caffe 绘制loss/ accuracy曲线


Copy ‘caffe-master/tools/extra/parse_log.sh' 'caffe-master/tools/extra/extract_seconds.py' 'caffe-master/tools/extra/plot_training_log.py.example' to the same folder(e.g.output/logs) that contains your log file.



1. Train a model with mAP and an output LOG file; (Refer to 点击打开链接)
(Open terminal at root-dir)


$ ./experiments/scripts/faster_rcnn_alt_opt.sh 0 VGG16 pascal_voc



2. Parse the LOG file with two output files .train and .test ;
(Open terminal at output/logs/)


$ ./parse_log.sh XXXX.log



3. Create a curve picture ;


$ ./plot_training_log.py.example 6 loss.png XXXX.log 


########################################################
  Notes: 
        1. Supporting multiple logs. 
        2. Log file name must end withthe lower-cased ".log". 
        3. To solve "Permissiondenied".

        $ chmod+x FILENAME 


  Supportedchart 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 


 

  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 1
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值