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.
pytorch-image-models/timm/models/resnet.py

404 lines
16 KiB

"""Pytorch ResNet implementation w/ 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.
ResNext additions added by Ross Wightman
"""
import torch.nn as nn
import torch.nn.functional as F
import math
from .helpers import load_pretrained
from .adaptive_avgmax_pool import SelectAdaptivePool2d
from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
_models = ['resnet18', 'resnet34', 'resnet50', 'resnet101', 'resnet152',
'resnext50_32x4d', 'resnext101_32x4d', 'resnext101_64x4d', 'resnext152_32x4d',
'ig_resnext101_32x8d', 'ig_resnext101_32x16d', 'ig_resnext101_32x32d', 'ig_resnext101_32x48d']
__all__ = ['ResNet'] + _models
def _cfg(url='', **kwargs):
return {
'url': url,
'num_classes': 1000, 'input_size': (3, 224, 224), 'pool_size': (7, 7),
'crop_pct': 0.875, 'interpolation': 'bilinear',
'mean': IMAGENET_DEFAULT_MEAN, 'std': IMAGENET_DEFAULT_STD,
'first_conv': 'conv1', 'classifier': 'fc',
**kwargs
}
default_cfgs = {
'resnet18': _cfg(url='https://download.pytorch.org/models/resnet18-5c106cde.pth'),
'resnet34': _cfg(
url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/resnet34-43635321.pth'),
'resnet50': _cfg(url='https://download.pytorch.org/models/resnet50-19c8e357.pth'),
'resnet101': _cfg(url='https://download.pytorch.org/models/resnet101-5d3b4d8f.pth'),
'resnet152': _cfg(url='https://download.pytorch.org/models/resnet152-b121ed2d.pth'),
'resnext50_32x4d': _cfg(url='https://www.dropbox.com/s/yxci33lfew51p6a/resnext50_32x4d-068914d1.pth?dl=1',
interpolation='bicubic'),
'resnext101_32x4d': _cfg(url=''),
'resnext101_64x4d': _cfg(url=''),
'resnext152_32x4d': _cfg(url=''),
'ig_resnext101_32x8d': _cfg(url='https://download.pytorch.org/models/ig_resnext101_32x8-c38310e5.pth'),
'ig_resnext101_32x16d': _cfg(url='https://download.pytorch.org/models/ig_resnext101_32x16-c6f796b0.pth'),
'ig_resnext101_32x32d': _cfg(url='https://download.pytorch.org/models/ig_resnext101_32x32-e4b90b00.pth'),
'ig_resnext101_32x48d': _cfg(url='https://download.pytorch.org/models/ig_resnext101_32x48-3e41cc8a.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, in_chans=3,
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(in_chans, 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, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNet-18 model.
"""
default_cfg = default_cfgs['resnet18']
model = ResNet(BasicBlock, [2, 2, 2, 2], num_classes=num_classes, in_chans=in_chans, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def resnet34(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNet-34 model.
"""
default_cfg = default_cfgs['resnet34']
model = ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, in_chans=in_chans, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def resnet50(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNet-50 model.
"""
default_cfg = default_cfgs['resnet50']
model = ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, in_chans=in_chans, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def resnet101(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNet-101 model.
"""
default_cfg = default_cfgs['resnet101']
model = ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, in_chans=in_chans, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def resnet152(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNet-152 model.
"""
default_cfg = default_cfgs['resnet152']
model = ResNet(Bottleneck, [3, 8, 36, 3], num_classes=num_classes, in_chans=in_chans, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def resnext50_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNeXt50-32x4d model.
"""
default_cfg = default_cfgs['resnext50_32x4d']
model = ResNet(
Bottleneck, [3, 4, 6, 3], cardinality=32, base_width=4,
num_classes=num_classes, in_chans=in_chans, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def resnext101_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNeXt-101 model.
"""
default_cfg = default_cfgs['resnext101_32x4d']
model = ResNet(
Bottleneck, [3, 4, 23, 3], cardinality=32, base_width=4,
num_classes=num_classes, in_chans=in_chans, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def resnext101_64x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNeXt101-64x4d model.
"""
default_cfg = default_cfgs['resnext101_32x4d']
model = ResNet(
Bottleneck, [3, 4, 23, 3], cardinality=64, base_width=4,
num_classes=num_classes, in_chans=in_chans, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def resnext152_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNeXt152-32x4d model.
"""
default_cfg = default_cfgs['resnext152_32x4d']
model = ResNet(
Bottleneck, [3, 8, 36, 3], cardinality=32, base_width=4,
num_classes=num_classes, in_chans=in_chans, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def ig_resnext101_32x8d(pretrained=True, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNeXt-101 32x8 model pre-trained on weakly-supervised data
and finetuned on ImageNet from Figure 5 in
`"Exploring the Limits of Weakly Supervised Pretraining" <https://arxiv.org/abs/1805.00932>`_
Weights from https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/
Args:
pretrained (bool): load pretrained weights
num_classes (int): number of classes for classifier (default: 1000 for pretrained)
in_chans (int): number of input planes (default: 3 for pretrained / color)
"""
default_cfg = default_cfgs['ig_resnext101_32x8d']
model = ResNet(Bottleneck, [3, 4, 23, 3], cardinality=32, base_width=8, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def ig_resnext101_32x16d(pretrained=True, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNeXt-101 32x16 model pre-trained on weakly-supervised data
and finetuned on ImageNet from Figure 5 in
`"Exploring the Limits of Weakly Supervised Pretraining" <https://arxiv.org/abs/1805.00932>`_
Weights from https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/
Args:
pretrained (bool): load pretrained weights
num_classes (int): number of classes for classifier (default: 1000 for pretrained)
in_chans (int): number of input planes (default: 3 for pretrained / color)
"""
default_cfg = default_cfgs['ig_resnext101_32x16d']
model = ResNet(Bottleneck, [3, 4, 23, 3], cardinality=32, base_width=16, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def ig_resnext101_32x32d(pretrained=True, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNeXt-101 32x32 model pre-trained on weakly-supervised data
and finetuned on ImageNet from Figure 5 in
`"Exploring the Limits of Weakly Supervised Pretraining" <https://arxiv.org/abs/1805.00932>`_
Weights from https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/
Args:
pretrained (bool): load pretrained weights
num_classes (int): number of classes for classifier (default: 1000 for pretrained)
in_chans (int): number of input planes (default: 3 for pretrained / color)
"""
default_cfg = default_cfgs['ig_resnext101_32x32d']
model = ResNet(Bottleneck, [3, 4, 23, 3], cardinality=32, base_width=32, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def ig_resnext101_32x48d(pretrained=True, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNeXt-101 32x48 model pre-trained on weakly-supervised data
and finetuned on ImageNet from Figure 5 in
`"Exploring the Limits of Weakly Supervised Pretraining" <https://arxiv.org/abs/1805.00932>`_
Weights from https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/
Args:
pretrained (bool): load pretrained weights
num_classes (int): number of classes for classifier (default: 1000 for pretrained)
in_chans (int): number of input planes (default: 3 for pretrained / color)
"""
default_cfg = default_cfgs['ig_resnext101_32x48d']
model = ResNet(Bottleneck, [3, 4, 23, 3], cardinality=32, base_width=48, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model