362 lines
11 KiB
Python
362 lines
11 KiB
Python
"""
|
|
Code imported from https://github.com/Cadene/pretrained-models.pytorch
|
|
"""
|
|
from __future__ import division, absolute_import
|
|
import torch
|
|
import torch.nn as nn
|
|
import torch.utils.model_zoo as model_zoo
|
|
|
|
__all__ = ['inceptionresnetv2']
|
|
|
|
pretrained_settings = {
|
|
'inceptionresnetv2': {
|
|
'imagenet': {
|
|
'url':
|
|
'http://data.lip6.fr/cadene/pretrainedmodels/inceptionresnetv2-520b38e4.pth',
|
|
'input_space': 'RGB',
|
|
'input_size': [3, 299, 299],
|
|
'input_range': [0, 1],
|
|
'mean': [0.5, 0.5, 0.5],
|
|
'std': [0.5, 0.5, 0.5],
|
|
'num_classes': 1000
|
|
},
|
|
'imagenet+background': {
|
|
'url':
|
|
'http://data.lip6.fr/cadene/pretrainedmodels/inceptionresnetv2-520b38e4.pth',
|
|
'input_space': 'RGB',
|
|
'input_size': [3, 299, 299],
|
|
'input_range': [0, 1],
|
|
'mean': [0.5, 0.5, 0.5],
|
|
'std': [0.5, 0.5, 0.5],
|
|
'num_classes': 1001
|
|
}
|
|
}
|
|
}
|
|
|
|
|
|
class BasicConv2d(nn.Module):
|
|
|
|
def __init__(self, in_planes, out_planes, kernel_size, stride, padding=0):
|
|
super(BasicConv2d, self).__init__()
|
|
self.conv = nn.Conv2d(
|
|
in_planes,
|
|
out_planes,
|
|
kernel_size=kernel_size,
|
|
stride=stride,
|
|
padding=padding,
|
|
bias=False
|
|
) # verify bias false
|
|
self.bn = nn.BatchNorm2d(
|
|
out_planes,
|
|
eps=0.001, # value found in tensorflow
|
|
momentum=0.1, # default pytorch value
|
|
affine=True
|
|
)
|
|
self.relu = nn.ReLU(inplace=False)
|
|
|
|
def forward(self, x):
|
|
x = self.conv(x)
|
|
x = self.bn(x)
|
|
x = self.relu(x)
|
|
return x
|
|
|
|
|
|
class Mixed_5b(nn.Module):
|
|
|
|
def __init__(self):
|
|
super(Mixed_5b, self).__init__()
|
|
|
|
self.branch0 = BasicConv2d(192, 96, kernel_size=1, stride=1)
|
|
|
|
self.branch1 = nn.Sequential(
|
|
BasicConv2d(192, 48, kernel_size=1, stride=1),
|
|
BasicConv2d(48, 64, kernel_size=5, stride=1, padding=2)
|
|
)
|
|
|
|
self.branch2 = nn.Sequential(
|
|
BasicConv2d(192, 64, kernel_size=1, stride=1),
|
|
BasicConv2d(64, 96, kernel_size=3, stride=1, padding=1),
|
|
BasicConv2d(96, 96, kernel_size=3, stride=1, padding=1)
|
|
)
|
|
|
|
self.branch3 = nn.Sequential(
|
|
nn.AvgPool2d(3, stride=1, padding=1, count_include_pad=False),
|
|
BasicConv2d(192, 64, kernel_size=1, stride=1)
|
|
)
|
|
|
|
def forward(self, x):
|
|
x0 = self.branch0(x)
|
|
x1 = self.branch1(x)
|
|
x2 = self.branch2(x)
|
|
x3 = self.branch3(x)
|
|
out = torch.cat((x0, x1, x2, x3), 1)
|
|
return out
|
|
|
|
|
|
class Block35(nn.Module):
|
|
|
|
def __init__(self, scale=1.0):
|
|
super(Block35, self).__init__()
|
|
|
|
self.scale = scale
|
|
|
|
self.branch0 = BasicConv2d(320, 32, kernel_size=1, stride=1)
|
|
|
|
self.branch1 = nn.Sequential(
|
|
BasicConv2d(320, 32, kernel_size=1, stride=1),
|
|
BasicConv2d(32, 32, kernel_size=3, stride=1, padding=1)
|
|
)
|
|
|
|
self.branch2 = nn.Sequential(
|
|
BasicConv2d(320, 32, kernel_size=1, stride=1),
|
|
BasicConv2d(32, 48, kernel_size=3, stride=1, padding=1),
|
|
BasicConv2d(48, 64, kernel_size=3, stride=1, padding=1)
|
|
)
|
|
|
|
self.conv2d = nn.Conv2d(128, 320, kernel_size=1, stride=1)
|
|
self.relu = nn.ReLU(inplace=False)
|
|
|
|
def forward(self, x):
|
|
x0 = self.branch0(x)
|
|
x1 = self.branch1(x)
|
|
x2 = self.branch2(x)
|
|
out = torch.cat((x0, x1, x2), 1)
|
|
out = self.conv2d(out)
|
|
out = out * self.scale + x
|
|
out = self.relu(out)
|
|
return out
|
|
|
|
|
|
class Mixed_6a(nn.Module):
|
|
|
|
def __init__(self):
|
|
super(Mixed_6a, self).__init__()
|
|
|
|
self.branch0 = BasicConv2d(320, 384, kernel_size=3, stride=2)
|
|
|
|
self.branch1 = nn.Sequential(
|
|
BasicConv2d(320, 256, kernel_size=1, stride=1),
|
|
BasicConv2d(256, 256, kernel_size=3, stride=1, padding=1),
|
|
BasicConv2d(256, 384, kernel_size=3, stride=2)
|
|
)
|
|
|
|
self.branch2 = nn.MaxPool2d(3, stride=2)
|
|
|
|
def forward(self, x):
|
|
x0 = self.branch0(x)
|
|
x1 = self.branch1(x)
|
|
x2 = self.branch2(x)
|
|
out = torch.cat((x0, x1, x2), 1)
|
|
return out
|
|
|
|
|
|
class Block17(nn.Module):
|
|
|
|
def __init__(self, scale=1.0):
|
|
super(Block17, self).__init__()
|
|
|
|
self.scale = scale
|
|
|
|
self.branch0 = BasicConv2d(1088, 192, kernel_size=1, stride=1)
|
|
|
|
self.branch1 = nn.Sequential(
|
|
BasicConv2d(1088, 128, kernel_size=1, stride=1),
|
|
BasicConv2d(
|
|
128, 160, kernel_size=(1, 7), stride=1, padding=(0, 3)
|
|
),
|
|
BasicConv2d(
|
|
160, 192, kernel_size=(7, 1), stride=1, padding=(3, 0)
|
|
)
|
|
)
|
|
|
|
self.conv2d = nn.Conv2d(384, 1088, kernel_size=1, stride=1)
|
|
self.relu = nn.ReLU(inplace=False)
|
|
|
|
def forward(self, x):
|
|
x0 = self.branch0(x)
|
|
x1 = self.branch1(x)
|
|
out = torch.cat((x0, x1), 1)
|
|
out = self.conv2d(out)
|
|
out = out * self.scale + x
|
|
out = self.relu(out)
|
|
return out
|
|
|
|
|
|
class Mixed_7a(nn.Module):
|
|
|
|
def __init__(self):
|
|
super(Mixed_7a, self).__init__()
|
|
|
|
self.branch0 = nn.Sequential(
|
|
BasicConv2d(1088, 256, kernel_size=1, stride=1),
|
|
BasicConv2d(256, 384, kernel_size=3, stride=2)
|
|
)
|
|
|
|
self.branch1 = nn.Sequential(
|
|
BasicConv2d(1088, 256, kernel_size=1, stride=1),
|
|
BasicConv2d(256, 288, kernel_size=3, stride=2)
|
|
)
|
|
|
|
self.branch2 = nn.Sequential(
|
|
BasicConv2d(1088, 256, kernel_size=1, stride=1),
|
|
BasicConv2d(256, 288, kernel_size=3, stride=1, padding=1),
|
|
BasicConv2d(288, 320, kernel_size=3, stride=2)
|
|
)
|
|
|
|
self.branch3 = nn.MaxPool2d(3, stride=2)
|
|
|
|
def forward(self, x):
|
|
x0 = self.branch0(x)
|
|
x1 = self.branch1(x)
|
|
x2 = self.branch2(x)
|
|
x3 = self.branch3(x)
|
|
out = torch.cat((x0, x1, x2, x3), 1)
|
|
return out
|
|
|
|
|
|
class Block8(nn.Module):
|
|
|
|
def __init__(self, scale=1.0, noReLU=False):
|
|
super(Block8, self).__init__()
|
|
|
|
self.scale = scale
|
|
self.noReLU = noReLU
|
|
|
|
self.branch0 = BasicConv2d(2080, 192, kernel_size=1, stride=1)
|
|
|
|
self.branch1 = nn.Sequential(
|
|
BasicConv2d(2080, 192, kernel_size=1, stride=1),
|
|
BasicConv2d(
|
|
192, 224, kernel_size=(1, 3), stride=1, padding=(0, 1)
|
|
),
|
|
BasicConv2d(
|
|
224, 256, kernel_size=(3, 1), stride=1, padding=(1, 0)
|
|
)
|
|
)
|
|
|
|
self.conv2d = nn.Conv2d(448, 2080, kernel_size=1, stride=1)
|
|
if not self.noReLU:
|
|
self.relu = nn.ReLU(inplace=False)
|
|
|
|
def forward(self, x):
|
|
x0 = self.branch0(x)
|
|
x1 = self.branch1(x)
|
|
out = torch.cat((x0, x1), 1)
|
|
out = self.conv2d(out)
|
|
out = out * self.scale + x
|
|
if not self.noReLU:
|
|
out = self.relu(out)
|
|
return out
|
|
|
|
|
|
# ----------------
|
|
# Model Definition
|
|
# ----------------
|
|
class InceptionResNetV2(nn.Module):
|
|
"""Inception-ResNet-V2.
|
|
|
|
Reference:
|
|
Szegedy et al. Inception-v4, Inception-ResNet and the Impact of Residual
|
|
Connections on Learning. AAAI 2017.
|
|
|
|
Public keys:
|
|
- ``inceptionresnetv2``: Inception-ResNet-V2.
|
|
"""
|
|
|
|
def __init__(self, num_classes, loss='softmax', **kwargs):
|
|
super(InceptionResNetV2, self).__init__()
|
|
self.loss = loss
|
|
|
|
# Modules
|
|
self.conv2d_1a = BasicConv2d(3, 32, kernel_size=3, stride=2)
|
|
self.conv2d_2a = BasicConv2d(32, 32, kernel_size=3, stride=1)
|
|
self.conv2d_2b = BasicConv2d(
|
|
32, 64, kernel_size=3, stride=1, padding=1
|
|
)
|
|
self.maxpool_3a = nn.MaxPool2d(3, stride=2)
|
|
self.conv2d_3b = BasicConv2d(64, 80, kernel_size=1, stride=1)
|
|
self.conv2d_4a = BasicConv2d(80, 192, kernel_size=3, stride=1)
|
|
self.maxpool_5a = nn.MaxPool2d(3, stride=2)
|
|
self.mixed_5b = Mixed_5b()
|
|
self.repeat = nn.Sequential(
|
|
Block35(scale=0.17), Block35(scale=0.17), Block35(scale=0.17),
|
|
Block35(scale=0.17), Block35(scale=0.17), Block35(scale=0.17),
|
|
Block35(scale=0.17), Block35(scale=0.17), Block35(scale=0.17),
|
|
Block35(scale=0.17)
|
|
)
|
|
self.mixed_6a = Mixed_6a()
|
|
self.repeat_1 = nn.Sequential(
|
|
Block17(scale=0.10), Block17(scale=0.10), Block17(scale=0.10),
|
|
Block17(scale=0.10), Block17(scale=0.10), Block17(scale=0.10),
|
|
Block17(scale=0.10), Block17(scale=0.10), Block17(scale=0.10),
|
|
Block17(scale=0.10), Block17(scale=0.10), Block17(scale=0.10),
|
|
Block17(scale=0.10), Block17(scale=0.10), Block17(scale=0.10),
|
|
Block17(scale=0.10), Block17(scale=0.10), Block17(scale=0.10),
|
|
Block17(scale=0.10), Block17(scale=0.10)
|
|
)
|
|
self.mixed_7a = Mixed_7a()
|
|
self.repeat_2 = nn.Sequential(
|
|
Block8(scale=0.20), Block8(scale=0.20), Block8(scale=0.20),
|
|
Block8(scale=0.20), Block8(scale=0.20), Block8(scale=0.20),
|
|
Block8(scale=0.20), Block8(scale=0.20), Block8(scale=0.20)
|
|
)
|
|
|
|
self.block8 = Block8(noReLU=True)
|
|
self.conv2d_7b = BasicConv2d(2080, 1536, kernel_size=1, stride=1)
|
|
self.global_avgpool = nn.AdaptiveAvgPool2d(1)
|
|
self.classifier = nn.Linear(1536, num_classes)
|
|
|
|
def load_imagenet_weights(self):
|
|
settings = pretrained_settings['inceptionresnetv2']['imagenet']
|
|
pretrain_dict = model_zoo.load_url(settings['url'])
|
|
model_dict = self.state_dict()
|
|
pretrain_dict = {
|
|
k: v
|
|
for k, v in pretrain_dict.items()
|
|
if k in model_dict and model_dict[k].size() == v.size()
|
|
}
|
|
model_dict.update(pretrain_dict)
|
|
self.load_state_dict(model_dict)
|
|
|
|
def featuremaps(self, x):
|
|
x = self.conv2d_1a(x)
|
|
x = self.conv2d_2a(x)
|
|
x = self.conv2d_2b(x)
|
|
x = self.maxpool_3a(x)
|
|
x = self.conv2d_3b(x)
|
|
x = self.conv2d_4a(x)
|
|
x = self.maxpool_5a(x)
|
|
x = self.mixed_5b(x)
|
|
x = self.repeat(x)
|
|
x = self.mixed_6a(x)
|
|
x = self.repeat_1(x)
|
|
x = self.mixed_7a(x)
|
|
x = self.repeat_2(x)
|
|
x = self.block8(x)
|
|
x = self.conv2d_7b(x)
|
|
return x
|
|
|
|
def forward(self, x):
|
|
f = self.featuremaps(x)
|
|
v = self.global_avgpool(f)
|
|
v = v.view(v.size(0), -1)
|
|
|
|
if not self.training:
|
|
return v
|
|
|
|
y = self.classifier(v)
|
|
|
|
if self.loss == 'softmax':
|
|
return y
|
|
elif self.loss == 'triplet':
|
|
return y, v
|
|
else:
|
|
raise KeyError('Unsupported loss: {}'.format(self.loss))
|
|
|
|
|
|
def inceptionresnetv2(num_classes, loss='softmax', pretrained=True, **kwargs):
|
|
model = InceptionResNetV2(num_classes=num_classes, loss=loss, **kwargs)
|
|
if pretrained:
|
|
model.load_imagenet_weights()
|
|
return model
|