9种经典图片分类卷积模型系列合集(推荐程度依次递减):
Imagenet的预训练Se_resnet50是1000个类别,根据笔者的经验,预训练的网络结构是不能更改的,改了效果就不行,只能在末尾增加一个(1000,classes)的全连接层,中间还有一层dropout,这样效果是最好的。
注意:最好的网络结构在下面被命名为了fb_se_resnet50,直接调用这个函数即可。
"""
ResNet code gently borrowed from
https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py
"""
from __future__ import print_function, division, absolute_import
from abc import ABC
from collections import OrderedDict
import math
import torch
import torch.nn as nn
from torch.utils import model_zoo
__all__ = ['SENet', 'fb_SENet', 'senet154', 'se_resnet50', 'se_resnet101', 'se_resnet152', 'fb_se_resnet101',
'se_resnext50_32x4d', 'se_resnext101_32x4d', 'fb_se_resnet50', 'fb_se_resnext50_32x4d', 'at_se_resnet50']
pretrained_settings = {
'senet154': {
True: {
'url': 'http://data.lip6.fr/cadene/pretrainedmodels/senet154-c7b49a05.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_resnet50': {
True: {
'url': 'http://data.lip6.fr/cadene/pretrainedmodels/se_resnet50-ce0d4300.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_resnet101': {
True: {
'url': 'http://data.lip6.fr/cadene/pretrainedmodels/se_resnet101-7e38fcc6.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_resnet152': {
True: {
'url': 'http://data.lip6.fr/cadene/pretrainedmodels/se_resnet152-d17c99b7.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_resnext50_32x4d': {
True: {
'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': {
True: {
'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
def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
"""3x3 convolution with padding"""
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=dilation, groups=groups, bias=False, dilation=dilation)
def conv1x1(in_planes, out_planes, stride=1):
"""1x1 convolution"""
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
class ChannelAttention(nn.Module):
def __init__(self, in_planes, ratio=16):
super(ChannelAttention, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.max_pool = nn.AdaptiveMaxPool2d(1)
self.fc1 = nn.Conv2d(in_planes, in_planes // 16, 1, bias=False)
self.relu1 = nn.ReLU()
self.fc2 = nn.Conv2d(in_planes // 16, in_planes, 1, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
x = self.avg_pool(x)
# debug = 1
avg_out = self.fc2(self.relu1(self.fc1(x)))
max_out = self.fc2(self.relu1(self.fc1(self.max_pool(x))))
out = avg_out + max_out
return self.sigmoid(out)
class SpatialAttention(nn.Module):
def __init__(self, kernel_size=7):
super(SpatialAttention, self).__init__()
assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
padding = 3 if kernel_size == 7 else 1
self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
avg_out = torch.mean(x, dim=1, keepdim=True)
max_out, _ = torch.max(x, dim=1, keepdim=True)
x = torch.cat([avg_out, max_out], dim=1)
x = self.conv1(x)
return self.sigmoid(x)
class BasicBlock(nn.Module):
expansion = 1
__constants__ = ['downsample']
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
base_width=64, dilation=1, norm_layer=None):
super(BasicBlock, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
if groups != 1 or base_width != 64:
raise ValueError('BasicBlock only supports groups=1 and base_width=64')
if dilation > 1:
raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
# Both self.conv1 and self.downsample layers downsample the input when stride != 1
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = norm_layer(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = norm_layer(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
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 Def_Bottleneck(nn.Module):
expansion = 4
__constants__ = ['downsample']
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
base_width=64, dilation=1, norm_layer=None):
super(Bottleneck, self).__init__()
if norm_layer is None:
norm_layer = nn.BatchNorm2d
width = int(planes * (base_width / 64.)) * groups
self.conv1 = conv1x1(inplanes, width)
self.bn1 = norm_layer(width)
self.conv2 = conv3x3(width, width, stride, groups, dilation)
self.bn2 = norm_layer(width)
self.conv3 = conv1x1(width, planes * self.expansion)
self.bn3 = norm_layer(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = 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:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class SEBottleneck(Bottleneck):
"""
Bottleneck for SENet154.
"""
expansion = 4
def __init__(self, inplanes, planes, groups, reduction, stride=1,
downsample=None):
super(SEBottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes * 2, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes * 2)
self.conv2 = nn.Conv2d(planes * 2, planes * 4, kernel_size=3,
stride=stride, padding=1, groups=groups,
bias=False)
self.bn2 = nn.BatchNorm2d(planes * 4)
self.conv3 = nn.Conv2d(planes * 4, 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 SEResNetBottleneck(Bottleneck):
"""
ResNet bottleneck with a Squeeze-and-Excitation module. It follows Caffe
implementation and uses `stride=stride` in `conv1` and not in `conv2`
(the latter is used in the torchvision implementation of ResNet).
"""
expansion = 4
def __init__(self, inplanes, planes, groups, reduction, stride=1,
downsample=None):
super(SEResNetBottleneck, self).__init__()
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False,
stride=stride)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, padding=1,
groups=groups, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, 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 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 SENet(nn.Module):
def __init__(self, block, layers, groups, reduction, dropout_p=0.5,
inplanes=128, input_3x3=True, downsample_kernel_size=3,
downsample_padding=1, num_classes=1000, zero_init_residual=False):
"""
Parameters
----------
block (nn.Module): Bottleneck class.
- For SENet154: SEBottleneck
- For SE-ResNet models: SEResNetBottleneck
- 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 SENet154: 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 SENet154: 0.2
- For SE-ResNet models: None
- For SE-ResNeXt models: None
inplanes (int): Number of input channels for layer1.
- For SENet154: 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 SENet154: 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 SENet154: 3
- For SE-ResNet models: 1
- For SE-ResNeXt models: 1
downsample_padding (int): Padding for downsampling convolutions in
layer2, layer3 and layer4.
- For SENet154: 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(SENet, 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
)
self.avg_pool = nn.AvgPool2d(7, stride=1)
self.dropout = nn.Dropout(dropout_p) if dropout_p is not None else None
self.last_linear = nn.Linear(512 * block.expansion, 1000)
self.bottleneck = nn.Sequential(
nn.Linear(1000, 1000),
nn.BatchNorm1d(1000),
nn.ReLU(),
nn.Dropout(0.5)
)
self.bottleneck[0].weight.data.normal_(0, 0.005)
self.bottleneck[0].bias.data.fill_(0.1)
self.head = nn.Sequential(
nn.Linear(1000, 4),
# nn.ReLU(),
# nn.Dropout(0.5),
# nn.Linear(512, 4)
)
# self.fc = nn.Linear(512, num_classes)
for dep in range(1):
self.head[dep * 1].weight.data.normal_(0, 0.01)
self.head[dep * 1].bias.data.fill_(0.0)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
if zero_init_residual:
for m in self.modules():
if isinstance(m, Def_Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)
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 features(self, x):
x = self.layer0(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
return x
def logits(self, x):
x = self.avg_pool(x)
if self.dropout is not None:
x = self.dropout(x)
x = x.view(x.size(0), -1)
x = self.last_linear(x)
x = self.bottleneck(x)
x = self.head(x)
return x
def forward(self, x):
x = self.features(x)
x = self.logits(x)
return x
class fb_SENet(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, num_classes=1000):
super(fb_SENet, 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
)
self.avg_pool = nn.AvgPool2d(7, stride=1)
self.dropout = nn.Dropout(dropout_p) if dropout_p is not None else None
self.last_linear = nn.Linear(512 * block.expansion, 1000)
self.last_linear2 = nn.Linear(1000, 4)
self.last_linear2.weight.data.normal_(0, 0.01)
self.last_linear2.bias.data.fill_(0.0)
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 features(self, x):
x = self.layer0(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
return x
def logits(self, x):
x = self.avg_pool(x)
x = self.dropout(x)
x = x.view(x.size(0), -1)
x = self.last_linear(x)
# feature = x
# x = self.relu(x)
x = self.dropout(x)
x = self.last_linear2(x)
# x = self.dropout(x)
# x = self.last_linear3(x)
return x
def forward(self, x):
x = self.features(x)
x = self.logits(x)
return x
class Attention_SENet(nn.Module):
def __init__(self, block, layers, groups, reduction, dropout_p=0.2,
inplanes=128, inplanes2=64, input_3x3=True, downsample_kernel_size=3,
downsample_padding=1, num_classes=1000, norm_layer=None, ):
super(Attention_SENet, self).__init__()
self.inplanes = inplanes
self.inplanes2 = inplanes2
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
)
if norm_layer is None:
norm_layer = nn.BatchNorm2d
self._norm_layer = norm_layer
self.conv1 = nn.Conv2d(3, self.inplanes2, kernel_size=7, stride=2, padding=3,
bias=False)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.bn1 = norm_layer(self.inplanes2)
self.relu = nn.ReLU(inplace=True)
# 网络的第一层加入注意力机制
self.ca = ChannelAttention(self.inplanes2)
self.sa = SpatialAttention()
# 网络的卷积层的最后一层加入注意力机制
self.ca1 = ChannelAttention(2048)
self.sa1 = SpatialAttention()
self.avg_pool = nn.AvgPool2d(7, stride=1)
self.dropout = nn.Dropout(dropout_p) if dropout_p is not None else None
self.last_linear = nn.Linear(512 * block.expansion, 1000)
self.relu = nn.ReLU()
self.last_linear2 = nn.Linear(1000, 4)
self.last_linear2.weight.data.normal_(0, 0.01)
self.last_linear2.bias.data.fill_(0.0)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
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 features(self, x):
x = self.layer0(x)
x = self.ca(x) * x
# x = self.sa1(x) * x
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
return x
def logits(self, x):
x = self.ca1(x) * x
# x = self.sa1(x) * x
x = self.avg_pool(x)
x = self.dropout(x)
x = x.view(x.size(0), -1)
x = self.last_linear(x)
x = self.dropout(x)
x = self.last_linear2(x)
return x
def forward(self, x):
x = self.features(x)
x = self.logits(x)
return x
def initialize_pretrained_model(model, num_classes, settings):
# assert num_classes == settings['num_classes'], \
# 'num_classes should be {}, but is {}'.format(
# settings['num_classes'], num_classes)
model.load_state_dict(model_zoo.load_url(settings['url']), strict=False)
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 senet154(num_classes=1000, pretrained='imagenet'):
model = SENet(SEBottleneck, [3, 8, 36, 3], groups=64, reduction=16,
dropout_p=0.2, num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['senet154'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def se_resnet50(num_classes=1000, pretrained='imagenet'):
model = SENet(SEResNetBottleneck, [3, 4, 6, 3], groups=1, reduction=16,
dropout_p=None, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['se_resnet50'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def fb_se_resnet50(num_classes=1000, pretrained='imagenet'):
model = fb_SENet(SEResNetBottleneck, [3, 4, 6, 3], groups=1, reduction=16,
dropout_p=0.5, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['se_resnet50'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def at_se_resnet50(num_classes=1000, pretrained='imagenet'):
model = Attention_SENet(SEResNetBottleneck, [3, 4, 6, 3], groups=1, reduction=16,
dropout_p=0.5, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes, norm_layer=None)
if pretrained is not None:
settings = pretrained_settings['se_resnet50'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def se_resnet101(num_classes=1000, pretrained='imagenet'):
model = SENet(SEResNetBottleneck, [3, 4, 23, 3], groups=1, reduction=16,
dropout_p=None, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['se_resnet101'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def fb_se_resnet101(num_classes=1000, pretrained='imagenet'):
model = fb_SENet(SEResNetBottleneck, [3, 4, 23, 3], groups=1, reduction=16,
dropout_p=0.5, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['se_resnet101'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def se_resnet152(num_classes=1000, pretrained='imagenet'):
model = SENet(SEResNetBottleneck, [3, 8, 36, 3], groups=1, reduction=16,
dropout_p=None, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['se_resnet152'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def fb_se_resnext50_32x4d(num_classes=1000, pretrained='imagenet'):
model = fb_SENet(SEResNeXtBottleneck, [3, 4, 6, 3], groups=32, reduction=16,
dropout_p=0.5, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['se_resnext50_32x4d'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def se_resnext50_32x4d(num_classes=1000, pretrained='imagenet'):
model = SENet(SEResNeXtBottleneck, [3, 4, 6, 3], groups=32, reduction=16,
dropout_p=None, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['se_resnext50_32x4d'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model
def se_resnext101_32x4d(num_classes=1000, pretrained='imagenet'):
model = SENet(SEResNeXtBottleneck, [3, 4, 23, 3], groups=32, reduction=16,
dropout_p=None, inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
num_classes=num_classes)
if pretrained is not None:
settings = pretrained_settings['se_resnext101_32x4d'][pretrained]
initialize_pretrained_model(model, num_classes, settings)
return model