caffe中 cifar10案例（四）可视化loss和accurary曲线

$ cd /opt/caffe-master

#把原先输出到窗口的信息，记录到1.log文件里。
$ sudo time sh examples/cifar10/train_quick.sh >& examples/cifar10/1.log

#这种办法，屏幕上不再有显示，如果要想在屏幕上显示，可以用：
$ sudo time sh examples/cifar10/train_quick.sh |tee examples/cifar10/1.log

caffe提供了{caffe_root}/tools/extra/plot_training_log.py工具可视化loss和accurary曲线。

$ python tools/extra/plot_training_log.py 0 a.png examples/cifar10/1.log

$ python tools/extra/plot_training_log.py 2 l.png examples/cifar10/1.log

plot_training_log.py的语法
./plot_training_log.py chart_type[0-7] /where/to/save.png /path/to/first.log …
Notes:
1. Supporting multiple logs.
2. Log file name must end with the lower-cased “.log”.
Supported chart types:
0: Test accuracy vs. Iters
1: Test accuracy vs. Seconds
2: Test loss vs. Iters
3: Test loss vs. Seconds
4: Train learning rate vs. Iters
5: Train learning rate vs. Seconds
6: Train loss vs. Iters
7: Train loss vs. Seconds