404] Test net output #1: loss = 8.76846 (* 1 = 8.76846 loss)I0511 15:53:04.419961 3591 solver.cpp:454] Snapshotting to binary proto file /home/wang/caffe-master/examples/NN2_iter_80000.caffemodelI0511 15:53:06.138357 3591 sgd_solver.cpp:273] Snapshotting solver state to binary proto file /home/wang/caffe-master/examples/NN2_iter_80000.solverstateI0511 15:53:06.519551 3591 solver.cpp:337] Iteration 80000, Testing net (#0)I0511 15:57:08.719681 3591 solver.cpp:404] Test net output #0: accuracy = 0.00164773I0511 15:57:08.719737 3591 solver.cpp:404] Test net output #1: loss = 8.77126 (* 1 = 8.77126 loss)I0511 15:57:09.294163 3591 solver.cpp:228] Iteration 80000, loss = 8.56576I0511 15:57:09.294188 3591 solver.cpp:244] Train net output #0: loss = 8.56576 (* 1 = 8.56576 loss)I0511 15:57:09.294193 3591 sgd_solver.cpp:106] Iteration 80000, lr = 0.001I0511 17:01:19.190099 3591 solver.cpp:337] Iteration 85000, Testing net (#0)I0511 17:05:21.148668 3591 solver.cpp:404] Test net output #0: accuracy = 0.00185606I0511 17:05:21.148733 3591 solver.cpp:404] Test net output #1: loss = 8.77196 (* 1 = 8.77196 loss)I0511 17:14:57.670343 3591 solver.cpp:337] Iteration 86000, Testing net (#0)I0511 17:18:59.659850 3591 solver.cpp:404] Test net output #0: accuracy = 0.00181818I0511 17:18:59.659907 3591 solver.cpp:404] Test net output #1: loss = 8.77126 (* 1 = 8.77126 loss)I0511 17:19:00.234335 3591 solver.cpp:228] Iteration 86000, loss = 8.72875I0511 17:19:00.234359 3591 solver.cpp:244] Train net output #0: loss = 8.72875 (* 1 = 8.72875 loss)I0511 17:19:00.234364 3591 sgd_solver.cpp:106] Iteration 86000, lr = 0.001I0511 17:28:36.196920 3591 solver.cpp:337] Iteration 87000, Testing net (#0)I0511 17:32:38.181174 3591 solver.cpp:404] Test net output #0: accuracy = 0.00181818I0511 17:32:38.181231 3591 solver.cpp:404] Test net output #1: loss = 8.771 (* 1 = 8.771 loss)I0511 17:42:14.658293 3591 solver.cpp:337] Iteration 88000, Testing net (#0)I0511 17:46:16.614358 3591 solver.cpp:404] Test net output #0: accuracy = 0.00188447I0511 17:46:16.614415 3591 solver.cpp:404] Test net output #1: loss = 8.76964 (* 1 = 8.76964 loss)I0511 17:46:17.188212 3591 solver.cpp:228] Iteration 88000, loss = 8.80409I0511 17:46:17.188233 3591 solver.cpp:244] Train net output #0: loss = 8.80409 (* 1 = 8.80409 loss)I0511 17:46:17.188240 3591 sgd_solver.cpp:106] Iteration 88000, lr = 0.001I0511 17:55:53.358322 3591 solver.cpp:337] Iteration 89000, Testing net (#0)I0511 17:59:55.305763 3591 solver.cpp:404] Test net output #0: accuracy = 0.00186553I0511 17:59:55.305868 3591 solver.cpp:404] Test net output #1: loss = 8.76909 (* 1 = 8.76909 loss)I0511 18:09:31.658655 3591 solver.cpp:454] Snapshotting to binary proto file /home/wang/caffe-master/examples/NN2_iter_90000.caffemodelI0511 18:09:33.138741 3591 sgd_solver.cpp:273] Snapshotting solver state to binary proto file /home/wang/caffe-master/examples/NN2_iter_90000.solverstateI0511 18:09:33.691995 3591 solver.cpp:337] Iteration 90000, Testing net (#0)I0511 18:13:35.626065 3591 solver.cpp:404] Test net output #0: accuracy = 0.00168561I0511 18:13:35.626148 3591 solver.cpp:404] Test net output #1: loss = 8.76973 (* 1 = 8.76973 loss)I0511 18:13:36.200448 3591 solver.cpp:228] Iteration 90000, loss = 8.97326I0511 18:13:36.200469 3591 solver.cpp:244] Train net output #0: loss = 8.97326 (* 1 = 8.97326 loss)I0511 18:13:36.200474 3591 sgd_solver.cpp:106] Iteration 90000, lr = 0.001I0511 19:31:23.715662 3591 solver.cpp:337] Iteration 96000, Testing net (#0)I0511 19:35:25.677780 3591 solver.cpp:404] Test net output #0: accuracy = 0.00188447I0511 19:35:25.677836 3591 solver.cpp:404] Test net output #1: loss = 8.7695 (* 1 = 8.7695 loss)I0511 19:35:26.251850 3591 solver.cpp:228] Iteration 96000, loss = 8.74232I0511 19:35:26.251875 3591 solver.cpp:244] Train net output #0: loss = 8.74232 (* 1 = 8.74232 loss)I0511 19:35:26.251880 3591 sgd_solver.cpp:106] Iteration 96000, lr = 0.001I0511 19:45:02.057610 3591 solver.cpp:337] Iteration 97000, Testing net (#0)I0511 19:49:04.029269 3591 solver.cpp:404] Test net output #0: accuracy = 0.00188447I0511 19:49:04.029357 3591 solver.cpp:404] Test net output #1: loss = 8.77655 (* 1 = 8.77655 loss)I0511 19:58:40.265120 3591 solver.cpp:337] Iteration 98000, Testing net (#0)I0511 20:02:42.182787 3591 solver.cpp:404] Test net output #0: accuracy = 0.00183712I0511 20:02:42.182859 3591 solver.cpp:404] Test net output #1: loss = 8.77069 (* 1 = 8.77069 loss)I0511 20:02:42.756922 3591 solver.cpp:228] Iteration 98000, loss = 8.61745I0511 20:02:42.756944 3591 solver.cpp:244] Train net output #0: loss = 8.61745 (* 1 = 8.61745 loss)由于代码字符数的限制，我不得不删除日志的一些行。不过，这并不重要。正如你所看到的，”Iteration 98000“和”Iteration 0“之间没有区别。我对这种情况感到非常困惑。
这是我的模型架构
name: "NN2"layer { name: "data" type: "Data" top: "data" top: "label" include { phase: TRAIN } transform_param { mirror: true mean_file :"/home/jiayi-wei/caffe/examples/NN2/image_train_mean.binaryproto" data_param { source: "/home/jiayi-wei/caffe/examples/NN2/img_train_lmdb" batch_size: 30 backend: LMDB }}layer { name: "data" type: "Data" top: "data" top: "label" include { phase: TEST } transform_param { mirror: false mean_file :"/home/jiayi-wei/caffe/examples/NN2/image_train_mean.binaryproto" data_param { source: "/home/jiayi-wei/caffe/examples/NN2/img_val_lmdb" batch_size: 11 backend: LMDB }}#第一层layer { name: "conv11" type: "Convolution" bottom: "data" top: "conv11" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 64 kernel_size: 3 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "relu11" type: "ReLU" bottom: "conv11" top: "conv11"}layer { name: "conv12" type: "Convolution" bottom: "conv11" top: "conv12" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 128 kernel_size: 3 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "relu12" type: "ReLU" bottom: "conv12" top: "conv12"}layer { name: "pool1" type: "Pooling" bottom: "conv12" top: "pool1" pooling_param { pool: MAX kernel_size: 2 stride: 2 }}#第二层layer { name: "conv21" type: "Convolution" bottom: "pool1" top: "conv21" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 64 kernel_size: 3 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "relu21" type: "ReLU" bottom: "conv21" top: "conv21"}layer { name: "conv22" type: "Convolution" bottom: "conv21" top: "conv22" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 128 kernel_size: 3 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "relu22" type: "ReLU" bottom: "conv22" top: "conv22"}layer { name: "pool2" type: "Pooling" bottom: "conv22" top: "pool2" pooling_param { pool: MAX kernel_size: 2 stride: 2 }}#第三层layer { name: "conv31" type: "Convolution" bottom: "pool2" top: "conv31" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 128 pad:1 kernel_size: 3 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "relu31" type: "ReLU" bottom: "conv31" top: "conv31"}layer { name: "conv32" type: "Convolution" bottom: "conv31" top: "conv32" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 128 pad:1 kernel_size: 3 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "relu32" type: "ReLU" bottom: "conv32" top: "conv32"}layer { name: "pool3" type: "Pooling" bottom: "conv32" top: "pool3" pooling_param { pool: MAX pad:1 kernel_size: 2 stride: 2 }}#第四层layer { name: "conv41" type: "Convolution" bottom: "pool3" top: "conv41" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 256 pad:1 kernel_size: 3 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "relu41" type: "ReLU" bottom: "conv41" top: "conv41"}layer { name: "conv42" type: "Convolution" bottom: "conv41" top: "conv42" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 256 pad:1 kernel_size: 3 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "relu42" type: "ReLU" bottom: "conv42" top: "conv42"}layer { name: "conv43" type: "Convolution" bottom: "conv42" top: "conv43" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 256 pad:1 kernel_size: 3 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "relu43" type: "ReLU" bottom: "conv43" top: "conv43"}layer { name: "pool4" type: "Pooling" bottom: "conv43" top: "pool4" pooling_param { pool: MAX kernel_size: 2 stride: 2 }}#第五层layer { name: "conv51" type: "Convolution" bottom: "pool4" top: "conv51" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 256 pad:1 kernel_size: 3 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "relu51" type: "ReLU" bottom: "conv51" top: "conv51"}layer { name: "conv52" type: "Convolution" bottom: "conv51" top: "conv52" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 256 pad:1 kernel_size: 3 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "relu52" type: "ReLU" bottom: "conv52" top: "conv52"}layer { name: "conv53" type: "Convolution" bottom: "conv52" top: "conv53" param { lr_mult: 1 decay_mult: 1 } param { lr_mult: 2 decay_mult: 0 } convolution_param { num_output: 256 pad:1 kernel_size: 3 stride: 1 weight_filler { type: "gaussian" std: 0.01 } bias_filler { type: "constant" value: 0 } }}layer { name: "pool5" type: "Pooling" bottom: "conv53" top: "pool5" pooling_param { pool: AVE pad:1 kernel_size: 2 stride: 2 }}#Dropout和全连接层layer { name: "dropout" type: "Dropout" bottom: "pool5" top: "pool5" dropout_param { dropout_ratio: 0.5 }}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:1000 weight_filler { type: "gaussian" std: 0.005 } bias_filler { type: "constant" value: 1 } }}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:10575 weight_filler { type: "gaussian" std: 0.005 } bias_filler { type: "constant" value: 1 } }}layer { name: "accuracy" type: "Accuracy" bottom: "fc7" bottom: "label" top: "accuracy" include { phase: TEST }}layer { name: "SoftMax" type: "SoftmaxWithLoss" bottom: "fc7" bottom: "label" top: "SoftMax"}以下是我的求解器配置。我已经将base_lr更改为＂0.001＂
net: "train_val.prototxt"test_iter: 10000test_interval: 1000base_lr: ０．００１lr_policy: "step"gamma: 0.1stepsize: 100000display: 20max_iter: 450000momentum: 0.9weight_decay: 0.0005snapshot: 10000snapshot_prefix: "/home/jiayi-wei/caffe/examples/NN2"solver_mode: GPU我尝试过更改一些参数，并且我已经尝试过从拥有三个“conv”层的块中删除一个“conv”层。然而，结果始终如图所示保持不变。
请告诉我如何解决这个问题？谢谢
回答：
从你的日志来看，似乎你的模型在训练过程中倾向于持续预测不变的标签，也就是说，你的训练过程出现了发散。我建议你进行以下检查。
- 检查转换训练/验证lmdb数据时的标签。在你的CNN架构中，Dropout层最好放在全连接层，即“fc6”之下，而不是池化层“pool5”之下。
- 我不知道你在训练过程中是如何采样训练数据的。原则上，如果你只使用Softmax成本（多项式交叉熵损失），你应该在准备训练/验证lmdb数据时打乱你的训练数据，并设置一个适当大的批量大小，例如在训练时设置为256。
- 你的学习率（base_lr）可能太大，你可以进一步将其从0.001降低到0.0001，但我注意到CASIA WebFace基线（http://arxiv.org/abs/1411.7923）使用了0.01的学习率，而你的输入数据规模、激活函数、模型的深度和宽度与其相似，因此不太可能是由学习率引起的。（但你应该检查权重初始化方法是否有很大影响。）
- 尝试使用较小的卷积核大小。有时这可能有助于减少由于卷积核与其对应输入特征图之间的对齐问题导致的信息损失。
顺便说一下，你正在训练一个包含10575个类别的分类任务，每个类别只有大约40个训练样本，因此在某种程度上，训练数据是不足的。因此，像基线工作一样，为了增强模型区分相同和不同样本的能力，最好在Softmax成本之外再添加一个对比成本。
参考资料 Sun Y, Chen Y, Wang X, et al. Deep learning face representation by joint identification-verification[C]//Advances in Neural Information Processing Systems. 2014: 1988-1996.
