class SSD(nn.Module):
def __init__(self, phase, base, extras, head, num_classes):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
self.cfg = Config
self.vgg = nn.ModuleList(base)
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.priorbox = PriorBox(self.cfg)
with torch.no_grad():
self.priors = torch.tensor(self.priorbox.forward())
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):
sources = list()
loc = list()
conf = list()
# get outputs of conv4_3
for k in range(23):
x = self.vgg[k](x)
s = self.L2Norm(x)
sources.append(s)
# get outputs of fc7
for k in range(23, len(self.vgg)):
x = self.vgg[k](x)
sources.append(x)
# get the rest outputs
for k, v in enumerate(self.extras):
x = F.relu(v(x), inplace=True)
if k % 2 == 1:
sources.append(x)
# regression layers and classification 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())
# resize
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":
# loc会resize到batch_size,num_anchors,4
# conf会resize到batch_size,num_anchors,
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)
else:
output = (loc.view(loc.size(0), -1,
4), conf.view(conf.size(0), -1,
self.num_classes), self.priors)
return output
def SSD300(input_shape,
num_classes=21,
anchors_size=[30, 60, 111, 162, 213, 264, 315]):
#---------------------------------#
# 典型的输入大小为[300,300,3]
#---------------------------------#
input_tensor = Input(shape=input_shape)
# net变量里面包含了整个SSD的结构，通过层名可以找到对应的特征层
net = VGG16(input_tensor)
#-----------------------将提取到的主干特征进行处理---------------------------#
# 对conv4_3的通道进行l2标准化处理
# 38,38,512
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
net['conv4_3_norm_mbox_loc'] = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv4_3_norm_mbox_loc')(
net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc_flat'] = Flatten(
name='conv4_3_norm_mbox_loc_flat')(net['conv4_3_norm_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
net['conv4_3_norm_mbox_conf'] = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv4_3_norm_mbox_conf')(
net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf_flat'] = Flatten(
name='conv4_3_norm_mbox_conf_flat')(net['conv4_3_norm_mbox_conf'])
priorbox = PriorBox(input_shape,
anchors_size[0],
max_size=anchors_size[1],
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')
net['conv4_3_norm_mbox_priorbox'] = priorbox(net['conv4_3_norm'])
# 对fc7层进行处理
# 19,19,1024
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
net['fc7_mbox_loc'] = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='fc7_mbox_loc')(net['fc7'])
net['fc7_mbox_loc_flat'] = Flatten(name='fc7_mbox_loc_flat')(
net['fc7_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
net['fc7_mbox_conf'] = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='fc7_mbox_conf')(net['fc7'])
net['fc7_mbox_conf_flat'] = Flatten(name='fc7_mbox_conf_flat')(
net['fc7_mbox_conf'])
priorbox = PriorBox(input_shape,
anchors_size[1],
max_size=anchors_size[2],
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# 对conv6_2进行处理
# 10,10,512
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
net['conv6_2_mbox_loc_flat'] = Flatten(name='conv6_2_mbox_loc_flat')(
net['conv6_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv6_2_mbox_conf')(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
net['conv6_2_mbox_conf_flat'] = Flatten(name='conv6_2_mbox_conf_flat')(
net['conv6_2_mbox_conf'])
priorbox = PriorBox(input_shape,
anchors_size[2],
max_size=anchors_size[3],
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# 对conv7_2进行处理
# 5,5,256
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
net['conv7_2_mbox_loc_flat'] = Flatten(name='conv7_2_mbox_loc_flat')(
net['conv7_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv7_2_mbox_conf')(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
net['conv7_2_mbox_conf_flat'] = Flatten(name='conv7_2_mbox_conf_flat')(
net['conv7_2_mbox_conf'])
priorbox = PriorBox(input_shape,
anchors_size[3],
max_size=anchors_size[4],
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# 对conv8_2进行处理
# 3,3,256
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
net['conv8_2_mbox_loc_flat'] = Flatten(name='conv8_2_mbox_loc_flat')(
net['conv8_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv8_2_mbox_conf')(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
net['conv8_2_mbox_conf_flat'] = Flatten(name='conv8_2_mbox_conf_flat')(
net['conv8_2_mbox_conf'])
priorbox = PriorBox(input_shape,
anchors_size[4],
max_size=anchors_size[5],
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# 对conv9_2进行处理
# 1,1,256
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv9_2_mbox_loc')(net['conv9_2'])
net['conv9_2_mbox_loc'] = x
net['conv9_2_mbox_loc_flat'] = Flatten(name='conv9_2_mbox_loc_flat')(
net['conv9_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv9_2_mbox_conf')(net['conv9_2'])
net['conv9_2_mbox_conf'] = x
net['conv9_2_mbox_conf_flat'] = Flatten(name='conv9_2_mbox_conf_flat')(
net['conv9_2_mbox_conf'])
priorbox = PriorBox(input_shape,
anchors_size[5],
max_size=anchors_size[6],
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv9_2_mbox_priorbox')
net['conv9_2_mbox_priorbox'] = priorbox(net['conv9_2'])
# 将所有结果进行堆叠
net['mbox_loc'] = concatenate([
net['conv4_3_norm_mbox_loc_flat'], net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'], net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'], net['conv9_2_mbox_loc_flat']
],
axis=1,
name='mbox_loc')
net['mbox_conf'] = concatenate([
net['conv4_3_norm_mbox_conf_flat'], net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'], net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'], net['conv9_2_mbox_conf_flat']
],
axis=1,
name='mbox_conf')
net['mbox_priorbox'] = concatenate([
net['conv4_3_norm_mbox_priorbox'], net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'], net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'], net['conv9_2_mbox_priorbox']
],
axis=1,
name='mbox_priorbox')
# 8732,4
net['mbox_loc'] = Reshape((-1, 4), name='mbox_loc_final')(net['mbox_loc'])
# 8732,21
net['mbox_conf'] = Reshape((-1, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
# 8732,8
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
# 8732,33
net['predictions'] = concatenate(
[net['mbox_loc'], net['mbox_conf'], net['mbox_priorbox']],
axis=2,
name='predictions')
model = Model(net['input'], net['predictions'])
return model
def SSD300(input_shape, num_classes=21):
# 300,300,3
input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
# SSD结构,net字典
net = VGG16(input_tensor)
#-----------------------将提取到的主干特征进行处理---------------------------#
# 对conv4_3进行处理 38,38,512
net['conv4_3_norm'] = Normalize(20, name='conv4_3_norm')(net['conv4_3'])
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
net['conv4_3_norm_mbox_loc'] = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv4_3_norm_mbox_loc')(
net['conv4_3_norm'])
net['conv4_3_norm_mbox_loc_flat'] = Flatten(
name='conv4_3_norm_mbox_loc_flat')(net['conv4_3_norm_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
net['conv4_3_norm_mbox_conf'] = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv4_3_norm_mbox_conf')(
net['conv4_3_norm'])
net['conv4_3_norm_mbox_conf_flat'] = Flatten(
name='conv4_3_norm_mbox_conf_flat')(net['conv4_3_norm_mbox_conf'])
priorbox = PriorBox(img_size,
30.0,
max_size=60.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_norm_mbox_priorbox')
net['conv4_3_norm_mbox_priorbox'] = priorbox(net['conv4_3_norm'])
# 对fc7层进行处理
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
net['fc7_mbox_loc'] = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='fc7_mbox_loc')(net['fc7'])
net['fc7_mbox_loc_flat'] = Flatten(name='fc7_mbox_loc_flat')(
net['fc7_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
net['fc7_mbox_conf'] = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='fc7_mbox_conf')(net['fc7'])
net['fc7_mbox_conf_flat'] = Flatten(name='fc7_mbox_conf_flat')(
net['fc7_mbox_conf'])
priorbox = PriorBox(img_size,
60.0,
max_size=111.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# 对conv6_2进行处理
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
net['conv6_2_mbox_loc_flat'] = Flatten(name='conv6_2_mbox_loc_flat')(
net['conv6_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv6_2_mbox_conf')(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
net['conv6_2_mbox_conf_flat'] = Flatten(name='conv6_2_mbox_conf_flat')(
net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size,
111.0,
max_size=162.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# 对conv7_2进行处理
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
net['conv7_2_mbox_loc_flat'] = Flatten(name='conv7_2_mbox_loc_flat')(
net['conv7_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv7_2_mbox_conf')(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
net['conv7_2_mbox_conf_flat'] = Flatten(name='conv7_2_mbox_conf_flat')(
net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size,
162.0,
max_size=213.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# 对conv8_2进行处理
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
net['conv8_2_mbox_loc_flat'] = Flatten(name='conv8_2_mbox_loc_flat')(
net['conv8_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv8_2_mbox_conf')(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
net['conv8_2_mbox_conf_flat'] = Flatten(name='conv8_2_mbox_conf_flat')(
net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size,
213.0,
max_size=264.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# 对conv9_2进行处理
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv9_2_mbox_loc')(net['conv9_2'])
net['conv9_2_mbox_loc'] = x
net['conv9_2_mbox_loc_flat'] = Flatten(name='conv9_2_mbox_loc_flat')(
net['conv9_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv9_2_mbox_conf')(net['conv9_2'])
net['conv9_2_mbox_conf'] = x
net['conv9_2_mbox_conf_flat'] = Flatten(name='conv9_2_mbox_conf_flat')(
net['conv9_2_mbox_conf'])
priorbox = PriorBox(img_size,
264.0,
max_size=315.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv9_2_mbox_priorbox')
net['conv9_2_mbox_priorbox'] = priorbox(net['conv9_2'])
# 将所有结果进行堆叠
net['mbox_loc'] = concatenate([
net['conv4_3_norm_mbox_loc_flat'], net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'], net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'], net['conv9_2_mbox_loc_flat']
],
axis=1,
name='mbox_loc')
net['mbox_conf'] = concatenate([
net['conv4_3_norm_mbox_conf_flat'], net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'], net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'], net['conv9_2_mbox_conf_flat']
],
axis=1,
name='mbox_conf')
net['mbox_priorbox'] = concatenate([
net['conv4_3_norm_mbox_priorbox'], net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'], net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'], net['conv9_2_mbox_priorbox']
],
axis=1,
name='mbox_priorbox')
# if hasattr(net['mbox_loc'], '_keras_shape'):
# num_boxes = net['mbox_loc']._keras_shape[-1] // 4
# elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
# 8732,4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
# 8732,21
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = concatenate(
[net['mbox_loc'], net['mbox_conf'], net['mbox_priorbox']],
axis=2,
name='predictions')
print(net['predictions'])
model = Model(net['input'], net['predictions'])
return model
def SSD300(input_shape, num_classes=21):
# 300,300,3
input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
mbn3L_model = MobileNetV3_Small(
shape=input_shape,
n_class=num_classes,
include_top=False,
backbone=True,
input_tensor=input_tensor).build(plot=False)
# SSD结构,net字典
#net = mobilenet(input_tensor)
net = mbn3L_model
#-----------------------将提取到的主干特征进行处理---------------------------#
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
net['conv4_3_loc'] = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv4_3_loc')(net['conv4_3'])
net['conv4_3_loc_flat'] = Flatten(name='conv4_3_loc_flat')(
net['conv4_3_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
net['conv4_3_conf'] = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv4_3_conf')(net['conv4_3'])
net['conv4_3_conf_flat'] = Flatten(name='conv4_3_conf_flat')(
net['conv4_3_conf'])
priorbox = PriorBox(img_size,
30.0,
max_size=60.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_priorbox')
net['conv4_3_priorbox'] = priorbox(net['conv4_3'])
# 对fc7层进行处理
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
net['fc7_mbox_loc'] = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='fc7_mbox_loc')(net['fc7'])
net['fc7_mbox_loc_flat'] = Flatten(name='fc7_mbox_loc_flat')(
net['fc7_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
net['fc7_mbox_conf'] = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='fc7_mbox_conf')(net['fc7'])
net['fc7_mbox_conf_flat'] = Flatten(name='fc7_mbox_conf_flat')(
net['fc7_mbox_conf'])
priorbox = PriorBox(img_size,
60.0,
max_size=111.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# 对conv6_2进行处理
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
net['conv6_2_mbox_loc_flat'] = Flatten(name='conv6_2_mbox_loc_flat')(
net['conv6_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv6_2_mbox_conf')(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
net['conv6_2_mbox_conf_flat'] = Flatten(name='conv6_2_mbox_conf_flat')(
net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size,
111.0,
max_size=162.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# 对conv7_2进行处理
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
net['conv7_2_mbox_loc_flat'] = Flatten(name='conv7_2_mbox_loc_flat')(
net['conv7_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv7_2_mbox_conf')(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
net['conv7_2_mbox_conf_flat'] = Flatten(name='conv7_2_mbox_conf_flat')(
net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size,
162.0,
max_size=213.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# 对conv8_2进行处理
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
net['conv8_2_mbox_loc_flat'] = Flatten(name='conv8_2_mbox_loc_flat')(
net['conv8_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv8_2_mbox_conf')(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
net['conv8_2_mbox_conf_flat'] = Flatten(name='conv8_2_mbox_conf_flat')(
net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size,
213.0,
max_size=264.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# 对conv9_2进行处理
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv9_2_mbox_loc')(net['conv9_2'])
net['conv9_2_mbox_loc'] = x
net['conv9_2_mbox_loc_flat'] = Flatten(name='conv9_2_mbox_loc_flat')(
net['conv9_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv9_2_mbox_conf')(net['conv9_2'])
net['conv9_2_mbox_conf'] = x
net['conv9_2_mbox_conf_flat'] = Flatten(name='conv9_2_mbox_conf_flat')(
net['conv9_2_mbox_conf'])
priorbox = PriorBox(img_size,
264.0,
max_size=315.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv9_2_mbox_priorbox')
net['conv9_2_mbox_priorbox'] = priorbox(net['conv9_2'])
# 将所有结果进行堆叠
net['mbox_loc'] = concatenate([
net['conv4_3_loc_flat'], net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'], net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'], net['conv9_2_mbox_loc_flat']
],
axis=1,
name='mbox_loc')
net['mbox_conf'] = concatenate([
net['conv4_3_conf_flat'], net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'], net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'], net['conv9_2_mbox_conf_flat']
],
axis=1,
name='mbox_conf')
net['mbox_priorbox'] = concatenate([
net['conv4_3_priorbox'], net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'], net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'], net['conv9_2_mbox_priorbox']
],
axis=1,
name='mbox_priorbox')
if hasattr(net['mbox_loc'], '_keras_shape'):
num_boxes = net['mbox_loc']._keras_shape[-1] // 4
elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
# 8732,4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
# 8732,21
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = concatenate(
[net['mbox_loc'], net['mbox_conf'], net['mbox_priorbox']],
axis=2,
name='predictions')
model = Model(input_tensor, net['predictions'])
return model
class SSD(nn.Module):
def __init__(self, phase, base, extras, head, num_classes, confidence,
nms_iou):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
self.cfg = Config
self.vgg = nn.ModuleList(base)
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.priorbox = PriorBox(self.cfg)
with torch.no_grad():
self.priors = Variable(self.priorbox.forward())
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, confidence, nms_iou)
def forward(self, x):
sources = list()
loc = list()
conf = list()
#---------------------------#
# 获得conv4_3的内容
# shape为38,38,512
#---------------------------#
for k in range(23):
x = self.vgg[k](x)
#---------------------------#
# conv4_3的内容
# 需要进行L2标准化
#---------------------------#
s = self.L2Norm(x)
sources.append(s)
#---------------------------#
# 获得conv7的内容
# shape为19,19,1024
#---------------------------#
for k in range(23, len(self.vgg)):
x = self.vgg[k](x)
sources.append(x)
#-------------------------------------------------------------#
# 在add_extras获得的特征层里
# 第1层、第3层、第5层、第7层可以用来进行回归预测和分类预测。
# shape分别为(10,10,512), (5,5,256), (3,3,256), (1,1,256)
#-------------------------------------------------------------#
for k, v in enumerate(self.extras):
x = F.relu(v(x), inplace=True)
if k % 2 == 1:
sources.append(x)
#-------------------------------------------------------------#
# 为获得的6个有效特征层添加回归预测和分类预测
#-------------------------------------------------------------#
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())
#-------------------------------------------------------------#
# 进行reshape方便堆叠
#-------------------------------------------------------------#
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)
#-------------------------------------------------------------#
# loc会reshape到batch_size,num_anchors,4
# conf会reshap到batch_size,num_anchors,self.num_classes
# 如果用于预测的话，会添加上detect用于对先验框解码，获得预测结果
# 不用于预测的话，直接返回网络的回归预测结果和分类预测结果用于训练
#-------------------------------------------------------------#
if self.phase == "test":
output = self.detect(
loc.view(loc.size(0), -1, 4),
self.softmax(conf.view(conf.size(0), -1, self.num_classes)),
self.priors)
else:
output = (loc.view(loc.size(0), -1,
4), conf.view(conf.size(0), -1,
self.num_classes), self.priors)
return output
def __init__(self, phase, base, extras, head, num_classes):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
self.cfg = Config
self.vgg = nn.ModuleList(base)
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.priorbox = PriorBox(self.cfg)
with torch.no_grad():
self.priors = Variable(self.priorbox.forward())
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)
self.upsample_256_256 = Upsample(10)
self.conv_256_512 = nn.Conv2d(in_channels=256,
out_channels=512,
kernel_size=1,
stride=1)
#conv8_2 -> conv8_2
self.conv_512_512_1 = nn.Conv2d(in_channels=512,
out_channels=512,
kernel_size=1,
stride=1)
self.upsample_512_512 = Upsample(19)
self.conv_512_1024 = nn.Conv2d(in_channels=512,
out_channels=1024,
kernel_size=1,
stride=1)
self.conv_1024_1024 = nn.Conv2d(in_channels=1024,
out_channels=1024,
kernel_size=1,
stride=1)
self.upsample_1024_1024 = Upsample(38)
self.conv_1024_512 = nn.Conv2d(in_channels=1024,
out_channels=512,
kernel_size=1,
stride=1)
self.conv_512_512_2 = nn.Conv2d(in_channels=512,
out_channels=512,
kernel_size=1,
stride=1)
self.smooth = nn.Conv2d(512, 512, kernel_size=3, padding=1, stride=1)
self.smooth1 = nn.Conv2d(1024,
1024,
kernel_size=3,
padding=1,
stride=1)
if USE_CBAM:
self.CBAM1 = Bottleneck(512)
self.CBAM2 = Bottleneck(1024)
self.CBAM3 = Bottleneck(512)
self.CBAM4 = Bottleneck(256)
self.CBAM5 = Bottleneck(256)
self.CBAM6 = Bottleneck(256)
if USE_SE:
self.SE1 = SEModule(512)
self.SE2 = SEModule(1024)
self.SE3 = SEModule(512)
self.SE4 = SEModule(256)
self.SE5 = SEModule(256)
self.SE6 = SEModule(256)
class SSD(nn.Module):
def __init__(self, phase, base, extras, head, num_classes):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
self.cfg = Config
self.vgg = nn.ModuleList(base)
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.priorbox = PriorBox(self.cfg)
with torch.no_grad():
self.priors = Variable(self.priorbox.forward())
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)
self.upsample_256_256 = Upsample(10)
self.conv_256_512 = nn.Conv2d(in_channels=256,
out_channels=512,
kernel_size=1,
stride=1)
#conv8_2 -> conv8_2
self.conv_512_512_1 = nn.Conv2d(in_channels=512,
out_channels=512,
kernel_size=1,
stride=1)
self.upsample_512_512 = Upsample(19)
self.conv_512_1024 = nn.Conv2d(in_channels=512,
out_channels=1024,
kernel_size=1,
stride=1)
self.conv_1024_1024 = nn.Conv2d(in_channels=1024,
out_channels=1024,
kernel_size=1,
stride=1)
self.upsample_1024_1024 = Upsample(38)
self.conv_1024_512 = nn.Conv2d(in_channels=1024,
out_channels=512,
kernel_size=1,
stride=1)
self.conv_512_512_2 = nn.Conv2d(in_channels=512,
out_channels=512,
kernel_size=1,
stride=1)
self.smooth = nn.Conv2d(512, 512, kernel_size=3, padding=1, stride=1)
self.smooth1 = nn.Conv2d(1024,
1024,
kernel_size=3,
padding=1,
stride=1)
if USE_CBAM:
self.CBAM1 = Bottleneck(512)
self.CBAM2 = Bottleneck(1024)
self.CBAM3 = Bottleneck(512)
self.CBAM4 = Bottleneck(256)
self.CBAM5 = Bottleneck(256)
self.CBAM6 = Bottleneck(256)
if USE_SE:
self.SE1 = SEModule(512)
self.SE2 = SEModule(1024)
self.SE3 = SEModule(512)
self.SE4 = SEModule(256)
self.SE5 = SEModule(256)
self.SE6 = SEModule(256)
def forward(self, x):
sources = list()
attention = list()
loc = list()
conf = list()
# 获得conv4_3的内容
for k in range(10):
x = self.vgg[k](x)
sources.append(x)
for k in range(23, 30):
x = self.vgg[k](x)
s = self.L2Norm(x)
sources.append(s)
# 获得fc7的内容
for k in range(30, len(self.vgg)):
x = self.vgg[k](x)
sources.append(x)
# 获得后面的内容
for k, v in enumerate(self.extras):
x = F.relu(v(x), inplace=True)
if k % 2 == 1:
sources.append(x)
if USE_SE:
attention.append(sources[0])
attention.append(self.SE1(sources[1]))
attention.append(sources[2])
attention.append(self.SE2(sources[3]))
attention.append(self.SE3(sources[4]))
attention.append(self.SE4(sources[5]))
attention.append(self.SE5(sources[6]))
attention.append(self.SE6(sources[7]))
sources_final = list()
conv8_fp1 = self.conv_256_512(self.upsample_256_256(
attention[5])) + self.conv_512_512_1(attention[4])
conv8_fp = self.smooth(conv8_fp1)
fc7_fp1 = self.conv_512_1024(
self.upsample_512_512(conv8_fp1)) + self.conv_1024_1024(
attention[3])
fc7_fp = self.smooth(fc7_fp1)
conv4_fp = self.conv_1024_512(
self.upsample_1024_1024(fc7_fp1)) + self.conv_512_512_2(
attention[1])
conv4_fp = self.smooth(conv4_fp)
if USE_CBAM:
sources_final.append(self.CBAM1(conv4_fp))
sources_final.append(self.CBAM2(fc7_fp))
sources_final.append(self.CBAM3(conv8_fp))
sources_final.append(self.CBAM4(sources[5]))
sources_final.append(self.CBAM5(sources[6]))
sources_final.append(self.CBAM6(sources[7]))
else:
sources_final.append(conv4_fp)
sources_final.append(fc7_fp)
sources_final.append(conv8_fp)
sources_final.append(attention[5])
sources_final.append(attention[6])
sources_final.append(attention[7])
# 添加回归层和分类层
# 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())
for (x, l, c) in zip(sources_final, self.loc, self.conf):
loc.append(l(x).permute(0, 2, 3, 1).contiguous())
conf.append(c(x).permute(0, 2, 3, 1).contiguous())
# 进行resize
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":
# loc会resize到batch_size,num_anchors,4
# conf会resize到batch_size,num_anchors,
# 这部分暂时没有进行改动
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)
else:
output = (loc.view(loc.size(0), -1,
4), conf.view(conf.size(0), -1,
self.num_classes), self.priors)
return output
class SSD(nn.Module):
def __init__(self, phase, base, extras, head, num_classes):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
self.cfg = Config
self.vgg = nn.ModuleList(base)
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.priorbox = PriorBox(self.cfg)
with torch.no_grad():
self.priors = Variable(self.priorbox.forward())
# self.priors = self.priorbox.forward() # 这一行改成这样也能正常运行
self.loc = nn.ModuleList(head[0])
self.conf = nn.ModuleList(head[1])
self.relu_list4cxq = nn.ModuleList([torch.nn.ReLU(True) for i in range(8)]) # 自己修改后的方式
self.feature_maps4cxq = None # 用于grad cam
self.scores4cxq = None # 用于grad cam
if phase == 'test':
self.softmax = nn.Softmax(dim=-1)
self.detect = Detect(num_classes, 0, 200, 0.01, 0.45)
def forward(self, x):
sources = list()
loc = list()
conf = list()
# 获得conv4_3的内容
for k in range(23):
x = self.vgg[k](x)
s = self.L2Norm(x)
sources.append(s)
# 获得fc7的内容
for k in range(23, len(self.vgg)):
x = self.vgg[k](x)
sources.append(x)
# 获得后面的内容
for k, v in enumerate(self.extras):
# x = F.relu(v(x), inplace=True) # 原始实现方式
x = self.relu_list4cxq[k](v(x)) # 修改后的方式
if k % 2 == 1:
sources.append(x)
self.feature_maps4cxq = sources # 6张特征图
# 添加回归层和分类层
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())
self.scores4cxq = conf # 用于保存各个类别的分数
# 进行resize
loc = torch.cat([o.view(o.size(0), -1) for o in loc], 1) # torch.Size([4, 34928])
conf = torch.cat([o.view(o.size(0), -1) for o in conf], 1) # torch.Size([4, 26196])
if self.phase == "test":
# loc会resize到batch_size,num_anchors,4
# conf会resize到batch_size,num_anchors,num_classes
# output = self.detect(
output = self.detect.apply(
loc.view(loc.size(0), -1, 4), # loc preds torch.Size([4, 8732, 4])
self.softmax(conf.view(conf.size(0), -1,
self.num_classes)), # conf preds # torch.Size([4, 8732, 3])
self.priors # torch.Size([8732, 4])
) # torch.Size([1, 3, 200, 5]) 1置信度+4位置信息
else:
output = (
loc.view(loc.size(0), -1, 4),
conf.view(conf.size(0), -1, self.num_classes),
self.priors
) # torch.Size([4, 8732, 4]) torch.Size([4, 8732, 3]) torch.Size([8732, 4])
return output
def __init__(self, phase, base, extras, head, num_classes):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
self.cfg = Config
self.vgg = nn.ModuleList(base)
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.priorbox = PriorBox(self.cfg)
with torch.no_grad():
self.priors = Variable(self.priorbox.forward())
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)
self.DilationConv_128_128 = nn.Conv2d(in_channels=128,
out_channels=128,
kernel_size=3,
padding=2,
dilation=2,
stride=2)
self.conv_512_256 = nn.Conv2d(in_channels=512,
out_channels=256,
kernel_size=1,
stride=1)
self.upsample_1024_1024 = Upsample(38)
self.conv_1024_128 = nn.Conv2d(in_channels=1024,
out_channels=128,
kernel_size=1,
stride=1)
self.DilationConv_512_256 = nn.Conv2d(in_channels=512,
out_channels=256,
kernel_size=3,
padding=2,
dilation=2,
stride=2)
self.conv_1024_512 = nn.Conv2d(in_channels=1024,
out_channels=512,
kernel_size=1,
stride=1)
self.upsample_512_512 = Upsample(19)
self.conv_512_256_fc7 = nn.Conv2d(in_channels=512,
out_channels=256,
kernel_size=1,
stride=1)
self.DilationConv_512_128_2 = nn.Conv2d(in_channels=512,
out_channels=128,
kernel_size=3,
padding=2,
dilation=2,
stride=2)
self.conv_512_256_2 = nn.Conv2d(in_channels=512,
out_channels=256,
kernel_size=1,
stride=1)
self.upsample_256_256_2 = Upsample(10)
self.conv_256_128_2 = nn.Conv2d(in_channels=256,
out_channels=128,
kernel_size=1,
stride=1)
self.smooth = nn.Conv2d(512, 512, kernel_size=3, padding=1, stride=1)
self.smooth2 = nn.Conv2d(1024,
1024,
kernel_size=3,
padding=1,
stride=1)
self.bn = nn.BatchNorm2d(128)
self.bn1 = nn.BatchNorm2d(256)
if USE_SE:
self.SE1 = SEModule(512)
self.SE2 = SEModule(512)
self.SE3 = SEModule(512)
self.SE4 = SEModule(256)
self.SE5 = SEModule(256)
self.SE6 = SEModule(256)
if USE_ECA:
self.ECA1 = ECAModule(512)
self.ECA2 = ECAModule(1024)
self.ECA3 = ECAModule(512)
self.ECA4 = ECAModule(256)
class SSD(nn.Module):
def __init__(self, phase, base, extras, head, num_classes):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
self.cfg = Config
self.vgg = nn.ModuleList(base)
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.priorbox = PriorBox(self.cfg)
with torch.no_grad():
self.priors = Variable(self.priorbox.forward())
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)
self.DilationConv_128_128 = nn.Conv2d(in_channels=128,
out_channels=128,
kernel_size=3,
padding=2,
dilation=2,
stride=2)
self.conv_512_256 = nn.Conv2d(in_channels=512,
out_channels=256,
kernel_size=1,
stride=1)
self.upsample_1024_1024 = Upsample(38)
self.conv_1024_128 = nn.Conv2d(in_channels=1024,
out_channels=128,
kernel_size=1,
stride=1)
self.DilationConv_512_256 = nn.Conv2d(in_channels=512,
out_channels=256,
kernel_size=3,
padding=2,
dilation=2,
stride=2)
self.conv_1024_512 = nn.Conv2d(in_channels=1024,
out_channels=512,
kernel_size=1,
stride=1)
self.upsample_512_512 = Upsample(19)
self.conv_512_256_fc7 = nn.Conv2d(in_channels=512,
out_channels=256,
kernel_size=1,
stride=1)
self.DilationConv_512_128_2 = nn.Conv2d(in_channels=512,
out_channels=128,
kernel_size=3,
padding=2,
dilation=2,
stride=2)
self.conv_512_256_2 = nn.Conv2d(in_channels=512,
out_channels=256,
kernel_size=1,
stride=1)
self.upsample_256_256_2 = Upsample(10)
self.conv_256_128_2 = nn.Conv2d(in_channels=256,
out_channels=128,
kernel_size=1,
stride=1)
self.smooth = nn.Conv2d(512, 512, kernel_size=3, padding=1, stride=1)
self.smooth2 = nn.Conv2d(1024,
1024,
kernel_size=3,
padding=1,
stride=1)
self.bn = nn.BatchNorm2d(128)
self.bn1 = nn.BatchNorm2d(256)
if USE_SE:
self.SE1 = SEModule(512)
self.SE2 = SEModule(512)
self.SE3 = SEModule(512)
self.SE4 = SEModule(256)
self.SE5 = SEModule(256)
self.SE6 = SEModule(256)
if USE_ECA:
self.ECA1 = ECAModule(512)
self.ECA2 = ECAModule(1024)
self.ECA3 = ECAModule(512)
self.ECA4 = ECAModule(256)
def forward(self, x):
sources = list()
loc = list()
conf = list()
for k in range(10):
x = self.vgg[k](x)
sources.append(x)
# 获得conv4_3的内容
for k in range(10, 23):
x = self.vgg[k](x)
s = self.L2Norm(x)
sources.append(s)
# 获得fc7的内容
# for k in range(23, len(self.vgg)):
# x = self.vgg[k](x)
# sources.append(x)
for k in range(23, 30):
x = self.vgg[k](x)
s = self.L2Norm(x)
sources.append(s)
for k in range(30, len(self.vgg)):
x = self.vgg[k](x)
sources.append(x)
# 获得后面的内容
for k, v in enumerate(self.extras):
x = F.relu(v(x), inplace=True)
if k % 2 == 1:
sources.append(x)
sources_final = list()
sources_final1 = list()
if USE_ECA:
sources_final.append(self.ECA4(sources[5]))
else:
sources_final.append(sources[5])
conv8_fp1 = torch.cat(
(F.relu(self.bn(self.DilationConv_512_128_2(sources[2])),
inplace=True),
F.relu(self.conv_512_256_2(sources[4]), inplace=True),
F.relu(self.conv_256_128_2(self.upsample_256_256_2(sources[5])),
inplace=True)), 1)
conv8_fp = F.relu(self.smooth(conv8_fp1), inplace=True)
if USE_ECA:
sources_final.append(self.ECA3(conv8_fp))
else:
sources_final.append(conv8_fp)
# fc7_fp = torch.cat((F.relu(self.bn(self.DilationConv_512_256(sources[1])),inplace=True),
# F.relu(self.conv_1024_512(sources[3]),inplace=True),
# F.relu(self.conv512_256_fc7(self.upsample_512_512(sources[4])),inplace=True)),1)
# fc7_fp1 = torch.cat((F.relu(self.bn1(self.DilationConv_512_256(sources[1])),inplace=True),
# F.relu(self.conv_1024_512(sources[3]),inplace=True),
# F.relu(self.conv_512_256_fc7(self.upsample_512_512(sources[4])),inplace=True)),1)
fc7_fp1 = torch.cat(
(F.relu(self.bn1(self.DilationConv_512_256(sources[1])),
inplace=True),
F.relu(self.conv_1024_512(sources[3]), inplace=True),
F.relu(self.conv_512_256_fc7(self.upsample_512_512(sources[4])),
inplace=True)), 1)
fc7_fp = F.relu(self.smooth2(fc7_fp1), inplace=True)
if USE_ECA:
sources_final.append(self.ECA2(fc7_fp))
else:
sources_final.append(fc7_fp)
conv4_fp = torch.cat(
(F.relu(self.bn(self.DilationConv_128_128(sources[0])),
inplace=True),
F.relu(self.conv_512_256(sources[1]), inplace=True),
F.relu(self.conv_1024_128(self.upsample_1024_1024(sources[3])),
inplace=True)), 1)
conv4_fp = F.relu(self.smooth(conv4_fp), inplace=True)
if USE_ECA:
sources_final.append(self.ECA1(conv4_fp))
else:
sources_final.append(conv4_fp)
# 添加回归层和分类层
# 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())
for (x, l, c) in zip(sources_final[::-1], self.loc, self.conf):
loc.append(l(x).permute(0, 2, 3, 1).contiguous())
conf.append(c(x).permute(0, 2, 3, 1).contiguous())
# 进行resize
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":
# loc会resize到batch_size,num_anchors,4
# conf会resize到batch_size,num_anchors,
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)
else:
output = (loc.view(loc.size(0), -1,
4), conf.view(conf.size(0), -1,
self.num_classes), self.priors)
return output