def __init__(self, inc=128, outc=128):
super(gated_conv1x1, self).__init__()
self.inp = int(inc / 2)
self.oup = int(outc / 2)
self.conv1x1_1 = nn.Conv2d(self.inp, self.oup, 1, 1, 0, bias=False)
self.gate_1 = nn.Conv2d(self.inp, self.oup, 1, 1, 0, bias=True)
self.sigmoid1 = nn.Sigmoid()
self.eltmul1 = nn.EltMul()
self.conv1x1_2 = nn.Conv2d(self.inp, self.oup, 1, 1, 0, bias=False)
self.gate_2 = nn.Conv2d(self.inp, self.oup, 1, 1, 0, bias=True)
self.sigmoid2 = nn.Sigmoid()
self.eltmul2 = nn.EltMul()
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, up_from_channels, up_to_channels):
super(LFPN, self).__init__()
self.conv1 = nn.Conv2d(up_from_channels, up_to_channels, kernel_size=1)
self.conv1_relu = nn.ReLU(inplace=True)
self.upsampling = nn.ConvTranspose2d(up_to_channels,
up_to_channels,
kernel_size=4,
stride=2,
padding=1,
groups=up_to_channels,
bias=False)
self.conv2 = nn.Conv2d(up_to_channels, up_to_channels, kernel_size=1)
self.conv2_relu = nn.ReLU(inplace=True)
self.eltmul = nn.EltMul()
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)
TensorSize([64, 112, 112])
],
'out_shape': [
TensorSize([64, 112, 112])
],
'out_flops': [
802816
]
}
test_on(eltadd)
######
# test on EltMul
######
eltmul = {
'layers': [
nn.EltMul() # same shape
],
'ins': [
TensorSize([1, 64, 112, 112])
],
'out_shape': [
TensorSize([1, 64, 112, 112])
],
'out_flops': [
802816
]
}
test_on(eltmul)