def tv_resnet50(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNet-50 model with original Torchvision weights.
"""
model = ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, in_chans=in_chans, **kwargs)
model.default_cfg = default_cfgs['tv_resnet50']
if pretrained:
load_pretrained(model, 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 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 ssl_resnet18(pretrained=True, **kwargs):
"""Constructs a semi-supervised ResNet-18 model pre-trained on YFCC100M dataset and finetuned on ImageNet
`"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
"""
model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
model.default_cfg = default_cfgs['ssl_resnet18']
if pretrained:
load_pretrained(model, num_classes=kwargs.get('num_classes', 0), in_chans=kwargs.get('in_chans', 3))
return model
def ssl_resnext101_32x16d(pretrained=True, **kwargs):
"""Constructs a semi-supervised ResNeXt-101 32x16 model pre-trained on YFCC100M dataset and finetuned on ImageNet
`"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
"""
model = ResNet(Bottleneck, [3, 4, 23, 3], cardinality=32, base_width=16, **kwargs)
model.default_cfg = default_cfgs['ssl_resnext101_32x16d']
if pretrained:
load_pretrained(model, num_classes=kwargs.get('num_classes', 0), in_chans=kwargs.get('in_chans', 3))
return model
def ig_resnext101_32x48d(pretrained=True, **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/
"""
model = ResNet(Bottleneck, [3, 4, 23, 3], cardinality=32, base_width=48, **kwargs)
model.default_cfg = default_cfgs['ig_resnext101_32x48d']
if pretrained:
load_pretrained(model, num_classes=kwargs.get('num_classes', 0), in_chans=kwargs.get('in_chans', 3))
return model
def tv_resnext50_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNeXt50-32x4d model with original Torchvision weights.
"""
default_cfg = default_cfgs['tv_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_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 ecaresnet50(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs an ECA-ResNet-50 model.
"""
default_cfg = default_cfgs['ecaresnet50']
block_args = dict(attn_layer='eca')
model = ResNet(
Bottleneck, [3, 4, 6, 3], num_classes=num_classes, in_chans=in_chans, block_args=block_args, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def swsl_resnet50(pretrained=True, **kwargs):
"""Constructs a semi-weakly supervised ResNet-50 model pre-trained on 1B weakly supervised
image dataset and finetuned on ImageNet.
`"Billion-scale Semi-Supervised Learning for Image Classification" <https://arxiv.org/abs/1905.00546>`_
Weights from https://github.com/facebookresearch/semi-supervised-ImageNet1K-models/
"""
model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
model.default_cfg = default_cfgs['swsl_resnet50']
if pretrained:
load_pretrained(model, num_classes=kwargs.get('num_classes', 0), in_chans=kwargs.get('in_chans', 3))
return model
def resnet50d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNet-50-D model.
"""
default_cfg = default_cfgs['resnet50d']
model = ResNet(
Bottleneck, [3, 4, 6, 3], stem_width=32, stem_type='deep', avg_down=True,
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 ecaresnet18(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
""" Constructs an ECA-ResNet-18 model.
"""
default_cfg = default_cfgs['ecaresnet18']
block_args = dict(attn_layer='eca')
model = ResNet(
BasicBlock, [2, 2, 2, 2], num_classes=num_classes, in_chans=in_chans, block_args=block_args, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def resnet26d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNet-26 v1d model.
This is technically a 28 layer ResNet, sticking with 'd' modifier from Gluon for now.
"""
default_cfg = default_cfgs['resnet26d']
model = ResNet(
Bottleneck, [2, 2, 2, 2], stem_width=32, stem_type='deep', avg_down=True,
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 resnext50d_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNeXt50d-32x4d model. ResNext50 w/ deep stem & avg pool downsample
"""
default_cfg = default_cfgs['resnext50d_32x4d']
model = ResNet(
Bottleneck, [3, 4, 6, 3], cardinality=32, base_width=4,
stem_width=32, stem_type='deep', avg_down=True,
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 seresnext26d_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a SE-ResNeXt-26-D model.
This is technically a 28 layer ResNet, using the 'D' modifier from Gluon / bag-of-tricks for
combination of deep stem and avg_pool in downsample.
"""
default_cfg = default_cfgs['seresnext26d_32x4d']
model = ResNet(
Bottleneck, [2, 2, 2, 2], cardinality=32, base_width=4, stem_width=32, stem_type='deep', avg_down=True,
num_classes=num_classes, in_chans=in_chans, block_args=dict(attn_layer='se'), **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def wide_resnet101_2(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a Wide ResNet-101-2 model.
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.
"""
model = ResNet(
Bottleneck, [3, 4, 23, 3], base_width=128,
num_classes=num_classes, in_chans=in_chans, **kwargs)
model.default_cfg = default_cfgs['wide_resnet101_2']
if pretrained:
load_pretrained(model, model.default_cfg, num_classes, in_chans)
return model
def seresnext26tn_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a SE-ResNeXt-26-TN model.
This is technically a 28 layer ResNet, like a 'D' bag-of-tricks model but with tiered 24, 32, 64 channels
in the deep stem. The channel number of the middle stem conv is narrower than the 'T' variant.
"""
default_cfg = default_cfgs['seresnext26tn_32x4d']
model = ResNet(
Bottleneck, [2, 2, 2, 2], cardinality=32, base_width=4,
stem_width=32, stem_type='deep_tiered_narrow', avg_down=True,
num_classes=num_classes, in_chans=in_chans, block_args=dict(attn_layer='se'), **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
