本文主要参考caffe官方文档[<Fine-tuning a Pretrained Network for Style Recognition>](http://nbviewer.jupyter.org/github/BVLC/caffe/blob/master/examples/02-fine-tuning.ipynb) 是第二篇案例.笔者对其进行了为期一周的断断续续的研究,笔者起先对python/caffe并不了解+英语不好,阅读+理解的时间有点长,前前后后过了不下十遍终于从这第二篇文档看
0 前言 本文内容主要:介绍Pointer-Generator-Network在文本摘要任务中的背景,模型架构与原理.在中英文数据集上实战效果与评估,最后得出结论.参考的<Get To The Point: Summarization with Pointer-Generator Networks>以及多篇博客均在文末给出连接,文中使用数据集已上传百度网盘,代码已传至GitHub,读者可以在文中找到相应连接,实际操作过程中确实遇到很多坑,并未在文中一一指明,有兴趣的读者可以留言一起交流.由于水
正文 what should I do if... ...my loss diverges? (increases by order of magnitude, goes to inf. or NaN) lower the learning rate raise momentum (with corresponding learning rate drop) raise weight decay raise batch size use gradient clipping (limit the
import re import pylab as pl import numpy as np if __name__=="__main__": accuracys=[] losses=[] with open(r'/home/wxl/bnscallog.txt','r') as f: lines=f.readlines(); print len(lines) str="".join(lines) str=str.replace('\n','') print len