dpn网络的pytorch实现方式


Posted in Python onJanuary 14, 2020

我就废话不多说了,直接上代码吧!

import torch
import torch.nn as nn
import torch.nn.functional as F



class CatBnAct(nn.Module):
 def __init__(self, in_chs, activation_fn=nn.ReLU(inplace=True)):
  super(CatBnAct, self).__init__()
  self.bn = nn.BatchNorm2d(in_chs, eps=0.001)
  self.act = activation_fn

 def forward(self, x):
  x = torch.cat(x, dim=1) if isinstance(x, tuple) else x
  return self.act(self.bn(x))


class BnActConv2d(nn.Module):
 def __init__(self, s, out_chs, kernel_size, stride,
     padding=0, groups=1, activation_fn=nn.ReLU(inplace=True)):
  super(BnActConv2d, self).__init__()
  self.bn = nn.BatchNorm2d(in_chs, eps=0.001)
  self.act = activation_fn
  self.conv = nn.Conv2d(in_chs, out_chs, kernel_size, stride, padding, groups=groups, bias=False)

 def forward(self, x):
  return self.conv(self.act(self.bn(x)))


class InputBlock(nn.Module):
 def __init__(self, num_init_features, kernel_size=7,
     padding=3, activation_fn=nn.ReLU(inplace=True)):
  super(InputBlock, self).__init__()
  self.conv = nn.Conv2d(
   3, num_init_features, kernel_size=kernel_size, stride=2, padding=padding, bias=False)
  self.bn = nn.BatchNorm2d(num_init_features, eps=0.001)
  self.act = activation_fn
  self.pool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

 def forward(self, x):
  x = self.conv(x)
  x = self.bn(x)
  x = self.act(x)
  x = self.pool(x)
  return x


class DualPathBlock(nn.Module):
 def __init__(
   self, in_chs, num_1x1_a, num_3x3_b, num_1x1_c, inc, groups, block_type='normal', b=False):
  super(DualPathBlock, self).__init__()
  self.num_1x1_c = num_1x1_c
  self.inc = inc
  self.b = b
  if block_type is 'proj':
   self.key_stride = 1
   self.has_proj = True
  elif block_type is 'down':
   self.key_stride = 2
   self.has_proj = True
  else:
   assert block_type is 'normal'
   self.key_stride = 1
   self.has_proj = False

  if self.has_proj:
   # Using different member names here to allow easier parameter key matching for conversion
   if self.key_stride == 2:
    self.c1x1_w_s2 = BnActConv2d(
     in_chs=in_chs, out_chs=num_1x1_c + 2 * inc, kernel_size=1, stride=2)
   else:
    self.c1x1_w_s1 = BnActConv2d(
     in_chs=in_chs, out_chs=num_1x1_c + 2 * inc, kernel_size=1, stride=1)
  self.c1x1_a = BnActConv2d(in_chs=in_chs, out_chs=num_1x1_a, kernel_size=1, stride=1)
  self.c3x3_b = BnActConv2d(
   in_chs=num_1x1_a, out_chs=num_3x3_b, kernel_size=3,
   stride=self.key_stride, padding=1, groups=groups)
  if b:
   self.c1x1_c = CatBnAct(in_chs=num_3x3_b)
   self.c1x1_c1 = nn.Conv2d(num_3x3_b, num_1x1_c, kernel_size=1, bias=False)
   self.c1x1_c2 = nn.Conv2d(num_3x3_b, inc, kernel_size=1, bias=False)
  else:
   self.c1x1_c = BnActConv2d(in_chs=num_3x3_b, out_chs=num_1x1_c + inc, kernel_size=1, stride=1)

 def forward(self, x):
  x_in = torch.cat(x, dim=1) if isinstance(x, tuple) else x
  if self.has_proj:
   if self.key_stride == 2:
    x_s = self.c1x1_w_s2(x_in)
   else:
    x_s = self.c1x1_w_s1(x_in)
   x_s1 = x_s[:, :self.num_1x1_c, :, :]
   x_s2 = x_s[:, self.num_1x1_c:, :, :]
  else:
   x_s1 = x[0]
   x_s2 = x[1]
  x_in = self.c1x1_a(x_in)
  x_in = self.c3x3_b(x_in)
  if self.b:
   x_in = self.c1x1_c(x_in)
   out1 = self.c1x1_c1(x_in)
   out2 = self.c1x1_c2(x_in)
  else:
   x_in = self.c1x1_c(x_in)
   out1 = x_in[:, :self.num_1x1_c, :, :]
   out2 = x_in[:, self.num_1x1_c:, :, :]
  resid = x_s1 + out1
  dense = torch.cat([x_s2, out2], dim=1)
  return resid, dense


class DPN(nn.Module):
 def __init__(self, small=False, num_init_features=64, k_r=96, groups=32,
     b=False, k_sec=(3, 4, 20, 3), inc_sec=(16, 32, 24, 128),
     num_classes=1000, test_time_pool=False):
  super(DPN, self).__init__()
  self.test_time_pool = test_time_pool
  self.b = b
  bw_factor = 1 if small else 4

  blocks = OrderedDict()

  # conv1
  if small:
   blocks['conv1_1'] = InputBlock(num_init_features, kernel_size=3, padding=1)
  else:
   blocks['conv1_1'] = InputBlock(num_init_features, kernel_size=7, padding=3)

  # conv2
  bw = 64 * bw_factor
  inc = inc_sec[0]
  r = (k_r * bw) // (64 * bw_factor)
  blocks['conv2_1'] = DualPathBlock(num_init_features, r, r, bw, inc, groups, 'proj', b)
  in_chs = bw + 3 * inc
  for i in range(2, k_sec[0] + 1):
   blocks['conv2_' + str(i)] = DualPathBlock(in_chs, r, r, bw, inc, groups, 'normal', b)
   in_chs += inc

  # conv3
  bw = 128 * bw_factor
  inc = inc_sec[1]
  r = (k_r * bw) // (64 * bw_factor)
  blocks['conv3_1'] = DualPathBlock(in_chs, r, r, bw, inc, groups, 'down', b)
  in_chs = bw + 3 * inc
  for i in range(2, k_sec[1] + 1):
   blocks['conv3_' + str(i)] = DualPathBlock(in_chs, r, r, bw, inc, groups, 'normal', b)
   in_chs += inc

  # conv4
  bw = 256 * bw_factor
  inc = inc_sec[2]
  r = (k_r * bw) // (64 * bw_factor)
  blocks['conv4_1'] = DualPathBlock(in_chs, r, r, bw, inc, groups, 'down', b)
  in_chs = bw + 3 * inc
  for i in range(2, k_sec[2] + 1):
   blocks['conv4_' + str(i)] = DualPathBlock(in_chs, r, r, bw, inc, groups, 'normal', b)
   in_chs += inc

  # conv5
  bw = 512 * bw_factor
  inc = inc_sec[3]
  r = (k_r * bw) // (64 * bw_factor)
  blocks['conv5_1'] = DualPathBlock(in_chs, r, r, bw, inc, groups, 'down', b)
  in_chs = bw + 3 * inc
  for i in range(2, k_sec[3] + 1):
   blocks['conv5_' + str(i)] = DualPathBlock(in_chs, r, r, bw, inc, groups, 'normal', b)
   in_chs += inc
  blocks['conv5_bn_ac'] = CatBnAct(in_chs)

  self.features = nn.Sequential(blocks)

  # Using 1x1 conv for the FC layer to allow the extra pooling scheme
  self.last_linear = nn.Conv2d(in_chs, num_classes, kernel_size=1, bias=True)

 def logits(self, features):
  if not self.training and self.test_time_pool:
   x = F.avg_pool2d(features, kernel_size=7, stride=1)
   out = self.last_linear(x)
   # The extra test time pool should be pooling an img_size//32 - 6 size patch
   out = adaptive_avgmax_pool2d(out, pool_type='avgmax')
  else:
   x = adaptive_avgmax_pool2d(features, pool_type='avg')
   out = self.last_linear(x)
  return out.view(out.size(0), -1)

 def forward(self, input):
  x = self.features(input)
  x = self.logits(x)
  return x

""" PyTorch selectable adaptive pooling
Adaptive pooling with the ability to select the type of pooling from:
 * 'avg' - Average pooling
 * 'max' - Max pooling
 * 'avgmax' - Sum of average and max pooling re-scaled by 0.5
 * 'avgmaxc' - Concatenation of average and max pooling along feature dim, doubles feature dim

Both a functional and a nn.Module version of the pooling is provided.

"""

def pooling_factor(pool_type='avg'):
 return 2 if pool_type == 'avgmaxc' else 1


def adaptive_avgmax_pool2d(x, pool_type='avg', padding=0, count_include_pad=False):
 """Selectable global pooling function with dynamic input kernel size
 """
 if pool_type == 'avgmaxc':
  x = torch.cat([
   F.avg_pool2d(
    x, kernel_size=(x.size(2), x.size(3)), padding=padding, count_include_pad=count_include_pad),
   F.max_pool2d(x, kernel_size=(x.size(2), x.size(3)), padding=padding)
  ], dim=1)
 elif pool_type == 'avgmax':
  x_avg = F.avg_pool2d(
    x, kernel_size=(x.size(2), x.size(3)), padding=padding, count_include_pad=count_include_pad)
  x_max = F.max_pool2d(x, kernel_size=(x.size(2), x.size(3)), padding=padding)
  x = 0.5 * (x_avg + x_max)
 elif pool_type == 'max':
  x = F.max_pool2d(x, kernel_size=(x.size(2), x.size(3)), padding=padding)
 else:
  if pool_type != 'avg':
   print('Invalid pool type %s specified. Defaulting to average pooling.' % pool_type)
  x = F.avg_pool2d(
   x, kernel_size=(x.size(2), x.size(3)), padding=padding, count_include_pad=count_include_pad)
 return x


class AdaptiveAvgMaxPool2d(torch.nn.Module):
 """Selectable global pooling layer with dynamic input kernel size
 """
 def __init__(self, output_size=1, pool_type='avg'):
  super(AdaptiveAvgMaxPool2d, self).__init__()
  self.output_size = output_size
  self.pool_type = pool_type
  if pool_type == 'avgmaxc' or pool_type == 'avgmax':
   self.pool = nn.ModuleList([nn.AdaptiveAvgPool2d(output_size), nn.AdaptiveMaxPool2d(output_size)])
  elif pool_type == 'max':
   self.pool = nn.AdaptiveMaxPool2d(output_size)
  else:
   if pool_type != 'avg':
    print('Invalid pool type %s specified. Defaulting to average pooling.' % pool_type)
   self.pool = nn.AdaptiveAvgPool2d(output_size)

 def forward(self, x):
  if self.pool_type == 'avgmaxc':
   x = torch.cat([p(x) for p in self.pool], dim=1)
  elif self.pool_type == 'avgmax':
   x = 0.5 * torch.sum(torch.stack([p(x) for p in self.pool]), 0).squeeze(dim=0)
  else:
   x = self.pool(x)
  return x

 def factor(self):
  return pooling_factor(self.pool_type)

 def __repr__(self):
  return self.__class__.__name__ + ' (' \
    + 'output_size=' + str(self.output_size) \
    + ', pool_type=' + self.pool_type + ')'

以上这篇dpn网络的pytorch实现方式就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持三水点靠木。

Python 相关文章推荐
python二叉树的实现实例
Nov 21 Python
python中base64加密解密方法实例分析
May 16 Python
Python中操作文件之write()方法的使用教程
May 25 Python
对pandas replace函数的使用方法小结
May 18 Python
Python中的引用知识点总结
May 20 Python
Python 3 判断2个字典相同
Aug 06 Python
python中property属性的介绍及其应用详解
Aug 29 Python
解决pytorch多GPU训练保存的模型,在单GPU环境下加载出错问题
Jun 23 Python
Python sqlalchemy时间戳及密码管理实现代码详解
Aug 01 Python
python利用蒙版抠图(使用PIL.Image和cv2)输出透明背景图
Aug 04 Python
python字典key不能是可以是啥类型
Aug 04 Python
浅析python 通⽤爬⾍和聚焦爬⾍
Sep 28 Python
Django之form组件自动校验数据实现
Jan 14 #Python
简单了解python filter、map、reduce的区别
Jan 14 #Python
Python vtk读取并显示dicom文件示例
Jan 13 #Python
Python解析多帧dicom数据详解
Jan 13 #Python
python 将dicom图片转换成jpg图片的实例
Jan 13 #Python
基于Python和PyYAML读取yaml配置文件数据
Jan 13 #Python
Python 实现判断图片格式并转换,将转换的图像存到生成的文件夹中
Jan 13 #Python
You might like
解析isset与is_null的区别
2013/08/09 PHP
php实现TCP端口检测的方法
2015/04/01 PHP
php格式化电话号码的方法
2015/04/24 PHP
php一个解析字符串排列数组的方法
2015/05/12 PHP
PHP请求远程地址设置超时时间的解决方法
2016/10/29 PHP
取键盘键位ASCII码的网页
2007/07/30 Javascript
JS和JQUERY获取页面大小,滚动条位置,元素位置(示例代码)
2013/12/14 Javascript
jquery.validate 自定义验证方法及validate相关参数
2016/01/18 Javascript
第一次接触Bootstrap框架
2016/10/24 Javascript
获取当前按钮或者html的ID名称实例(推荐)
2017/06/23 Javascript
JavaScript 隐性类型转换步骤浅析
2018/03/15 Javascript
让webpack+vue-cil项目不再自动打开浏览器的方法
2018/09/27 Javascript
vue项目从node8.x升级到12.x后的问题解决
2019/10/25 Javascript
vue项目使用$router.go(-1)返回时刷新原来的界面操作
2020/07/26 Javascript
vue中touch和click共存的解决方式
2020/07/28 Javascript
[36:02]DOTA2上海特级锦标赛D组小组赛#2 Liquid VS VP第一局
2016/02/28 DOTA
python判断一个集合是否包含了另外一个集合中所有项的方法
2015/06/30 Python
Python的组合模式与责任链模式编程示例
2016/02/02 Python
Python中列表和元组的使用方法和区别详解
2020/12/30 Python
详解appium+python 启动一个app步骤
2017/12/20 Python
python监控键盘输入实例代码
2018/02/09 Python
Python基础知识点 初识Python.md
2019/05/14 Python
python多线程共享变量的使用和效率方法
2019/07/16 Python
PIL包中Image模块的convert()函数的具体使用
2020/02/26 Python
Python代码一键转Jar包及Java调用Python新姿势
2020/03/10 Python
keras模型保存为tensorflow的二进制模型方式
2020/05/25 Python
中科软测试工程师面试题
2012/06/16 面试题
大学生求职简历的自我评价范文
2013/10/12 职场文书
办公室主任竞聘演讲稿
2014/05/15 职场文书
工地标语大全
2014/06/18 职场文书
白鹤梁导游词
2015/02/06 职场文书
经济纠纷起诉状
2015/05/20 职场文书
《有余数的除法》教学反思
2016/02/22 职场文书
大学生暑期实践报告之企业经营管理
2019/08/08 职场文书
新手,如何业余时间安排好写作、提高写作能力?
2019/10/21 职场文书
python3 实现mysql数据库连接池的示例代码
2021/04/17 Python