You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
306 lines
10 KiB
306 lines
10 KiB
"""Pytorch ResNet implementation tweaks
|
|
This file is a copy of https://github.com/pytorch/vision 'resnet.py' (BSD-3-Clause) with
|
|
additional dropout and dynamic global avg/max pool.
|
|
"""
|
|
import torch
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
import math
|
|
import torch.utils.model_zoo as model_zoo
|
|
from .adaptive_avgmax_pool import SelectAdaptivePool2d
|
|
|
|
__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152']
|
|
|
|
model_urls = {
|
|
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
|
|
'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
|
|
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
|
|
'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
|
|
'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
|
|
}
|
|
|
|
|
|
def conv3x3(in_planes, out_planes, stride=1):
|
|
"""3x3 convolution with padding"""
|
|
return nn.Conv2d(
|
|
in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False)
|
|
|
|
|
|
class BasicBlock(nn.Module):
|
|
expansion = 1
|
|
|
|
def __init__(self, inplanes, planes, stride=1, downsample=None,
|
|
cardinality=1, base_width=64, drop_rate=0.0):
|
|
super(BasicBlock, self).__init__()
|
|
|
|
assert cardinality == 1, 'BasicBlock only supports cardinality of 1'
|
|
assert base_width == 64, 'BasicBlock doest not support changing base width'
|
|
|
|
self.conv1 = conv3x3(inplanes, planes, stride)
|
|
self.bn1 = nn.BatchNorm2d(planes)
|
|
self.relu = nn.ReLU(inplace=True)
|
|
self.conv2 = conv3x3(planes, planes)
|
|
self.bn2 = nn.BatchNorm2d(planes)
|
|
self.downsample = downsample
|
|
self.stride = stride
|
|
self.drop_rate = drop_rate
|
|
|
|
def forward(self, x):
|
|
residual = x
|
|
|
|
out = self.conv1(x)
|
|
out = self.bn1(out)
|
|
out = self.relu(out)
|
|
|
|
if self.drop_rate > 0.:
|
|
out = F.dropout(out, p=self.drop_rate, training=self.training)
|
|
|
|
out = self.conv2(out)
|
|
out = self.bn2(out)
|
|
|
|
if self.downsample is not None:
|
|
residual = self.downsample(x)
|
|
|
|
out += residual
|
|
out = self.relu(out)
|
|
|
|
return out
|
|
|
|
|
|
class Bottleneck(nn.Module):
|
|
expansion = 4
|
|
|
|
def __init__(self, inplanes, planes, stride=1, downsample=None,
|
|
cardinality=1, base_width=64, drop_rate=0.0):
|
|
super(Bottleneck, self).__init__()
|
|
|
|
width = int(math.floor(planes * (base_width / 64)) * cardinality)
|
|
|
|
self.conv1 = nn.Conv2d(inplanes, width, kernel_size=1, bias=False)
|
|
self.bn1 = nn.BatchNorm2d(width)
|
|
self.conv2 = nn.Conv2d(width, width, kernel_size=3, stride=stride,
|
|
padding=1, groups=cardinality, 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.downsample = downsample
|
|
self.stride = stride
|
|
self.drop_rate = drop_rate
|
|
|
|
def forward(self, x):
|
|
residual = x
|
|
|
|
out = self.conv1(x)
|
|
out = self.bn1(out)
|
|
out = self.relu(out)
|
|
|
|
if self.drop_rate > 0.:
|
|
out = F.dropout(out, p=self.drop_rate, training=self.training)
|
|
|
|
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 += residual
|
|
out = self.relu(out)
|
|
|
|
return out
|
|
|
|
|
|
class ResNet(nn.Module):
|
|
|
|
def __init__(self, block, layers, num_classes=1000,
|
|
cardinality=1, base_width=64,
|
|
drop_rate=0.0, block_drop_rate=0.0,
|
|
global_pool='avg'):
|
|
self.num_classes = num_classes
|
|
self.inplanes = 64
|
|
self.cardinality = cardinality
|
|
self.base_width = base_width
|
|
self.drop_rate = drop_rate
|
|
self.expansion = block.expansion
|
|
super(ResNet, self).__init__()
|
|
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
|
|
self.bn1 = nn.BatchNorm2d(64)
|
|
self.relu = nn.ReLU(inplace=True)
|
|
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
|
|
self.layer1 = self._make_layer(block, 64, layers[0], drop_rate=block_drop_rate)
|
|
self.layer2 = self._make_layer(block, 128, layers[1], stride=2, drop_rate=block_drop_rate)
|
|
self.layer3 = self._make_layer(block, 256, layers[2], stride=2, drop_rate=block_drop_rate)
|
|
self.layer4 = self._make_layer(block, 512, layers[3], stride=2, drop_rate=block_drop_rate)
|
|
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
|
self.num_features = 512 * block.expansion
|
|
self.fc = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes)
|
|
|
|
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.init.constant_(m.weight, 1.)
|
|
nn.init.constant_(m.bias, 0.)
|
|
|
|
def _make_layer(self, block, planes, blocks, stride=1, drop_rate=0.):
|
|
downsample = None
|
|
if stride != 1 or self.inplanes != planes * block.expansion:
|
|
downsample = nn.Sequential(
|
|
nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False),
|
|
nn.BatchNorm2d(planes * block.expansion),
|
|
)
|
|
|
|
layers = [block(self.inplanes, planes, stride, downsample, self.cardinality, self.base_width, drop_rate)]
|
|
self.inplanes = planes * block.expansion
|
|
for i in range(1, blocks):
|
|
layers.append(block(self.inplanes, planes, cardinality=self.cardinality, base_width=self.base_width))
|
|
|
|
return nn.Sequential(*layers)
|
|
|
|
def get_classifier(self):
|
|
return self.fc
|
|
|
|
def reset_classifier(self, num_classes, global_pool='avg'):
|
|
self.global_pool = SelectAdaptivePool2d(pool_type=global_pool)
|
|
self.num_classes = num_classes
|
|
del self.fc
|
|
if num_classes:
|
|
self.fc = nn.Linear(self.num_features * self.global_pool.feat_mult(), num_classes)
|
|
else:
|
|
self.fc = None
|
|
|
|
def forward_features(self, x, pool=True):
|
|
x = self.conv1(x)
|
|
x = self.bn1(x)
|
|
x = self.relu(x)
|
|
x = self.maxpool(x)
|
|
|
|
x = self.layer1(x)
|
|
x = self.layer2(x)
|
|
x = self.layer3(x)
|
|
x = self.layer4(x)
|
|
|
|
if pool:
|
|
x = self.global_pool(x)
|
|
x = x.view(x.size(0), -1)
|
|
return x
|
|
|
|
def forward(self, x):
|
|
x = self.forward_features(x)
|
|
if self.drop_rate > 0.:
|
|
x = F.dropout(x, p=self.drop_rate, training=self.training)
|
|
x = self.fc(x)
|
|
return x
|
|
|
|
|
|
def resnet18(pretrained=False, **kwargs):
|
|
"""Constructs a ResNet-18 model.
|
|
|
|
Args:
|
|
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
|
"""
|
|
model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
|
|
if pretrained:
|
|
model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
|
|
return model
|
|
|
|
|
|
def resnet34(pretrained=False, **kwargs):
|
|
"""Constructs a ResNet-34 model.
|
|
|
|
Args:
|
|
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
|
"""
|
|
model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
|
|
if pretrained:
|
|
model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
|
|
return model
|
|
|
|
|
|
def resnet50(pretrained=False, **kwargs):
|
|
"""Constructs a ResNet-50 model.
|
|
|
|
Args:
|
|
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
|
"""
|
|
model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
|
|
if pretrained:
|
|
model.load_state_dict(model_zoo.load_url(model_urls['resnet50']))
|
|
return model
|
|
|
|
|
|
def resnet101(pretrained=False, **kwargs):
|
|
"""Constructs a ResNet-101 model.
|
|
|
|
Args:
|
|
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
|
"""
|
|
model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
|
|
if pretrained:
|
|
model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
|
|
return model
|
|
|
|
|
|
def resnet152(pretrained=False, **kwargs):
|
|
"""Constructs a ResNet-152 model.
|
|
|
|
Args:
|
|
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
|
"""
|
|
model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
|
|
if pretrained:
|
|
model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
|
|
return model
|
|
|
|
|
|
def resnext50_32x4d(cardinality=32, base_width=4, pretrained=False, **kwargs):
|
|
"""Constructs a ResNeXt50-32x4d model.
|
|
|
|
Args:
|
|
cardinality (int): Cardinality of the aggregated transform
|
|
base_width (int): Base width of the grouped convolution
|
|
"""
|
|
model = ResNet(
|
|
Bottleneck, [3, 4, 6, 3], cardinality=cardinality, base_width=base_width, **kwargs)
|
|
return model
|
|
|
|
|
|
def resnext101_32x4d(cardinality=32, base_width=4, pretrained=False, **kwargs):
|
|
"""Constructs a ResNeXt-101 model.
|
|
|
|
Args:
|
|
cardinality (int): Cardinality of the aggregated transform
|
|
base_width (int): Base width of the grouped convolution
|
|
"""
|
|
model = ResNet(
|
|
Bottleneck, [3, 4, 23, 3], cardinality=cardinality, base_width=base_width, **kwargs)
|
|
return model
|
|
|
|
|
|
def resnext101_64x4d(cardinality=64, base_width=4, pretrained=False, **kwargs):
|
|
"""Constructs a ResNeXt101-64x4d model.
|
|
|
|
Args:
|
|
cardinality (int): Cardinality of the aggregated transform
|
|
base_width (int): Base width of the grouped convolution
|
|
"""
|
|
model = ResNet(
|
|
Bottleneck, [3, 4, 23, 3], cardinality=cardinality, base_width=base_width, **kwargs)
|
|
return model
|
|
|
|
|
|
def resnext152_32x4d(cardinality=32, base_width=4, pretrained=False, **kwargs):
|
|
"""Constructs a ResNeXt152-32x4d model.
|
|
|
|
Args:
|
|
cardinality (int): Cardinality of the aggregated transform
|
|
base_width (int): Base width of the grouped convolution
|
|
"""
|
|
model = ResNet(
|
|
Bottleneck, [3, 8, 36, 3], cardinality=cardinality, base_width=base_width, **kwargs)
|
|
return model
|