基于Pytorch SSD模型分析

更新時間：2020年02月18日 14:35:05 作者：DaneAI

今天小編就為大家分享一篇基于Pytorch SSD模型分析，具有很好的參考價值，希望對大家有所幫助。一起跟隨小編過來看看吧

本文參考github上SSD實現(xiàn),對模型進行分析,主要分析模型組成及輸入輸出大小.SSD網(wǎng)絡(luò)結(jié)構(gòu)如下圖:

每輸入的圖像有8732個框輸出;

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基礎(chǔ)網(wǎng)絡(luò)結(jié)構(gòu):

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)

輸出為:

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中添加的網(wǎng)絡(luò)

add_extras函數(shù)構(gòu)建基本的卷積層

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)

輸出為:

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函數(shù)得到每個特征圖的默認box的位置計算網(wǎng)絡(luò)和分類得分網(wǎng)絡(luò)

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), ## 產(chǎn)生vgg19基本模型
          add_extras(extras[str(size)], 1024), 
          mbox[str(size)], num_classes)
#mbox[str(size)]為:[4, 6, 6, 6, 4, 4]

得到的輸出為:

base_為上述描述的vgg網(wǎng)絡(luò),extras_為extra_layers網(wǎng)絡(luò),head_為:

([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網(wǎng)絡(luò)及forward函數(shù)為:

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尺度為[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尺寸為[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輸出分別為:
  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

上述代碼中sources中保存的數(shù)據(jù)輸出如下,即用于邊框提取的特征圖:

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])

模型輸入為