forked from mrq/DL-Art-School
036684893e
- Added LARS and SGD optimizer variants that support turning off certain features for BN and bias layers - Added a variant of pytorch's resnet model that supports gradient checkpointing. - Modify the trainer infrastructure to support above - Fix bug with BYOL (should have been nonfunctional)
191 lines
7.5 KiB
Python
191 lines
7.5 KiB
Python
# A direct copy of torchvision's resnet.py modified to support gradient checkpointing.
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
from torchvision.models.resnet import BasicBlock, Bottleneck
|
|
from torchvision.models.utils import load_state_dict_from_url
|
|
import torchvision
|
|
|
|
|
|
__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
|
|
'resnet152', 'resnext50_32x4d', 'resnext101_32x8d',
|
|
'wide_resnet50_2', 'wide_resnet101_2']
|
|
|
|
from utils.util import checkpoint
|
|
|
|
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',
|
|
'resnext50_32x4d': 'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth',
|
|
'resnext101_32x8d': 'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth',
|
|
'wide_resnet50_2': 'https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth',
|
|
'wide_resnet101_2': 'https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth',
|
|
}
|
|
|
|
|
|
class ResNet(torchvision.models.resnet.ResNet):
|
|
|
|
def __init__(self, block, layers, num_classes=1000, zero_init_residual=False,
|
|
groups=1, width_per_group=64, replace_stride_with_dilation=None,
|
|
norm_layer=None):
|
|
super().__init__(block, layers, num_classes, zero_init_residual, groups, width_per_group,
|
|
replace_stride_with_dilation, norm_layer)
|
|
|
|
def _forward_impl(self, x):
|
|
# Should be the exact same implementation of torchvision.models.resnet.ResNet.forward_impl,
|
|
# except using checkpoints on the body conv layers.
|
|
x = self.conv1(x)
|
|
x = self.bn1(x)
|
|
x = self.relu(x)
|
|
x = self.maxpool(x)
|
|
|
|
x = checkpoint(self.layer1, x)
|
|
x = checkpoint(self.layer2, x)
|
|
x = checkpoint(self.layer3, x)
|
|
x = checkpoint(self.layer4, x)
|
|
|
|
x = self.avgpool(x)
|
|
x = torch.flatten(x, 1)
|
|
x = self.fc(x)
|
|
|
|
return x
|
|
|
|
def forward(self, x):
|
|
return self._forward_impl(x)
|
|
|
|
|
|
def _resnet(arch, block, layers, pretrained, progress, **kwargs):
|
|
model = ResNet(block, layers, **kwargs)
|
|
if pretrained:
|
|
state_dict = load_state_dict_from_url(model_urls[arch],
|
|
progress=progress)
|
|
model.load_state_dict(state_dict)
|
|
return model
|
|
|
|
|
|
def resnet18(pretrained=False, progress=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
|
|
"""
|
|
return _resnet('resnet18', BasicBlock, [2, 2, 2, 2], pretrained, progress,
|
|
**kwargs)
|
|
|
|
|
|
def resnet34(pretrained=False, progress=True, **kwargs):
|
|
r"""ResNet-34 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
|
|
"""
|
|
return _resnet('resnet34', BasicBlock, [3, 4, 6, 3], pretrained, progress,
|
|
**kwargs)
|
|
|
|
|
|
def resnet50(pretrained=False, progress=True, **kwargs):
|
|
r"""ResNet-50 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
|
|
"""
|
|
return _resnet('resnet50', Bottleneck, [3, 4, 6, 3], pretrained, progress,
|
|
**kwargs)
|
|
|
|
|
|
def resnet101(pretrained=False, progress=True, **kwargs):
|
|
r"""ResNet-101 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
|
|
"""
|
|
return _resnet('resnet101', Bottleneck, [3, 4, 23, 3], pretrained, progress,
|
|
**kwargs)
|
|
|
|
|
|
def resnet152(pretrained=False, progress=True, **kwargs):
|
|
r"""ResNet-152 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
|
|
"""
|
|
return _resnet('resnet152', Bottleneck, [3, 8, 36, 3], pretrained, progress,
|
|
**kwargs)
|
|
|
|
|
|
def resnext50_32x4d(pretrained=False, progress=True, **kwargs):
|
|
r"""ResNeXt-50 32x4d model from
|
|
`"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.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
|
|
"""
|
|
kwargs['groups'] = 32
|
|
kwargs['width_per_group'] = 4
|
|
return _resnet('resnext50_32x4d', Bottleneck, [3, 4, 6, 3],
|
|
pretrained, progress, **kwargs)
|
|
|
|
|
|
def resnext101_32x8d(pretrained=False, progress=True, **kwargs):
|
|
r"""ResNeXt-101 32x8d model from
|
|
`"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.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
|
|
"""
|
|
kwargs['groups'] = 32
|
|
kwargs['width_per_group'] = 8
|
|
return _resnet('resnext101_32x8d', Bottleneck, [3, 4, 23, 3],
|
|
pretrained, progress, **kwargs)
|
|
|
|
|
|
def wide_resnet50_2(pretrained=False, progress=True, **kwargs):
|
|
r"""Wide ResNet-50-2 model from
|
|
`"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_
|
|
|
|
The model is the same as ResNet except for the bottleneck number of channels
|
|
which is twice larger in every block. The number of channels in outer 1x1
|
|
convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
|
|
channels, and in Wide ResNet-50-2 has 2048-1024-2048.
|
|
|
|
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
|
|
"""
|
|
kwargs['width_per_group'] = 64 * 2
|
|
return _resnet('wide_resnet50_2', Bottleneck, [3, 4, 6, 3],
|
|
pretrained, progress, **kwargs)
|
|
|
|
|
|
def wide_resnet101_2(pretrained=False, progress=True, **kwargs):
|
|
r"""Wide ResNet-101-2 model from
|
|
`"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_
|
|
|
|
The model is the same as ResNet except for the bottleneck number of channels
|
|
which is twice larger in every block. The number of channels in outer 1x1
|
|
convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
|
|
channels, and in Wide ResNet-50-2 has 2048-1024-2048.
|
|
|
|
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
|
|
"""
|
|
kwargs['width_per_group'] = 64 * 2
|
|
return _resnet('wide_resnet101_2', Bottleneck, [3, 4, 23, 3],
|
|
pretrained, progress, **kwargs)
|