caffe两种绘制loss曲线的方法

我搜索了一下，然后发现一种是自己写然后绘制，

#这段代码可以在没有桌面的服务器上运行，历时两天终于搞定了，需要注意的是solver中路径参数都需要为全路径，显示所在文件夹的全路径命令为 pwd。
#如果出现中文解析问题，请删除中文注释。
#!usr/bin/env python
#coding:utf-8
from pylab import *
#import numpy as np
import matplotlib
matplotlib.use('Agg')
import sys,os
import matplotlib.pyplot  as plt
caffe_root = '/home/hugo/caffe/'
sys.path.insert(0, caffe_root + 'python')
import caffe
#caffe.set_device(all)
caffe.set_mode_cpu()
solver = caffe.SGDSolver('/home/hugo/caffe/examples/mnist/lenet_solver.prototxt')

#max_iter
niter =1000
display_iter = 100
test_iter = 100
test_interval = 500
train_loss = zeros(ceil(niter * 1.0 / display_iter))
# test loss
test_loss = zeros(ceil(niter * 1.0 / test_interval))
# test accuracy
test_acc = zeros(ceil(niter * 1.0 / test_interval))
solver.step(1)
_train_loss = 0; _test_loss = 0; _accuracy = 0
for it in range(niter):
    # 进行一次解算
    solver.step(1)
    # 计算train loss
    _train_loss += solver.net.blobs['loss'].data
    if it % display_iter == 0:
        # 计算平均train loss
        train_loss[it // display_iter] = _train_loss / display_iter
        _train_loss = 0

    if it % test_interval == 0:
        for test_it in range(test_iter):
            # 进行一次测试
            solver.test_nets[0].forward()
            # 计算test loss
            _test_loss += solver.test_nets[0].blobs['loss'].data
            # 计算test accuracy
            _accuracy += solver.test_nets[0].blobs['accuracy'].data
        # 计算平均test loss
        test_loss[it / test_interval] = _test_loss / test_iter
        # 计算平均test accuracy
        test_acc[it / test_interval] = _accuracy / test_iter
        _test_loss = 0
        _accuracy = 0

# 绘制train loss、test loss和accuracy曲线
print '\nplot the train loss and test accuracy\n'


# train loss -> 绿色
plt.plot(display_iter * arange(len(train_loss)), train_loss, 'g',label='train_loss')
# test loss -> 黄色
plt.plot(test_interval * arange(len(test_loss)), test_loss, 'y',label='test_loss')
# test accuracy -> 红色
plt.plot(test_interval * arange(len(test_acc)), test_acc, 'r',label='test_acc')

plt.xlabel('iteration')
plt.ylabel('loss')

plt.savefig('/home/hugo/caffe/examples/mnist/lenet.png')　　

运行上述代码时如果出现      TypeError: 'numpy.float64' object cannot be interpreted as an index

请执行sudo pip install -U numpy==1.11.0，降低numpy版本就可以了

或者，这段代码也可以运行，但是由于调用了twinx()，需要桌面，所以我在服务器上总跑不通。

import numpy as np
import matplotlib.pyplot as plt
import sys,os
caffe_root = '/home/tyd/caffe/'  # this file should be run from {caffe_root}/examples (otherwise change this line)
sys.path.insert(0, caffe_root + 'python')
import caffe

#caffe.set_device(0)
caffe.set_mode_cpu()
solver = caffe.SGDSolver('/home/tyd/caffe/examples/mnist/lenet_solver.prototxt')


niter =1000
test_interval = 200
train_loss = np.zeros(niter)
test_acc = np.zeros(int(np.ceil(niter / test_interval)))

# the main solver loop
for it in range(niter):
    solver.step(1)  # SGD by Caffe
    
    # store the train loss
    train_loss[it] = solver.net.blobs['loss'].data
    solver.test_nets[0].forward(start='conv1')
    
    if it % test_interval == 0:
        acc=solver.test_nets[0].blobs['accuracy'].data
        print 'Iteration', it, 'testing...','accuracy:',acc
        test_acc[it // test_interval] = acc

print test_acc
_, ax1 = plt.subplots()
ax2 = ax1.twinx()
ax1.plot(np.arange(niter), train_loss)
ax2.plot(test_interval * np.arange(len(test_acc)), test_acc, 'r')
ax1.set_xlabel('iteration')
ax1.set_ylabel('train loss')
ax2.set_ylabel('test accuracy')
plt.show()

还有一种是利用caffe自带的工具，像下面这篇博客里写的http://blog.csdn.net/u013078356/article/details/51154847

#!/usr/bin/env sh
set -e
LOG=/home/hugo/caffe/examples/mnist/log-'data +%Y-%m-%d-%H-%S'.log
./build/tools/caffe train --solver=examples/mnist/lenet_solver.prototxt 2>&1 | tee $LOG

　　抓log

cp parse_log.sh extract_seconds.py plot_training_log.py.example /home/hugo/caffe/examples/mnist/

　　复制caffe/tools/extra/,里面的三个脚本到需要绘制图片的log所在文件夹，

python plot_training_log.py 3 test.png log3wnocenter.log 

　　直接调用就可以生成了，但是这个方法缺点很多，由于对数据处理的不准确，绘制的图像也不准确，4-7的参数还不能用，真是太坑人了，我用后面的方法汇报给主管，主管很生气，也怪我不认真，mother fucker。

 在服务器上运行还有一个小技巧，就是远程ssh连接进行训练时，由于时间较长，一不小心关掉命令行，还得把model加到脚本里，继续进行训练，关键看不到停止岂不是浪费时间，

nohup python loss.py > nohup.log 2>&1 & 

这样就可以在关掉命令行后还继续在后台进行训练了。