基于Pytorch SSD模型分析

更新时间：2020年02月18日 14:35:05 作者：DaneAI

今天小编就为大家分享一篇基于Pytorch SSD模型分析，具有很好的参考价值，希望对大家有所帮助。一起跟随小编过来看看吧

本文参考github上SSD实现,对模型进行分析,主要分析模型组成及输入输出大小.SSD网络结构如下图:

每输入的图像有8732个框输出;

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
#from layers import *
from data import voc, coco
import os

base = {
 '300': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'C', 512, 512, 512, 'M',
   512, 512, 512],
 '512': [],
}
extras = {
 '300': [256, 'S', 512, 128, 'S', 256, 128, 256, 128, 256],
 '512': [],
}
mbox = {
 '300': [4, 6, 6, 6, 4, 4], # number of boxes per feature map location
 '512': [],
}

VGG基础网络结构:

def vgg(cfg, i, batch_norm=False):
 layers = []
 in_channels = i
 for v in cfg:
  if v == 'M':
   layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
  elif v == 'C':
   layers += [nn.MaxPool2d(kernel_size=2, stride=2, ceil_mode=True)]
  else:
   conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
   if batch_norm:
    layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
   else:
    layers += [conv2d, nn.ReLU(inplace=True)]
   in_channels = v
 pool5 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
 conv6 = nn.Conv2d(512, 1024, kernel_size=3, padding=6, dilation=6)
 conv7 = nn.Conv2d(1024, 1024, kernel_size=1)
 layers += [pool5, conv6,
    nn.ReLU(inplace=True), conv7, nn.ReLU(inplace=True)]
 return layers

size=300
vgg=vgg(base[str(size)], 3)
print(vgg)

输出为:

Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace)
Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace)
MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace)
Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace)
MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace)
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace)
Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace)
MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=True)
Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace)
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace)
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace)
MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace)
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace)
Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
ReLU(inplace)
MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
Conv2d(512, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(6, 6), dilation=(6, 6))
ReLU(inplace)
Conv2d(1024, 1024, kernel_size=(1, 1), stride=(1, 1))
ReLU(inplace)

SSD中添加的网络

add_extras函数构建基本的卷积层

def add_extras(cfg, i, batch_norm=False):
 # Extra layers added to VGG for feature scaling
 layers = []
 in_channels = i
 flag = False
 for k, v in enumerate(cfg):
  if in_channels != 'S':
   if v == 'S':
    layers += [nn.Conv2d(in_channels, cfg[k + 1],
       kernel_size=(1, 3)[flag], stride=2, padding=1)]
   else:
    layers += [nn.Conv2d(in_channels, v, kernel_size=(1, 3)[flag])]
   flag = not flag
  in_channels = v
 return layers

extra_layers=add_extras(extras[str(size)], 1024)
for layer in extra_layers:
 print(layer)

输出为:

Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1))
Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1))
Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1))
Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1))

multibox函数得到每个特征图的默认box的位置计算网络和分类得分网络

def multibox(vgg, extra_layers, cfg, num_classes):
 loc_layers = []
 conf_layers = []
 vgg_source = [21, -2]
 for k, v in enumerate(vgg_source):
  loc_layers += [nn.Conv2d(vgg[v].out_channels,
         cfg[k] * 4, kernel_size=3, padding=1)]
  conf_layers += [nn.Conv2d(vgg[v].out_channels,
      cfg[k] * num_classes, kernel_size=3, padding=1)]
 for k, v in enumerate(extra_layers[1::2], 2):
  loc_layers += [nn.Conv2d(v.out_channels, cfg[k]
         * 4, kernel_size=3, padding=1)]
  conf_layers += [nn.Conv2d(v.out_channels, cfg[k]
         * num_classes, kernel_size=3, padding=1)]
 return vgg, extra_layers, (loc_layers, conf_layers)

base_, extras_, head_ = multibox(vgg(base[str(size)], 3), ## 产生vgg19基本模型
          add_extras(extras[str(size)], 1024), 
          mbox[str(size)], num_classes)
#mbox[str(size)]为:[4, 6, 6, 6, 4, 4]

得到的输出为:

base_为上述描述的vgg网络,extras_为extra_layers网络,head_为:

([Conv2d(512, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 Conv2d(1024, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 Conv2d(512, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 Conv2d(256, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 Conv2d(256, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 Conv2d(256, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))],
 [Conv2d(512, 84, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 Conv2d(1024, 126, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 Conv2d(512, 126, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 Conv2d(256, 126, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 Conv2d(256, 84, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 Conv2d(256, 84, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))])

SSD网络及forward函数为:

class SSD(nn.Module):
 """Single Shot Multibox Architecture
 The network is composed of a base VGG network followed by the
 added multibox conv layers. Each multibox layer branches into
  1) conv2d for class conf scores
  2) conv2d for localization predictions
  3) associated priorbox layer to produce default bounding
   boxes specific to the layer's feature map size.
 See: https://arxiv.org/pdf/1512.02325.pdf for more details.

 Args:
  phase: (string) Can be "test" or "train"
  size: input image size
  base: VGG16 layers for input, size of either 300 or 500
  extras: extra layers that feed to multibox loc and conf layers
  head: "multibox head" consists of loc and conf conv layers
 """

 def __init__(self, phase, size, base, extras, head, num_classes):
  super(SSD, self).__init__()
  self.phase = phase
  self.num_classes = num_classes 
  self.cfg = (coco, voc)[num_classes == 21]
  self.priorbox = PriorBox(self.cfg)
  self.priors = Variable(self.priorbox.forward(), volatile=True)
  self.size = size

  # SSD network
  self.vgg = nn.ModuleList(base)
  # Layer learns to scale the l2 normalized features from conv4_3
  self.L2Norm = L2Norm(512, 20)
  self.extras = nn.ModuleList(extras)

  self.loc = nn.ModuleList(head[0])
  self.conf = nn.ModuleList(head[1])

  if phase == 'test':
   self.softmax = nn.Softmax(dim=-1)
   self.detect = Detect(num_classes, 0, 200, 0.01, 0.45)

 def forward(self, x):
  """Applies network layers and ops on input image(s) x.

  Args:
   x: input image or batch of images. Shape: [batch,3,300,300].

  Return:
   Depending on phase:
   test:
    Variable(tensor) of output class label predictions,
    confidence score, and corresponding location predictions for
    each object detected. Shape: [batch,topk,7]

   train:
    list of concat outputs from:
     1: confidence layers, Shape: [batch*num_priors,num_classes]
     2: localization layers, Shape: [batch,num_priors*4]
     3: priorbox layers, Shape: [2,num_priors*4]
  """
  sources = list()
  loc = list()
  conf = list()

  # apply vgg up to conv4_3 relu
  for k in range(23):
   x = self.vgg[k](x) ##得到的x尺度为[1,512,38,38]

  s = self.L2Norm(x)
  sources.append(s)

  # apply vgg up to fc7
  for k in range(23, len(self.vgg)):
   x = self.vgg[k](x) ##得到的x尺寸为[1,1024,19,19]
  sources.append(x)

  # apply extra layers and cache source layer outputs
  for k, v in enumerate(self.extras):
   x = F.relu(v(x), inplace=True)
   if k % 2 == 1:
    sources.append(x)
  '''
  上述得到的x输出分别为:
  torch.Size([1, 512, 10, 10])
  torch.Size([1, 256, 5, 5])
  torch.Size([1, 256, 3, 3])
  torch.Size([1, 256, 1, 1])
  '''

  # apply multibox head to source layers
  for (x, l, c) in zip(sources, self.loc, self.conf):
   loc.append(l(x).permute(0, 2, 3, 1).contiguous())
   conf.append(c(x).permute(0, 2, 3, 1).contiguous())

  loc = torch.cat([o.view(o.size(0), -1) for o in loc], 1)
  conf = torch.cat([o.view(o.size(0), -1) for o in conf], 1)
  if self.phase == "test":
   output = self.detect(
    loc.view(loc.size(0), -1, 4),     # loc preds
    self.softmax(conf.view(conf.size(0), -1,
        self.num_classes)),    # conf preds
    self.priors.type(type(x.data))     # default boxes
   )
  else:
   output = (
    loc.view(loc.size(0), -1, 4), #[1,8732,4]
    conf.view(conf.size(0), -1, self.num_classes),#[1,8732,21]
    self.priors
   )
  return output

上述代码中sources中保存的数据输出如下,即用于边框提取的特征图:

torch.Size([1, 512, 38, 38])
torch.Size([1, 1024, 19, 19])
torch.Size([1, 512, 10, 10])
torch.Size([1, 256, 5, 5])
torch.Size([1, 256, 3, 3])
torch.Size([1, 256, 1, 1])

模型输入为

x=Variable(torch.randn(1,3,300,300))

以上这篇基于Pytorch SSD模型分析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脚本之家。

您可能感兴趣的文章:

Python实现的批量修改文件后缀名操作示例
这篇文章主要介绍了Python实现的批量修改文件后缀名操作,涉及Python目录文件的遍历、重命名等相关操作技巧,需要的朋友可以参考下
2018-12-12
python开发之字符串string操作方法实例详解
这篇文章主要介绍了python开发之字符串string操作方法,以实例形式较为详细的分析了Python针对字符串的转义、连接、换行、输出等操作技巧,需要的朋友可以参考下
2015-11-11
Gradio机器学习模型快速部署工具quickstart
这篇文章主要为大家介绍了Gradio机器学习模型快速部署工具quickstart，有需要的朋友可以借鉴参考下，希望能够有所帮助，祝大家多多进步，早日升职加薪
2023-04-04
tensorflow使用CNN分析mnist手写体数字数据集
这篇文章主要介绍了tensorflow使用CNN分析mnist手写体数字数据集，文中示例代码介绍的非常详细，具有一定的参考价值，感兴趣的小伙伴们可以参考一下
2020-06-06
Python 中创建 PostgreSQL 数据库连接池
这篇文章主要介绍了Python 中创建 PostgreSQL 数据库连接池，Python 连接 PostgreSQL 是主要有两个包， py-postgresql 和 psycopg2 , 而本文的实例将使用后者，感兴趣的小伙伴可以参考一下
2021-10-10
Nginx+Uwsgi+Django 项目部署到服务器的思路详解
这篇文章主要介绍了Nginx+Uwsgi+Django 项目部署到服务器的思路，本文通过实例代码给大家介绍的非常详细，对大家的学习或工作具有一定的参考借鉴价值,需要的朋友可以参考下
2020-05-05
python爬虫实战之最简单的网页爬虫教程
在我们日常上网浏览网页的时候，经常会看到一些好看的图片，我们就希望把这些图片保存下载，或者用户用来做桌面壁纸，或者用来做设计的素材。下面这篇文章就来给大家介绍了关于利用python实现最简单的网页爬虫的相关资料，需要的朋友可以参考借鉴，下面来一起看看吧。
2017-08-08
Python中shape计算矩阵的方法示例
这篇文章主要介绍了Python中shape计算矩阵的方法,涉及Python数学运算相关实现技巧,需要的朋友可以参考下
2017-04-04
python实现的简单FTP上传下载文件实例
这篇文章主要介绍了python实现的简单FTP上传下载文件的方法,实例分析了Python基于FTP模块实现文件传输的技巧,需要的朋友可以参考下
2015-06-06
在Django的URLconf中使用多个视图前缀的方法
这篇文章主要介绍了在Django的URLconf中使用多个视图前缀的方法,Django是Python中最为著名的遵循MVC结构的开发框架,需要的朋友可以参考下
2015-07-07