mirrors/pytorch-image-models
1
0
Fork 0
mirror of https://github.com/huggingface/pytorch-image-models.git synced 2025-06-03 15:01:08 +08:00
Code Issues Projects Releases Wiki Activity

Fix another bug, update all gluon resnet models to use new creation method (feature support)

Browse Source
This commit is contained in:
Ross Wightman 2020-06-30 16:44:15 -07:00
parent d0113f9cdb
commit 7729f40dca
3 changed files with 86 additions and 228 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

302
timm/models/gluon_resnet.py
View File

@ -5,10 +5,9 @@ by Ross Wightman
""" """
from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
from .helpers import load_pretrained
from .layers import SEModule from .layers import SEModule
from .registry import register_model from .registry import register_model
from .resnet import ResNet, Bottleneck, BasicBlock from .resnet import _create_resnet_with_cfg, Bottleneck, BasicBlock
def _cfg(url='', **kwargs): def _cfg(url='', **kwargs):
@ -34,9 +33,6 @@ default_cfgs = {
'gluon_resnet50_v1d': _cfg(url='https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_resnet50_v1d-818a1b1b.pth'), 'gluon_resnet50_v1d': _cfg(url='https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_resnet50_v1d-818a1b1b.pth'),
'gluon_resnet101_v1d': _cfg(url='https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_resnet101_v1d-0f9c8644.pth'), 'gluon_resnet101_v1d': _cfg(url='https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_resnet101_v1d-0f9c8644.pth'),
'gluon_resnet152_v1d': _cfg(url='https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_resnet152_v1d-bd354e12.pth'), 'gluon_resnet152_v1d': _cfg(url='https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_resnet152_v1d-bd354e12.pth'),
'gluon_resnet50_v1e': _cfg(url=''),
'gluon_resnet101_v1e': _cfg(url=''),
'gluon_resnet152_v1e': _cfg(url=''),
'gluon_resnet50_v1s': _cfg(url='https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_resnet50_v1s-1762acc0.pth'), 'gluon_resnet50_v1s': _cfg(url='https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_resnet50_v1s-1762acc0.pth'),
'gluon_resnet101_v1s': _cfg(url='https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_resnet101_v1s-60fe0cc1.pth'), 'gluon_resnet101_v1s': _cfg(url='https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_resnet101_v1s-60fe0cc1.pth'),
'gluon_resnet152_v1s': _cfg(url='https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_resnet152_v1s-dcc41b81.pth'), 'gluon_resnet152_v1s': _cfg(url='https://github.com/rwightman/pytorch-pretrained-gluonresnet/releases/download/v0.1/gluon_resnet152_v1s-dcc41b81.pth'),
@ -50,318 +46,190 @@ default_cfgs = {
} }
def _create_resnet(variant, pretrained=False, **kwargs):
default_cfg = default_cfgs[variant]
return _create_resnet_with_cfg(variant, default_cfg, pretrained=pretrained, **kwargs)
@register_model @register_model
def gluon_resnet18_v1b(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet18_v1b(pretrained=False, **kwargs):
"""Constructs a ResNet-18 model. """Constructs a ResNet-18 model.
""" """
default_cfg = default_cfgs['gluon_resnet18_v1b'] model_args = dict(block=BasicBlock, layers=[2, 2, 2, 2], **kwargs)
model = ResNet(BasicBlock, [2, 2, 2, 2], num_classes=num_classes, in_chans=in_chans, **kwargs) return _create_resnet('gluon_resnet18_v1b', pretrained, **model_args)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnet34_v1b(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet34_v1b(pretrained=False, **kwargs):
"""Constructs a ResNet-34 model. """Constructs a ResNet-34 model.
""" """
default_cfg = default_cfgs['gluon_resnet34_v1b'] model_args = dict(block=BasicBlock, layers=[3, 4, 6, 3], **kwargs)
model = ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, in_chans=in_chans, **kwargs) return _create_resnet('gluon_resnet34_v1b', pretrained, **model_args)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnet50_v1b(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet50_v1b(pretrained=False, **kwargs):
"""Constructs a ResNet-50 model. """Constructs a ResNet-50 model.
""" """
default_cfg = default_cfgs['gluon_resnet50_v1b'] model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3], **kwargs)
model = ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, in_chans=in_chans, **kwargs) return _create_resnet('gluon_resnet50_v1b', pretrained, **model_args)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnet101_v1b(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet101_v1b(pretrained=False, **kwargs):
"""Constructs a ResNet-101 model. """Constructs a ResNet-101 model.
""" """
default_cfg = default_cfgs['gluon_resnet101_v1b'] model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], **kwargs)
model = ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, in_chans=in_chans, **kwargs) return _create_resnet('gluon_resnet101_v1b', pretrained, **model_args)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnet152_v1b(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet152_v1b(pretrained=False, **kwargs):
"""Constructs a ResNet-152 model. """Constructs a ResNet-152 model.
""" """
default_cfg = default_cfgs['gluon_resnet152_v1b'] model_args = dict(block=Bottleneck, layers=[3, 8, 36, 3], **kwargs)
model = ResNet(Bottleneck, [3, 8, 36, 3], num_classes=num_classes, in_chans=in_chans, **kwargs) return _create_resnet('gluon_resnet152_v1b', pretrained, **model_args)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnet50_v1c(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet50_v1c(pretrained=False, **kwargs):
"""Constructs a ResNet-50 model. """Constructs a ResNet-50 model.
""" """
default_cfg = default_cfgs['gluon_resnet50_v1c'] model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3], stem_width=32, stem_type='deep', **kwargs)
model = ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, in_chans=in_chans, return _create_resnet('gluon_resnet50_v1c', pretrained, **model_args)
stem_width=32, stem_type='deep', **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnet101_v1c(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet101_v1c(pretrained=False, **kwargs):
"""Constructs a ResNet-101 model. """Constructs a ResNet-101 model.
""" """
default_cfg = default_cfgs['gluon_resnet101_v1c'] model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], stem_width=32, stem_type='deep', **kwargs)
model = ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, in_chans=in_chans, return _create_resnet('gluon_resnet101_v1c', pretrained, **model_args)
stem_width=32, stem_type='deep', **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnet152_v1c(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet152_v1c(pretrained=False, **kwargs):
"""Constructs a ResNet-152 model. """Constructs a ResNet-152 model.
""" """
default_cfg = default_cfgs['gluon_resnet152_v1c'] model_args = dict(block=Bottleneck, layers=[3, 8, 36, 3], stem_width=32, stem_type='deep', **kwargs)
model = ResNet(Bottleneck, [3, 8, 36, 3], num_classes=num_classes, in_chans=in_chans, return _create_resnet('gluon_resnet152_v1c', pretrained, **model_args)
stem_width=32, stem_type='deep', **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnet50_v1d(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet50_v1d(pretrained=False, **kwargs):
"""Constructs a ResNet-50 model. """Constructs a ResNet-50 model.
""" """
default_cfg = default_cfgs['gluon_resnet50_v1d'] model_args = dict(
model = ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, in_chans=in_chans, block=Bottleneck, layers=[3, 4, 6, 3], stem_width=32, stem_type='deep', avg_down=True, **kwargs)
stem_width=32, stem_type='deep', avg_down=True, **kwargs) return _create_resnet('gluon_resnet50_v1d', pretrained, **model_args)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnet101_v1d(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet101_v1d(pretrained=False, **kwargs):
"""Constructs a ResNet-101 model. """Constructs a ResNet-101 model.
""" """
default_cfg = default_cfgs['gluon_resnet101_v1d'] model_args = dict(
model = ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, in_chans=in_chans, block=Bottleneck, layers=[3, 4, 23, 3], stem_width=32, stem_type='deep', avg_down=True, **kwargs)
stem_width=32, stem_type='deep', avg_down=True, **kwargs) return _create_resnet('gluon_resnet101_v1d', pretrained, **model_args)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnet152_v1d(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet152_v1d(pretrained=False, **kwargs):
"""Constructs a ResNet-152 model. """Constructs a ResNet-152 model.
""" """
default_cfg = default_cfgs['gluon_resnet152_v1d'] model_args = dict(
model = ResNet(Bottleneck, [3, 8, 36, 3], num_classes=num_classes, in_chans=in_chans, block=Bottleneck, layers=[3, 8, 36, 3], stem_width=32, stem_type='deep', avg_down=True, **kwargs)
stem_width=32, stem_type='deep', avg_down=True, **kwargs) return _create_resnet('gluon_resnet152_v1d', pretrained, **model_args)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnet50_v1e(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet50_v1s(pretrained=False, **kwargs):
"""Constructs a ResNet-50-V1e model. No pretrained weights for any 'e' variants
"""
default_cfg = default_cfgs['gluon_resnet50_v1e']
model = ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, in_chans=in_chans,
stem_width=64, stem_type='deep', avg_down=True, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model
def gluon_resnet101_v1e(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNet-101 model.
"""
default_cfg = default_cfgs['gluon_resnet101_v1e']
model = ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, in_chans=in_chans,
stem_width=64, stem_type='deep', avg_down=True, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model
def gluon_resnet152_v1e(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNet-152 model.
"""
default_cfg = default_cfgs['gluon_resnet152_v1e']
model = ResNet(Bottleneck, [3, 8, 36, 3], num_classes=num_classes, in_chans=in_chans,
stem_width=64, stem_type='deep', avg_down=True, **kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model
def gluon_resnet50_v1s(pretrained=False, num_classes=1000, in_chans=3, **kwargs):
"""Constructs a ResNet-50 model. """Constructs a ResNet-50 model.
""" """
default_cfg = default_cfgs['gluon_resnet50_v1s'] model_args = dict(
model = ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, in_chans=in_chans, block=Bottleneck, layers=[3, 4, 6, 3], stem_width=64, stem_type='deep', **kwargs)
stem_width=64, stem_type='deep', **kwargs) return _create_resnet('gluon_resnet50_v1s', pretrained, **model_args)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnet101_v1s(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet101_v1s(pretrained=False, **kwargs):
"""Constructs a ResNet-101 model. """Constructs a ResNet-101 model.
""" """
default_cfg = default_cfgs['gluon_resnet101_v1s'] model_args = dict(
model = ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, in_chans=in_chans, block=Bottleneck, layers=[3, 4, 23, 3], stem_width=64, stem_type='deep', **kwargs)
stem_width=64, stem_type='deep', **kwargs) return _create_resnet('gluon_resnet101_v1s', pretrained, **model_args)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnet152_v1s(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnet152_v1s(pretrained=False, **kwargs):
"""Constructs a ResNet-152 model. """Constructs a ResNet-152 model.
""" """
default_cfg = default_cfgs['gluon_resnet152_v1s'] model_args = dict(
model = ResNet(Bottleneck, [3, 8, 36, 3], num_classes=num_classes, in_chans=in_chans, block=Bottleneck, layers=[3, 8, 36, 3], stem_width=64, stem_type='deep', **kwargs)
stem_width=64, stem_type='deep', **kwargs) return _create_resnet('gluon_resnet152_v1s', pretrained, **model_args)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_resnext50_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnext50_32x4d(pretrained=False, **kwargs):
"""Constructs a ResNeXt50-32x4d model. """Constructs a ResNeXt50-32x4d model.
""" """
default_cfg = default_cfgs['gluon_resnext50_32x4d'] model_args = dict(block=Bottleneck, layers=[3, 4, 6, 3], cardinality=32, base_width=4, **kwargs)
model = ResNet( return _create_resnet('gluon_resnext50_32x4d', pretrained, **model_args)
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
@register_model @register_model
def gluon_resnext101_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnext101_32x4d(pretrained=False, **kwargs):
"""Constructs a ResNeXt-101 model. """Constructs a ResNeXt-101 model.
""" """
default_cfg = default_cfgs['gluon_resnext101_32x4d'] model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=4, **kwargs)
model = ResNet( return _create_resnet('gluon_resnext101_32x4d', pretrained, **model_args)
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
@register_model @register_model
def gluon_resnext101_64x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_resnext101_64x4d(pretrained=False, **kwargs):
"""Constructs a ResNeXt-101 model. """Constructs a ResNeXt-101 model.
""" """
default_cfg = default_cfgs['gluon_resnext101_64x4d'] model_args = dict(block=Bottleneck, layers=[3, 4, 23, 3], cardinality=64, base_width=4, **kwargs)
model = ResNet( return _create_resnet('gluon_resnext101_64x4d', pretrained, **model_args)
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
@register_model @register_model
def gluon_seresnext50_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_seresnext50_32x4d(pretrained=False, **kwargs):
"""Constructs a SEResNeXt50-32x4d model. """Constructs a SEResNeXt50-32x4d model.
""" """
default_cfg = default_cfgs['gluon_seresnext50_32x4d'] model_args = dict(
model = ResNet( block=Bottleneck, layers=[3, 4, 6, 3], cardinality=32, base_width=4,
Bottleneck, [3, 4, 6, 3], cardinality=32, base_width=4, block_args=dict(attn_layer=SEModule), **kwargs)
num_classes=num_classes, in_chans=in_chans, block_args=dict(attn_layer=SEModule), **kwargs) return _create_resnet('gluon_seresnext50_32x4d', pretrained, **model_args)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_seresnext101_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_seresnext101_32x4d(pretrained=False, **kwargs):
"""Constructs a SEResNeXt-101-32x4d model. """Constructs a SEResNeXt-101-32x4d model.
""" """
default_cfg = default_cfgs['gluon_seresnext101_32x4d'] model_args = dict(
model = ResNet( block=Bottleneck, layers=[3, 4, 23, 3], cardinality=32, base_width=4,
Bottleneck, [3, 4, 23, 3], cardinality=32, base_width=4, block_args=dict(attn_layer=SEModule), **kwargs)
num_classes=num_classes, in_chans=in_chans, block_args=dict(attn_layer=SEModule), **kwargs) return _create_resnet('gluon_seresnext101_32x4d', pretrained, **model_args)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
@register_model @register_model
def gluon_seresnext101_64x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_seresnext101_64x4d(pretrained=False, **kwargs):
"""Constructs a SEResNeXt-101-64x4d model. """Constructs a SEResNeXt-101-64x4d model.
""" """
default_cfg = default_cfgs['gluon_seresnext101_64x4d'] model_args = dict(
block_args = dict(attn_layer=SEModule) block=Bottleneck, layers=[3, 4, 23, 3], cardinality=64, base_width=4,
model = ResNet( block_args=dict(attn_layer=SEModule), **kwargs)
Bottleneck, [3, 4, 23, 3], cardinality=64, base_width=4, return _create_resnet('gluon_seresnext101_64x4d', pretrained, **model_args)
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
@register_model @register_model
def gluon_senet154(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def gluon_senet154(pretrained=False, **kwargs):
"""Constructs an SENet-154 model. """Constructs an SENet-154 model.
""" """
default_cfg = default_cfgs['gluon_senet154'] model_args = dict(
block_args = dict(attn_layer=SEModule) block=Bottleneck, layers=[3, 8, 36, 3], cardinality=64, base_width=4, stem_type='deep',
model = ResNet( down_kernel_size=3, block_reduce_first=2, block_args=dict(attn_layer=SEModule), **kwargs)
Bottleneck, [3, 8, 36, 3], cardinality=64, base_width=4, stem_type='deep', down_kernel_size=3, return _create_resnet('gluon_senet154', pretrained, **model_args)
block_reduce_first=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

9
timm/models/mobilenetv3.py
View File

@ -199,15 +199,6 @@ class MobileNetV3Features(nn.Module):
hooks = self.feature_info.get_by_key(keys=('module', 'hook_type')) hooks = self.feature_info.get_by_key(keys=('module', 'hook_type'))
self.feature_hooks = FeatureHooks(hooks, self.named_modules()) self.feature_hooks = FeatureHooks(hooks, self.named_modules())
def feature_channels(self, idx=None):
""" Feature Channel Shortcut
Returns feature channel count for each output index if idx == None. If idx is an integer, will
return feature channel count for that feature block index (independent of out_indices setting).
"""
if isinstance(idx, int):
return self.feature_info[idx]['num_chs']
return [self.feature_info[i]['num_chs'] for i in self.out_indices]
def forward(self, x) -> List[torch.Tensor]: def forward(self, x) -> List[torch.Tensor]:
x = self.conv_stem(x) x = self.conv_stem(x)
x = self.bn1(x) x = self.bn1(x)

3
timm/models/resnet.py
View File

@ -525,7 +525,6 @@ def _create_resnet_with_cfg(variant, default_cfg, pretrained=False, **kwargs):
out_indices = None out_indices = None
if kwargs.pop('features_only', False): if kwargs.pop('features_only', False):
features = True features = True
kwargs.pop('num_classes', 0)
out_indices = kwargs.pop('out_indices', (0, 1, 2, 3, 4)) out_indices = kwargs.pop('out_indices', (0, 1, 2, 3, 4))
pruned = kwargs.pop('pruned', False) pruned = kwargs.pop('pruned', False)
@ -910,7 +909,7 @@ def seresnext26tn_32x4d(pretrained=False, **kwargs):
@register_model @register_model
def ecaresnext26tn_32x4d(pretrained=False, num_classes=1000, in_chans=3, **kwargs): def ecaresnext26tn_32x4d(pretrained=False, **kwargs):
"""Constructs an ECA-ResNeXt-26-TN model. """Constructs an ECA-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 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. in the deep stem. The channel number of the middle stem conv is narrower than the 'T' variant.