def _pyramidbox(self):
self.ssh_conv3_l2norm = nn.L2Norm2d(512, 10)
self.ssh_conv4_l2norm = nn.L2Norm2d(512, 8)
self.ssh_conv5_l2norm = nn.L2Norm2d(512, 5)
self.SSHchannels = [512, 512, 512, 512, 512, 512]
loc = []
conf = []
for i in range(6):
loc.append(
nn.Conv2d(self.SSHchannels[i],
8,
kernel_size=3,
stride=1,
padding=1))
if i == 0:
conf.append(
nn.Conv2d(self.SSHchannels[i],
8,
kernel_size=3,
stride=1,
padding=1))
else:
conf.append(
nn.Conv2d(self.SSHchannels[i],
6,
kernel_size=3,
stride=1,
padding=1))
self.mbox_loc = nn.ModuleList(loc)
self.mbox_conf = nn.ModuleList(conf)
self.softmax = nn.Softmax(dim=-1)
def build_detect_head(self):
bbox_pred = []
cls_score = []
for oc in self.ssh_out_channels:
bbox_pred += [ nn.Conv2d(in_channels=oc, out_channels=8, kernel_size=1, stride=1, padding=0) ]
cls_score += [ nn.Conv2d(in_channels=oc, out_channels=4, kernel_size=1, stride=1, padding=0) ]
return nn.ModuleList(bbox_pred), nn.ModuleList(cls_score)
def build_det_head(self):
bbox_head = []
cls_head = []
for i in range(3):
bbox_head += [
nn.Conv2d(128, 4, kernel_size=1, stride=1, padding=0)
]
cls_head += [nn.Conv2d(128, 2, kernel_size=1, stride=1, padding=0)]
return nn.ModuleList(bbox_head), nn.ModuleList(cls_head)
def __init__(self, model_type='32'):
super(EXTD, self).__init__()
self.model_type = int(model_type)
self.mobilenet = MobileNetV2(model_type=self.model_type)
if self.model_type == 32:
self.base = nn.ModuleList(self.mobilenet.features)[:8]
elif self.model_type == 48 or self.model_type == 64:
self.base = nn.ModuleList(self.mobilenet.features)[:6]
else:
raise NotImplementedError
self.upsample = nn.Upsample(scale_factor=2,
mode='bilinear',
align_corners=False)
self.eltadd = nn.EltAdd()
self.upfeat = []
for it in range(5):
self.upfeat.append(
upsample(in_channels=self.model_type,
out_channels=self.model_type))
self.upfeat = nn.ModuleList(self.upfeat)
self.loc = []
self.conf = []
self.net_source = [4, 4, 4, 4]
self.feature_dim = []
if self.model_type == 32:
self.feature_dim += [self.base[4].conv[-3].out_channels]
for idx in self.net_source:
self.feature_dim += [self.base[idx].conv[-3].out_channels]
else:
self.feature_dim += [self.base[4].conv[-2].out_channels]
for idx in self.net_source:
self.feature_dim += [self.base[idx].conv[-2].out_channels]
self.loc += [
nn.Conv2d(self.feature_dim[0], 4, kernel_size=3, padding=1)
]
self.conf += [
nn.Conv2d(self.feature_dim[0], 4, kernel_size=3, padding=1)
]
for k, v in enumerate(self.net_source, 1):
self.loc += [
nn.Conv2d(self.feature_dim[k], 4, kernel_size=3, padding=1)
]
self.conf += [
nn.Conv2d(self.feature_dim[k], 2, kernel_size=3, padding=1)
]
self.loc += [nn.Conv2d(self.model_type, 4, kernel_size=3, padding=1)]
self.conf += [nn.Conv2d(self.model_type, 2, kernel_size=3, padding=1)]
self.loc = nn.ModuleList(self.loc)
self.conf = nn.ModuleList(self.conf)
self.softmax = nn.Softmax(dim=-1)
def __init__(self):
super(light_DSFD, self).__init__()
self.conv1 = CRelu(3, 32, kernel_size=7, stride=4, padding=3)
self.conv3 = CRelu(64, 64, kernel_size=5, stride=2, padding=2)
self.inception1 = Inception2d(64)
self.inception2 = Inception2d(64)
self.inception3 = Inception2d(128)
self.inception4 = Inception2d(128)
self.maxpool1 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.maxpool2 = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.conv5_1 = BasicConv2d(128, 128, kernel_size=1, stride=1, padding=0)
self.conv5_2 = BasicConv2d(128, 256, kernel_size=3, stride=2, padding=1)
self.conv6_1 = BasicConv2d(256, 128, kernel_size=1, stride=1, padding=0)
self.conv6_2 = BasicConv2d(128, 256, kernel_size=3, stride=2, padding=1)
fpn_in = [64, 64, 128, 128, 256, 256]
cpm_in = [64, 64, 64, 64, 64, 64]
fpn_channel = 64
cpm_channels = 64
output_channels = cpm_in
# fpn
self.smooth3 = nn.Conv2d( fpn_channel, fpn_channel, kernel_size=1, stride=1, padding=0)
self.smooth2 = nn.Conv2d( fpn_channel, fpn_channel, kernel_size=1, stride=1, padding=0)
self.smooth1 = nn.Conv2d( fpn_channel, fpn_channel, kernel_size=1, stride=1, padding=0)
self.upsample = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=False)
self.eltmul = nn.EltMul()
self.latlayer6 = nn.Conv2d( fpn_in[5], fpn_channel, kernel_size=1, stride=1, padding=0)
self.latlayer5 = nn.Conv2d( fpn_in[4], fpn_channel, kernel_size=1, stride=1, padding=0)
self.latlayer4 = nn.Conv2d( fpn_in[3], fpn_channel, kernel_size=1, stride=1, padding=0)
self.latlayer3 = nn.Conv2d( fpn_in[2], fpn_channel, kernel_size=1, stride=1, padding=0)
self.latlayer2 = nn.Conv2d( fpn_in[1], fpn_channel, kernel_size=1, stride=1, padding=0)
self.latlayer1 = nn.Conv2d( fpn_in[0], fpn_channel, kernel_size=1, stride=1, padding=0)
# cpm
self.cpm1 = Inception2d(cpm_in[0])
self.cpm2 = Inception2d(cpm_in[1])
self.cpm3 = Inception2d(cpm_in[2])
self.cpm4 = Inception2d(cpm_in[3])
self.cpm5 = Inception2d(cpm_in[4])
self.cpm6 = Inception2d(cpm_in[5])
face_head = face_multibox(output_channels, [1, 1, 1, 1, 1, 1], 2 , cpm_channels)
self.loc = nn.ModuleList(face_head[0])
self.conf = nn.ModuleList(face_head[1])
self.softmax = nn.Softmax(dim=-1)
def __init__(self):
super(SSH, self).__init__()
# backbone
self.vgg16 = nn.ModuleList(make_layers(vgg_cfgs['D']))
# SSH - M3
self.M3 = M_Module(512, 256, 128)
self.M3_bbox_pred = nn.Conv2d(512, 8, 1, 1, 0)
self.M3_cls_score = nn.Conv2d(512, 4, 1, 1, 0)
self.M3_cls_score_softmax = nn.Softmax(dim=1)
# SSH - M2
self.M2 = M_Module(512, 256, 128)
self.M2_bbox_pred = nn.Conv2d(512, 8, 1, 1, 0)
self.M2_cls_score = nn.Conv2d(512, 4, 1, 1, 0)
self.M2_cls_score_softmax = nn.Softmax(dim=1)
# SSH - M1
self.conv4_128 = nn.Conv2d(512, 128, 1, 1, 0)
self.conv4_128_relu = nn.ReLU(inplace=True)
self.conv5_128 = nn.Conv2d(512, 128, 1, 1, 0)
self.conv5_128_relu = nn.ReLU(inplace=True)
self.conv5_128_up = nn.ConvTranspose2d(128, 128, 4, 2, 1, groups=128, bias=False)
self.eltadd = nn.EltAdd()
self.conv4_fuse_final = nn.Conv2d(128, 128, 3, 1, 1)
self.conv4_fuse_final_relu = nn.ReLU(inplace=True)
self.M1 = M_Module(128, 128, 64)
self.M1_bbox_pred = nn.Conv2d(256, 8, 1, 1, 0)
self.M1_cls_score = nn.Conv2d(256, 4, 1, 1, 0)
self.M1_cls_score_softmax = nn.Softmax(dim=1)
def __init__(self):
super(HR, self).__init__()
self.conv = ConvBlock(3, 64, 7, 2, add_relu=True)
self.pool = nn.MaxPool2d(3, 2, 1)
self.res2a = ResidualBlock('res2a', 64, 64, 256, downsample=True)
self.res2b = ResidualBlock('res2b', 256, 64, 256)
self.res2c = ResidualBlock('res2c', 256, 64, 256)
self.res3a = ResidualBlock('res3a', 256, 128, 512, downsample=True)
self.res3b1 = ResidualBlock('res3b1', 512, 128, 512)
self.res3b2 = ResidualBlock('res3b2', 512, 128, 512)
self.res3b3 = ResidualBlock('res3b3', 512, 128, 512)
self.res4a = ResidualBlock('res4a', 512, 256, 1024, downsample=True)
self.res4bX = nn.ModuleList()
for i in range(0, 22):
self.res4bX.append(ResidualBlock('res4bX', 1024, 256, 1024))
# Detection Head
self.score_res4 = ConvBlock(1024, 125, 1, bias=True, add_relu=False, add_bn=False)
self.score4 = ConvTransLayer(125, 125, 4, 2, 0)
self.score_res3 = ConvBlock(512, 125, 1, bias=True, add_relu=False, add_bn=False)
self.eltadd = nn.EltAdd()
def __init__(self):
super(NN, self).__init__()
self.conv = nn.Conv2d(3, 64, 3, 1, 1)
self.headers = nn.ModuleList(
[nn.Conv2d(64, 4, 3, 1, 1),
nn.Conv2d(64, 2, 3, 1, 1)])
def __init__(self, mode='slim'):
super(ULFG, self).__init__()
self.mode = mode
self.base_channel = 8 * 2
self.backbone = nn.Sequential(
_conv_bn(3, self.base_channel, 2), # 160*120
_conv_dw(self.base_channel, self.base_channel * 2, 1),
_conv_dw(self.base_channel * 2, self.base_channel * 2, 2), # 80*60
_conv_dw(self.base_channel * 2, self.base_channel * 2, 1),
_conv_dw(self.base_channel * 2, self.base_channel * 4, 2), # 40*30
_conv_dw(self.base_channel * 4, self.base_channel * 4, 1),
_conv_dw(self.base_channel * 4, self.base_channel * 4, 1),
_conv_dw(self.base_channel * 4, self.base_channel * 4, 1),
_conv_dw(self.base_channel * 4, self.base_channel * 8, 2), # 20*15
_conv_dw(self.base_channel * 8, self.base_channel * 8, 1),
_conv_dw(self.base_channel * 8, self.base_channel * 8, 1),
_conv_dw(self.base_channel * 8, self.base_channel * 16, 2), # 10*8
_conv_dw(self.base_channel * 16, self.base_channel * 16, 1)
)
if self.mode == 'rfb':
self.backbone[7] = BasicRFB(self.base_channel * 4, self.base_channel * 4, stride=1, scale=1.0)
self.source_layer_indexes = [8, 11, 13]
self.extras = nn.Sequential(
nn.Conv2d(in_channels=self.base_channel * 16, out_channels=self.base_channel * 4, kernel_size=1),
nn.ReLU(),
_seperable_conv2d(in_channels=self.base_channel * 4, out_channels=self.base_channel * 16, kernel_size=3, stride=2, padding=1),
nn.ReLU()
)
self.regression_headers = nn.ModuleList([
_seperable_conv2d(in_channels=self.base_channel * 4, out_channels=3 * 4, kernel_size=3, padding=1),
_seperable_conv2d(in_channels=self.base_channel * 8, out_channels=2 * 4, kernel_size=3, padding=1),
_seperable_conv2d(in_channels=self.base_channel * 16, out_channels=2 * 4, kernel_size=3, padding=1),
nn.Conv2d(in_channels=self.base_channel * 16, out_channels=3 * 4, kernel_size=3, padding=1)
])
self.classification_headers = nn.ModuleList([
_seperable_conv2d(in_channels=self.base_channel * 4, out_channels=3 * 2, kernel_size=3, padding=1),
_seperable_conv2d(in_channels=self.base_channel * 8, out_channels=2 * 2, kernel_size=3, padding=1),
_seperable_conv2d(in_channels=self.base_channel * 16, out_channels=2 * 2, kernel_size=3, padding=1),
nn.Conv2d(in_channels=self.base_channel * 16, out_channels=3 * 2, kernel_size=3, padding=1)
])
self.softmax = nn.Softmax(dim=2)
def __init__(self):
super(S3FD, self).__init__()
# backbone
self.vgg16 = nn.ModuleList(make_layers(vgg_cfgs['D']))
# s3fd specific
self.conv_fc6 = nn.Conv2d(512, 1024, 3, 1, 1)
self.relu_fc6 = nn.ReLU()
self.conv_fc7 = nn.Conv2d(1024, 1024, 1, 1, 0)
self.relu_fc7 = nn.ReLU()
self.conv6_1 = nn.Conv2d(1024, 256, 1, 1, 0)
self.relu_conv6_1 = nn.ReLU()
self.conv6_2 = nn.Conv2d(256, 512, 3, 2, 1)
self.relu_conv6_2 = nn.ReLU()
self.conv7_1 = nn.Conv2d(512, 128, 1, 1, 0)
self.relu_conv7_1 = nn.ReLU()
self.conv7_2 = nn.Conv2d(128, 256, 3, 2, 1)
self.relu_conv7_2 = nn.ReLU()
self.l2norm_conv3_3 = nn.L2Norm2d(256, 10)
self.l2norm_conv4_3 = nn.L2Norm2d(512, 8)
self.l2norm_conv5_3 = nn.L2Norm2d(512, 5)
# Detection Head - mbox_loc
self.mbox_loc_conv3_3_norm = nn.Conv2d(256, 4, 3, 1, 1)
self.mbox_loc_conv4_3_norm = nn.Conv2d(512, 4, 3, 1, 1)
self.mbox_loc_conv5_3_norm = nn.Conv2d(512, 4, 3, 1, 1)
self.mbox_loc_conv_fc7 = nn.Conv2d(1024, 4, 3, 1, 1)
self.mbox_loc_conv6_2 = nn.Conv2d(512, 4, 3, 1, 1)
self.mbox_loc_conv7_2 = nn.Conv2d(256, 4, 3, 1, 1)
# Detection Head - mbox_conf
self.mbox_conf_conv3_3_norm = nn.Conv2d(
256, 4, 3, 1, 1) # 4->2 through maxout at channels 0~2
self.mbox_conf_conv4_3_norm = nn.Conv2d(512, 2, 3, 1, 1)
self.mbox_conf_conv5_3_norm = nn.Conv2d(512, 2, 3, 1, 1)
self.mbox_conf_conv_fc7 = nn.Conv2d(1024, 2, 3, 1, 1)
self.mbox_conf_conv6_2 = nn.Conv2d(512, 2, 3, 1, 1)
self.mbox_conf_conv7_2 = nn.Conv2d(256, 2, 3, 1, 1)
# Detection Head - mbox_conf - softmax
self.softmax = nn.Softmax(dim=-1)
def __init__(self):
super(DSFD, self).__init__()
self.size = 640
self.num_classes = 2
######
# build backbone
######
resnet152 = vision.models.resnet152()
self.layer1 = nn.Sequential(resnet152.conv1, resnet152.bn1,
resnet152.relu, resnet152.maxpool,
resnet152.layer1)
self.layer2 = nn.Sequential(resnet152.layer2)
self.layer3 = nn.Sequential(resnet152.layer3)
self.layer4 = nn.Sequential(resnet152.layer4)
self.layer5 = nn.Sequential(*[
nn.Conv2d(2048, 512, kernel_size=1),
nn.BatchNorm2d(512),
nn.ReLU(inplace=True),
nn.Conv2d(512, 512, kernel_size=3, padding=1, stride=2),
nn.BatchNorm2d(512),
nn.ReLU(inplace=True)
])
self.layer6 = nn.Sequential(*[
nn.Conv2d(
512,
128,
kernel_size=1,
),
nn.BatchNorm2d(128),
nn.ReLU(inplace=True),
nn.Conv2d(128, 256, kernel_size=3, padding=1, stride=2),
nn.BatchNorm2d(256),
nn.ReLU(inplace=True)
])
######
# dsfd specific layers
######
output_channels = [256, 512, 1024, 2048, 512, 256]
# fpn
fpn_in = output_channels
self.latlayer3 = nn.Conv2d(fpn_in[3],
fpn_in[2],
kernel_size=1,
stride=1,
padding=0)
self.latlayer2 = nn.Conv2d(fpn_in[2],
fpn_in[1],
kernel_size=1,
stride=1,
padding=0)
self.latlayer1 = nn.Conv2d(fpn_in[1],
fpn_in[0],
kernel_size=1,
stride=1,
padding=0)
self.smooth3 = nn.Conv2d(fpn_in[2],
fpn_in[2],
kernel_size=1,
stride=1,
padding=0)
self.smooth2 = nn.Conv2d(fpn_in[1],
fpn_in[1],
kernel_size=1,
stride=1,
padding=0)
self.smooth1 = nn.Conv2d(fpn_in[0],
fpn_in[0],
kernel_size=1,
stride=1,
padding=0)
self.upsample = nn.Upsample(scale_factor=2,
mode='bilinear',
align_corners=False)
self.eltmul = nn.EltMul()
# fem
cpm_in = output_channels
self.cpm3_3 = FEM(cpm_in[0])
self.cpm4_3 = FEM(cpm_in[1])
self.cpm5_3 = FEM(cpm_in[2])
self.cpm7 = FEM(cpm_in[3])
self.cpm6_2 = FEM(cpm_in[4])
self.cpm7_2 = FEM(cpm_in[5])
# pa
cfg_mbox = [1, 1, 1, 1, 1, 1]
head = pa_multibox(output_channels, cfg_mbox, self.num_classes)
# detection head
self.loc = nn.ModuleList(head[0])
self.conf = nn.ModuleList(head[1])
self.softmax = nn.Softmax(dim=-1)
import sys
sys.path.append('.')
from flops_counter import nn
from flops_counter.tensorsize import TensorSize
mlist = nn.ModuleList([nn.Conv2d(3, 64, 3, 1, 1)])
ts = TensorSize([1, 3, 224, 224])
# print(mlist[0](ts))
# print(mlist[0].flops)
# print(mlist.flops)
class NN(nn.Module):
def __init__(self):
super(NN, self).__init__()
self.conv = nn.Conv2d(3, 64, 3, 1, 1)
self.headers = nn.ModuleList(
[nn.Conv2d(64, 4, 3, 1, 1),
nn.Conv2d(64, 2, 3, 1, 1)])
def forward(self, x):
x = self.conv(x)
y1 = self.headers[0](x)
y2 = self.headers[1](x)
# self.headers.settle(x, y1)
return y1, y2
def _make_landmark_head(self, fpn_num=3, inchannels=64, anchor_num=2):
landmarkhead = nn.ModuleList()
for i in range(fpn_num):
landmarkhead.append(LandmarkHead(inchannels, anchor_num))
return landmarkhead
def _make_bbox_head(self, fpn_num=3, inchannels=64, anchor_num=2):
bboxhead = nn.ModuleList()
for i in range(fpn_num):
bboxhead.append(BboxHead(inchannels, anchor_num))
return bboxhead
def _make_class_head(self, fpn_num=3, inchannels=64, anchor_num=2):
classhead = nn.ModuleList()
for i in range(fpn_num):
classhead.append(ClassHead(inchannels, anchor_num))
return classhead
