Faster-Rcnn的loss曲线可视化

       由于要写论文需要画loss曲线，查找网上的loss曲线可视化的方法发现大多数是基于Imagenat的一些方法，在运用到Faster-Rcnn上时没法用，本人不怎么会编写代码，所以想到能否用python直接写一个代码，读取txt然后画出来，参考大神们的博客，然后总和总算一下午时间，搞出来了，大牛们不要见笑。

        首先，在训练Faster-Rcnn时会自己生成log文件，大概在/py-faster-rcnn/experiments/logs文件下，把他直接拿出来,放在任意位置即可，因为是txt格式，可以直接用，如果嫌麻烦重命名1.txt.接下来就是编写程序了

一下为log基本的格式

I0530 08:54:19.183091 10143 solver.cpp:229] Iteration 22000, loss = 0.173712
I0530 08:54:19.183137 10143 solver.cpp:245]     Train net output #0: rpn_cls_loss = 0.101713 (* 1 = 0.101713 loss)
I0530 08:54:19.183145 10143 solver.cpp:245]     Train net output #1: rpn_loss_bbox = 0.071999 (* 1 = 0.071999 loss)
I0530 08:54:19.183148 10143 sgd_solver.cpp:106] Iteration 22000, lr = 0.001

通过发现，我们只需获得 Iteration 和loss就行

#!/usr/bin/env pythonimport osimport sysimport numpy as npimport matplotlib.pyplot as pltimport mathimport reimport pylabfrom pylab import figure, show, legendfrom mpl_toolkits.axes_grid1 import host_subplot# read the log filefp = open('2.txt', 'r')train_iterations = []train_loss = []test_iterations = []#test_accuracy = []for ln in fp:  # get train_iterations and train_loss  if '] Iteration ' in ln and 'loss = ' in ln:    arr = re.findall(r'ion \b\d+\b,',ln)    train_iterations.append(int(arr[0].strip(',')[4:]))    train_loss.append(float(ln.strip().split(' = ')[-1]))    fp.close()host = host_subplot(111)plt.subplots_adjust(right=0.8) # ajust the right boundary of the plot window#par1 = host.twinx()# set labelshost.set_xlabel("iterations")host.set_ylabel("RPN loss")#par1.set_ylabel("validation accuracy")# plot curvesp1, = host.plot(train_iterations, train_loss, label="train RPN loss")#p2, = par1.plot(test_iterations, test_accuracy, label="validation accuracy")# set location of the legend, # 1->rightup corner, 2->leftup corner, 3->leftdown corner# 4->rightdown corner, 5->rightmid ...host.legend(loc=1)# set label colorhost.axis["left"].label.set_color(p1.get_color())#par1.axis["right"].label.set_color(p2.get_color())# set the range of x axis of host and y axis of par1host.set_xlim([-1500,60000])host.set_ylim([0., 1.6])plt.draw()plt.show()

绘图结果

参考博客地址：

http://blog.csdn.net/YhL_Leo/article/details/51774966