skipnet_face

举报
风吹稻花香 发表于 2022/01/23 00:30:56 2022/01/23
【摘要】 """based on MobileNet implementation fromhttps://github.com/rwightman/pytorch-image-models"""import time import torchimport torch.nn as nnimport math def _make_divis...


  
  1. """
  2. based on MobileNet implementation from
  3. https://github.com/rwightman/pytorch-image-models
  4. """
  5. import time
  6. import torch
  7. import torch.nn as nn
  8. import math
  9. def _make_divisible(v, divisor, min_value=None):
  10. """
  11. Ensures that all layers have a channel number that is divisible by 8
  12. function is taken from the original tf repo:
  13. https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
  14. """
  15. if min_value is None:
  16. min_value = divisor
  17. new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
  18. # Make sure that round down does not go down by more than 10%.
  19. if new_v < 0.9 * v:
  20. new_v += divisor
  21. return new_v
  22. class h_sigmoid(nn.Module):
  23. def __init__(self, inplace=True):
  24. super(h_sigmoid, self).__init__()
  25. self.relu = nn.ReLU6(inplace=inplace)
  26. def forwa

文章来源: blog.csdn.net,作者:AI视觉网奇,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/119178358

【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。