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
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)
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
