caffe可视化工具的使用

1,使用parse_log.sh工具 解析出来train,和test两个工具 plot_training_log.py工具不可以使用,于是使用自己写的脚本工具进行处理

2,由于提取的文件都是以空格隔开,读入到计算机中是一个维的数据,所以用命令来更新文件

写一个sh脚本displace.sh

#!/bin/bash

sudo awk \'{gsub(" ",","); print $0 }\' test_log.txt

用于将双空格改成逗号

执行时候

./displace.sh |tee test_log_1.txt 用于将改变写入新文件中

3,提取数据并画图plot_test.py文件

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

#%matplotlib inline

result = pd.read_csv(\'test_log_1.txt\',names=[\'Iters\', \'Time\', \'Accuracy\'])

print(result[\'Iters\'])

print(result[\'Time\'])

print(result[\'Accuracy\'])

result[\'Iters\']=pd.to_numeric(result[\'Iters\'])

result[\'Time\']=pd.to_numeric(result[\'Time\'])

result[\'Accuracy\']=pd.to_numeric(result[\'Accuracy\'])

result.dtypes

fig = plt.figure()

ax = fig.add_subplot(1, 1, 1)

ax.plot(result[\'Accuracy\'].values,label=\'Accuracy\')

#ax.plot(result[\'Class\'].values,label=\'Class\')

#ax.plot(result[\'Obj\'].values,label=\'Obj\')

#ax.plot(result[\'No Obj\'].values,label=\'No Obj\')

#ax.plot(result[\'Avg Recall\'].values,label=\'Avg Recall\')

#ax.plot(result[\'count\'].values,label=\'count\')

ax.legend(loc=\'best\')

ax.set_title(\'The Accuracy curves\')

#ax.set_title(\'The Region Avg IOU curves\')

ax.set_xlabel(\'batches\')

#fig.savefig(\'Avg IOU\')

fig.savefig(\'Accuracy\')