权重下载网址:https://data.lip6.fr/cadene/pretrainedmodels/
"""
ResNet code gently borrowed from
https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py
"""
import os
from collections import OrderedDict
import math
import torch.nn as nn
import torch
pretrained_settings = {
'se_resnext50_32x4d': {
'imagenet': {
'url': 'http://data.lip6.fr/cadene/pretrainedmodels/se_resnext50_32x4d-a260b3a4.pth',
'input_space': 'RGB',
'input_size': [3, 224, 224],
'input_range': [0, 1],
'mean': [0.485, 0.456, 0.406],
'std': [0.229, 0.224, 0.225],
'num_classes': 1000
}
},
'se_resnext101_32x4d': {
'imagenet': {
'url': 'http://data.lip6.fr/cadene/pretrainedmodels/se_resnext101_32x4d-3b2fe3d8.pth',
'input_space': 'RGB',
'input_size': [3, 224, 224],
'input_range': [0, 1],
'mean': [0.485, 0.456, 0.406],
'std': [0.229, 0.224, 0.225],
'num_classes': 1000
}
},
}
class SEModule(nn.Module):
def __init__(self, channels, reduction):
super(SEModule, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.fc1 = nn.Conv2d(channels, channels // reduction, kernel_size=1,
padding=0)
self.relu = nn.ReLU(inplace=True)
self.fc2 = nn.Conv2d(channels // reduction, channels, kernel_size=1,
padding=0)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
module_input = x
x = self.avg_pool(x)
x = self.fc1(x)
x = self.relu(x)
x = self.fc2(x)
x = self.sigmoid(x)
return module_input * x
class Bottleneck(nn.Module):
"""
Base class for bottlenecks that implements `forward()` method.
"""
def forward(self, x):
residual = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
residual = self.downsample(x)
out = self.se_module(out) + residual
out = self.relu(out)
return out
class SEResNeXtBottleneck(Bottleneck):
"""
ResNeXt bottleneck type C with a Squeeze-and-Excitation module.
"""
expansion = 4
def __init__(self, inplanes, planes, groups, reduction, stride=1,
downsample=None, base_width=4):
super(SEResNeXtBottleneck, self).__init__()
width = math.floor(planes * (base_width / 64)) * groups
self.conv1 = nn.Conv2d(inplanes, width, kernel_size=1, bias=False,
stride=1)
self.bn1 = nn.BatchNorm2d(width)
self.conv2 = nn.Conv2d(width, width, kernel_size=3, stride=stride,
padding=1, groups=groups, bias=False)
self.bn2 = nn.BatchNorm2d(width)
self.conv3 = nn.Conv2d(width, planes * 4, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(planes * 4)
self.relu = nn.ReLU(inplace=True)
self.se_module = SEModule(planes * 4, reduction=reduction)
self.downsample = downsample
self.stride = stride
class BackBone(nn.Module):
def __init__(self, block, layers, groups, reduction, dropout_p=0.2,
inplanes=128, input_3x3=True, downsample_kernel_size=3,
downsample_padding=1):
"""
Parameters
----------
block (nn.Module): Bottleneck class.
- For SE-ResNeXt models: SEResNeXtBottleneck
layers (list of ints): Number of residual blocks for 4 layers of the
network (layer1...layer4).
groups (int): Number of groups for the 3x3 convolution in each
bottleneck block.
- For BackBone154: 64
- For SE-ResNet models: 1
- For SE-ResNeXt models: 32
reduction (int): Reduction ratio for Squeeze-and-Excitation modules.
- For all models: 16
dropout_p (float or None): Drop probability for the Dropout layer.
If `None` the Dropout layer is not used.
- For BackBone154: 0.2
- For SE-ResNet models: None
- For SE-ResNeXt models: None
inplanes (int): Number of input channels for layer1.
- For BackBone154: 128
- For SE-ResNet models: 64
- For SE-ResNeXt models: 64
input_3x3 (bool): If `True`, use three 3x3 convolutions instead of
a single 7x7 convolution in layer0.
- For BackBone154: True
- For SE-ResNet models: False
- For SE-ResNeXt models: False
downsample_kernel_size (int): Kernel size for downsampling convolutions
in layer2, layer3 and layer4.
- For BackBone154: 3
- For SE-ResNet models: 1
- For SE-ResNeXt models: 1
downsample_padding (int): Padding for downsampling convolutions in
layer2, layer3 and layer4.
- For BackBone154: 1
- For SE-ResNet models: 0
- For SE-ResNeXt models: 0
num_classes (int): Number of outputs in `last_linear` layer.
- For all models: 1000
"""
super(BackBone, self).__init__()
self.inplanes = inplanes
if input_3x3:
layer0_modules = [
('conv1', nn.Conv2d(3, 64, 3, stride=2, padding=1,
bias=False)),
('bn1', nn.BatchNorm2d(64)),
('relu1', nn.ReLU(inplace=True)),
('conv2', nn.Conv2d(64, 64, 3, stride=1, padding=1,
bias=False)),
('bn2', nn.BatchNorm2d(64)),
('relu2', nn.ReLU(inplace=True)),
('conv3', nn.Conv2d(64, inplanes, 3, stride=1, padding=1,
bias=False)),
('bn3', nn.BatchNorm2d(inplanes)),
('relu3', nn.ReLU(inplace=True)),
]
else:
layer0_modules = [
('conv1', nn.Conv2d(3, inplanes, kernel_size=7, stride=2,
padding=3, bias=False)),
('bn1', nn.BatchNorm2d(inplanes)),
('relu1', nn.ReLU(inplace=True)),
]
# To preserve compatibility with Caffe weights `ceil_mode=True`
# is used instead of `padding=1`.
layer0_modules.append(('pool', nn.MaxPool2d(3, stride=2,
ceil_mode=True)))
self.layer0 = nn.Sequential(OrderedDict(layer0_modules))
self.layer1 = self._make_layer(
block,
planes=64,
blocks=layers[0],
groups=groups,
reduction=reduction,
downsample_kernel_size=1,
downsample_padding=0
)
self.layer2 = self._make_layer(
block,
planes=128,
blocks=layers[1],
stride=2,
groups=groups,
reduction=reduction,
downsample_kernel_size=downsample_kernel_size,
downsample_padding=downsample_padding
)
self.layer3 = self._make_layer(
block,
planes=256,
blocks=layers[2],
stride=2,
groups=groups,
reduction=reduction,
downsample_kernel_size=downsample_kernel_size,
downsample_padding=downsample_padding
)
self.layer4 = self._make_layer(
block,
planes=512,
blocks=layers[3],
stride=2,
groups=groups,
reduction=reduction,
downsample_kernel_size=downsample_kernel_size,
downsample_padding=downsample_padding
)
def _make_layer(self, block, planes, blocks, groups, reduction, stride=1,
downsample_kernel_size=1, downsample_padding=0):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(self.inplanes, planes * block.expansion,
kernel_size=downsample_kernel_size, stride=stride,
padding=downsample_padding, bias=False),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, groups, reduction, stride,
downsample))
self.inplanes = planes * block.expansion
for i in range(1, blocks):
layers.append(block(self.inplanes, planes, groups, reduction))
return nn.Sequential(*layers)
def forward(self, x):
x = self.layer0(x)
C2 = self.layer1(x)
C3 = self.layer2(C2)
C4 = self.layer3(C3)
C5 = self.layer4(C4)
return [C3, C4, C5]
def initialize_pretrained_model(model, settings):
weights_path = os.path.join(os.path.join(os.path.dirname(__file__), '..',
'pretrainedmodels', os.path.basename(settings['url'])))
state_dict = torch.load(weights_path)
# filter out last layer
for layer in ['last_linear.weight', 'last_linear.bias']:
del state_dict[layer]
state_dict_cur = model.state_dict()
state_dict_cur.update(state_dict_cur)
model.load_state_dict(state_dict_cur)
model.input_space = settings['input_space']
model.input_size = settings['input_size']
model.input_range = settings['input_range']
model.mean = settings['mean']
model.std = settings['std']
def se_resnext50_32x4d(pretrained_imagenet):
model = BackBone(SEResNeXtBottleneck, [3, 4, 6, 3], groups=32, reduction=16,
dropout_p=None, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
)
if pretrained_imagenet:
settings = pretrained_settings['se_resnext50_32x4d']['imagenet']
initialize_pretrained_model(model, settings)
return model
def se_resnext101_32x4d(pretrained_imagenet):
model = BackBone(SEResNeXtBottleneck, [3, 4, 23, 3], groups=32, reduction=16,
dropout_p=None, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
)
if pretrained_imagenet:
settings = pretrained_settings['se_resnext101_32x4d']['imagenet']
initialize_pretrained_model(model, settings)
return model