231 lines
8.5 KiB
Python
231 lines
8.5 KiB
Python
|
import math
|
||
|
|
|
||
|
|
import torch.nn as nn
|
||
|
|
from torch.hub import load_state_dict_from_url
|
||
|
|
from typing import Type, Any, Callable, Union, List, Optional
|
||
|
|
from torch import Tensor
|
||
|
|
|
||
|
|
model_urls = {
|
||
|
|
'resnet50': 'https://github.com/bubbliiiing/pspnet-pytorch/releases/download/v1.0/resnet50s-a75c83cf.pth',
|
||
|
|
'resnet101': '',
|
||
|
|
}
|
||
|
|
|
||
|
|
class BasicBlock(nn.Module):
|
||
|
|
expansion: int = 1
|
||
|
|
|
||
|
|
def __init__(
|
||
|
|
self,
|
||
|
|
inplanes: int,
|
||
|
|
planes: int,
|
||
|
|
stride: int = 1,
|
||
|
|
downsample: Optional[nn.Module] = None,
|
||
|
|
groups: int = 1,
|
||
|
|
base_width: int = 64,
|
||
|
|
dilation: int = 1,
|
||
|
|
norm_layer: Optional[Callable[..., nn.Module]] = None
|
||
|
|
) -> 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: Tensor) -> Tensor:
|
||
|
|
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
|
||
|
|
|
||
|
|
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 Bottleneck(nn.Module):
|
||
|
|
expansion = 4
|
||
|
|
|
||
|
|
def __init__(self, inplanes, planes, stride=1, dilation=1, downsample=None, previous_dilation=1,
|
||
|
|
norm_layer=None):
|
||
|
|
super(Bottleneck, self).__init__()
|
||
|
|
self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
|
||
|
|
self.bn1 = norm_layer(planes)
|
||
|
|
|
||
|
|
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=dilation, dilation=dilation,
|
||
|
|
bias=False)
|
||
|
|
self.bn2 = norm_layer(planes)
|
||
|
|
|
||
|
|
self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
|
||
|
|
self.bn3 = norm_layer(planes * 4)
|
||
|
|
|
||
|
|
self.relu = nn.ReLU(inplace=True)
|
||
|
|
|
||
|
|
self.downsample = downsample
|
||
|
|
self.dilation = dilation
|
||
|
|
self.stride = stride
|
||
|
|
|
||
|
|
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 += residual
|
||
|
|
out = self.relu(out)
|
||
|
|
return out
|
||
|
|
|
||
|
|
|
||
|
|
class ResNet(nn.Module):
|
||
|
|
def __init__(self, block, layers, num_classes=1000, dilated=False, deep_base=True, norm_layer=nn.BatchNorm2d):
|
||
|
|
self.inplanes = 128 if deep_base else 64
|
||
|
|
super(ResNet, self).__init__()
|
||
|
|
if deep_base:
|
||
|
|
self.conv1 = nn.Sequential(
|
||
|
|
nn.Conv2d(3, 64, kernel_size=3, stride=2, padding=1, bias=False),
|
||
|
|
norm_layer(64),
|
||
|
|
nn.ReLU(inplace=True),
|
||
|
|
nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1, bias=False),
|
||
|
|
norm_layer(64),
|
||
|
|
nn.ReLU(inplace=True),
|
||
|
|
nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1, bias=False),
|
||
|
|
)
|
||
|
|
else:
|
||
|
|
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
|
||
|
|
bias=False)
|
||
|
|
self.bn1 = norm_layer(self.inplanes)
|
||
|
|
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], norm_layer=norm_layer)
|
||
|
|
self.layer2 = self._make_layer(block, 128, layers[1], stride=2, norm_layer=norm_layer)
|
||
|
|
if dilated:
|
||
|
|
self.layer3 = self._make_layer(block, 256, layers[2], stride=1,
|
||
|
|
dilation=2, norm_layer=norm_layer)
|
||
|
|
self.layer4 = self._make_layer(block, 512, layers[3], stride=1,
|
||
|
|
dilation=4, norm_layer=norm_layer)
|
||
|
|
else:
|
||
|
|
self.layer3 = self._make_layer(block, 256, layers[2], stride=2,
|
||
|
|
norm_layer=norm_layer)
|
||
|
|
self.layer4 = self._make_layer(block, 512, layers[3], stride=2,
|
||
|
|
norm_layer=norm_layer)
|
||
|
|
|
||
|
|
self.avgpool = nn.AvgPool2d(7, stride=1)
|
||
|
|
self.fc = nn.Linear(512 * block.expansion, num_classes)
|
||
|
|
|
||
|
|
for m in self.modules():
|
||
|
|
if isinstance(m, nn.Conv2d):
|
||
|
|
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
||
|
|
m.weight.data.normal_(0, math.sqrt(2. / n))
|
||
|
|
elif isinstance(m, norm_layer):
|
||
|
|
m.weight.data.fill_(1)
|
||
|
|
m.bias.data.zero_()
|
||
|
|
|
||
|
|
def _make_layer(self, block, planes, blocks, stride=1, dilation=1, norm_layer=None, multi_grid=False):
|
||
|
|
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),
|
||
|
|
norm_layer(planes * block.expansion),
|
||
|
|
)
|
||
|
|
|
||
|
|
layers = []
|
||
|
|
multi_dilations = [4, 8, 16]
|
||
|
|
if multi_grid:
|
||
|
|
layers.append(block(self.inplanes, planes, stride, dilation=multi_dilations[0],
|
||
|
|
downsample=downsample, previous_dilation=dilation, norm_layer=norm_layer))
|
||
|
|
elif dilation == 1 or dilation == 2:
|
||
|
|
layers.append(block(self.inplanes, planes, stride, dilation=1,
|
||
|
|
downsample=downsample, previous_dilation=dilation, norm_layer=norm_layer))
|
||
|
|
elif dilation == 4:
|
||
|
|
layers.append(block(self.inplanes, planes, stride, dilation=2,
|
||
|
|
downsample=downsample, previous_dilation=dilation, norm_layer=norm_layer))
|
||
|
|
else:
|
||
|
|
raise RuntimeError("=> unknown dilation size: {}".format(dilation))
|
||
|
|
|
||
|
|
self.inplanes = planes * block.expansion
|
||
|
|
for i in range(1, blocks):
|
||
|
|
if multi_grid:
|
||
|
|
layers.append(block(self.inplanes, planes, dilation=multi_dilations[i],
|
||
|
|
previous_dilation=dilation, norm_layer=norm_layer))
|
||
|
|
else:
|
||
|
|
layers.append(block(self.inplanes, planes, dilation=dilation, previous_dilation=dilation,
|
||
|
|
norm_layer=norm_layer))
|
||
|
|
|
||
|
|
return nn.Sequential(*layers)
|
||
|
|
|
||
|
|
def forward(self, x):
|
||
|
|
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)
|
||
|
|
|
||
|
|
x = self.avgpool(x)
|
||
|
|
x = x.view(x.size(0), -1)
|
||
|
|
x = self.fc(x)
|
||
|
|
|
||
|
|
return x
|
||
|
|
|
||
|
|
|
||
|
|
def resnet50(pretrained=False, **kwargs):
|
||
|
|
model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
|
||
|
|
if pretrained:
|
||
|
|
model.load_state_dict(load_state_dict_from_url(model_urls['resnet50'], "./model_data"), strict=False)
|
||
|
|
return model
|
||
|
|
|
||
|
|
def resnet101(pretrained=False, **kwargs):
|
||
|
|
model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
|
||
|
|
# if pretrained:
|
||
|
|
# model.load_state_dict(load_state_dict_from_url(model_urls['resnet101'], "./model_data"), strict=False)
|
||
|
|
return model
|
||
|
|
|
||
|
|
def resnet18(pretrained: bool = False, progress: bool = True, **kwargs):
|
||
|
|
r"""ResNet-18 model from
|
||
|
|
`"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
pretrained (bool): If True, returns a model pre-trained on ImageNet
|
||
|
|
progress (bool): If True, displays a progress bar of the download to stderr
|
||
|
|
"""
|
||
|
|
model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
|
||
|
|
return model
|