ShuffleNetV2(torch.jit.ScriptModule)

举报
风吹稻花香 发表于 2021/06/05 00:18:59 2021/06/05
【摘要】   #coding=utf-8from collections import OrderedDict import torchimport torch.nn as nnimport torch.nn.functional as Ffrom torch.nn import initimport time def _make_divisible(v, divisor,...

 


  
  1. #coding=utf-8
  2. from collections import OrderedDict
  3. import torch
  4. import torch.nn as nn
  5. import torch.nn.functional as F
  6. from torch.nn import init
  7. import time
  8. def _make_divisible(v, divisor, min_value=None):
  9. """
  10. This function is taken from the original tf repo.
  11. It ensures that all layers have a channel number that is divisible by 8
  12. It can be seen here:
  13. https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
  14. :param v:
  15. :param divisor:
  16. :param min_value:
  17. :return:
  18. """
  19. if min_value is None:
  20. min_value = divisor
  21. new_v = max(min_value, int(v + divisor / 2.0) // divisor * divisor)
  22. # Make sure that round down does not go down by more than 10%.
  23. if new_v < 0.9 * v:
  24. new_v += divisor
  25. return new_v
  26. class SELayer(nn.Module):
  27. def __init__(self, channel, reduction=16):

文章来源: blog.csdn.net,作者:网奇,版权归原作者所有,如需转载,请联系作者。

原文链接:blog.csdn.net/jacke121/article/details/93872500

【版权声明】本文为华为云社区用户转载文章,如果您发现本社区中有涉嫌抄袭的内容,欢迎发送邮件进行举报,并提供相关证据,一经查实,本社区将立刻删除涉嫌侵权内容,举报邮箱: cloudbbs@huaweicloud.com
  • 点赞
  • 收藏
  • 关注作者

评论(0

0/1000
抱歉,系统识别当前为高风险访问,暂不支持该操作

全部回复

上滑加载中

设置昵称

在此一键设置昵称,即可参与社区互动!

*长度不超过10个汉字或20个英文字符,设置后3个月内不可修改。

*长度不超过10个汉字或20个英文字符,设置后3个月内不可修改。