如何从caffe日志文件中显示纪元时间？

Question

在培训期间，我使用下面的脚本

将日志输出写入文件

~/caffe/build/tools/caffe train --solver=solver.prototxt -gpu 0 2>&1 | tee -a my_log.log

要提取它，我使用了python脚本：

python ~/caffe/tools/extra/parse_log.py ./my_model.log .

输出为

NumIters,Seconds,LearningRate,loss
0.0,2.538275,0.002,1.38629
20.0,56.872385,0.002,1.1333
40.0,106.103729,0.002,0.245525
60.0,144.78454,0.002,0.31936
80.0,168.363851,0.002,0.160776
100.0,191.590772,0.002,1.06693
120.0,215.290937,0.002,0.549629
140.0,238.70139,0.002,0.139573
160.0,262.053791,0.002,0.328959
180.0,286.324327,0.002,0.326179

使用batch_size是4.如何绘制训练损失图，其中x轴是epcho而y轴是损失？我只能绘制一个图形，x轴是迭代，y轴是损失。

Answer 1

epoch_no = iteration_no * size_of_iteration / total_number_of_samples， 哪里： iteration_no - 报告中的第一列， size_of_iteration在prototxt文件中定义（如果使用普通数据级别，则为数据级别的batch_size参数）， total_number_of_samples在您的数据库中已知样本。