def inception_v4(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
default_cfg = default_cfgs['inception_v4']
model = InceptionV4(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 senet154(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
default_cfg = default_cfgs['senet154']
model = SENet(SEBottleneck, [3, 8, 36, 3], groups=64, reduction=16,
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(num_classes=1000, in_chans=3, pretrained=False, **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(num_classes=1000, in_chans=3, pretrained=False, **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 seresnext101_32x4d(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
default_cfg = default_cfgs['seresnext101_32x4d']
model = SENet(SEResNeXtBottleneck, [3, 4, 23, 3], groups=32, reduction=16,
inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
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 seresnet18(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
default_cfg = default_cfgs['seresnet18']
model = SENet(SEResNetBlock, [2, 2, 2, 2], groups=1, reduction=16,
inplanes=64, input_3x3=False,
downsample_kernel_size=1, downsample_padding=0,
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 tf_inception_v3(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
# my port of Tensorflow SLIM weights (http://download.tensorflow.org/models/inception_v3_2016_08_28.tar.gz)
default_cfg = default_cfgs['tf_inception_v3']
assert in_chans == 3
_assert_default_kwargs(kwargs)
model = Inception3(num_classes=num_classes, aux_logits=False, transform_input=False)
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
model.default_cfg = default_cfg
return model
def inception_v3(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
# original PyTorch weights, ported from Tensorflow but modified
default_cfg = default_cfgs['inception_v3']
assert in_chans == 3
_assert_default_kwargs(kwargs)
model = Inception3(num_classes=num_classes, aux_logits=True, transform_input=False)
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
model.default_cfg = default_cfg
return model
def gluon_inception_v3(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
# from gluon pretrained models, best performing in terms of accuracy/loss metrics
# https://gluon-cv.mxnet.io/model_zoo/classification.html
default_cfg = default_cfgs['gluon_inception_v3']
assert in_chans == 3
_assert_default_kwargs(kwargs)
model = Inception3(num_classes=num_classes, aux_logits=False, transform_input=False)
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
model.default_cfg = default_cfg
return model
def fbnetc_100(num_classes, in_chans=3, pretrained=False, **kwargs):
""" FBNet-C """
default_cfg = default_cfgs['fbnetc_100']
model = _gen_fbnetc(1.0,
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(num_classes=1000, in_chans=3, pretrained=False, **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 mnasnet_075(num_classes, in_chans=3, pretrained=False, **kwargs):
""" MNASNet B1, depth multiplier of 0.75. """
default_cfg = default_cfgs['mnasnet_075']
model = _gen_mnasnet_b1(0.75,
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 spnasnet_100(num_classes, in_chans=3, pretrained=False, **kwargs):
""" Single-Path NAS Pixel1"""
default_cfg = default_cfgs['spnasnet_100']
model = _gen_spnasnet(1.0,
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 chamnetv2_100(num_classes, in_chans=3, pretrained=False, **kwargs):
""" ChamNet """
default_cfg = default_cfgs['chamnetv2_100']
model = _gen_chamnet_v2(1.0,
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 adv_inception_v3(num_classes=1000, in_chans=3, pretrained=False, **kwargs):
# my port of Tensorflow adversarially trained Inception V3 from
# http://download.tensorflow.org/models/adv_inception_v3_2017_08_18.tar.gz
default_cfg = default_cfgs['adv_inception_v3']
assert in_chans == 3
_assert_default_kwargs(kwargs)
model = Inception3(num_classes=num_classes, aux_logits=False, transform_input=False)
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
model.default_cfg = default_cfg
return model
def mobilenetv3_100(num_classes, in_chans=3, pretrained=False, **kwargs):
""" MobileNet V3 """
default_cfg = default_cfgs['mobilenetv3_100']
model = _gen_mobilenet_v3(1.0,
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 mnasnet_small(num_classes, in_chans=3, pretrained=False, **kwargs):
""" MNASNet Small, depth multiplier of 1.0. """
default_cfg = default_cfgs['mnasnet_small']
model = _gen_mnasnet_small(1.0,
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 semnasnet_140(num_classes, in_chans=3, pretrained=False, **kwargs):
""" MNASNet A1 (w/ SE), depth multiplier of 1.4. """
default_cfg = default_cfgs['semnasnet_140']
model = _gen_mnasnet_a1(1.4,
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 pnasnet5large(num_classes=1000, in_chans=3, pretrained='imagenet'):
r"""PNASNet-5 model architecture from the
`"Progressive Neural Architecture Search"
<https://arxiv.org/abs/1712.00559>`_ paper.
"""
default_cfg = default_cfgs['pnasnet5large']
model = PNASNet5Large(num_classes=1000, in_chans=in_chans)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def dpn107(num_classes=1000, in_chans=3, pretrained=False):
default_cfg = default_cfgs['dpn107_extra']
model = DPN(num_init_features=128,
k_r=200,
groups=50,
k_sec=(4, 8, 20, 3),
inc_sec=(20, 64, 64, 128),
num_classes=num_classes,
in_chans=in_chans)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def dpn131(num_classes=1000, in_chans=3, pretrained=False):
default_cfg = default_cfgs['dpn131']
model = DPN(num_init_features=128,
k_r=160,
groups=40,
k_sec=(4, 8, 28, 3),
inc_sec=(16, 32, 32, 128),
num_classes=num_classes,
in_chans=in_chans)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def dpn92(num_classes=1000, in_chans=3, pretrained=False):
default_cfg = default_cfgs['dpn92_extra']
model = DPN(num_init_features=64,
k_r=96,
groups=32,
k_sec=(3, 4, 20, 3),
inc_sec=(16, 32, 24, 128),
num_classes=num_classes,
in_chans=in_chans)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def fbnetc_100(num_classes, in_chans=3, pretrained=False, **kwargs):
""" FBNet-C """
default_cfg = default_cfgs['fbnetc_100']
if pretrained:
# pretrained model trained with non-default BN epsilon
kwargs['bn_eps'] = _BN_EPS_TF_DEFAULT
model = _gen_fbnetc(1.0,
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 tflite_semnasnet_100(num_classes, in_chans=3, pretrained=False, **kwargs):
""" MNASNet A1, depth multiplier of 1.0. """
default_cfg = default_cfgs['tflite_semnasnet_100']
# these two args are for compat with tflite pretrained weights
kwargs['folded_bn'] = True
kwargs['padding_same'] = True
model = _gen_mnasnet_a1(1.0,
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 dpn68(num_classes=1000, in_chans=3, pretrained=False):
default_cfg = default_cfgs['dpn68']
model = DPN(small=True,
num_init_features=10,
k_r=128,
groups=32,
k_sec=(3, 4, 12, 3),
inc_sec=(16, 32, 32, 64),
num_classes=num_classes,
in_chans=in_chans)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def gluon_resnet18_v1b(num_classes=1000,
in_chans=3,
pretrained=False,
**kwargs):
"""Constructs a ResNet-18 model.
"""
default_cfg = default_cfgs['gluon_resnet18_v1b']
model = GluonResNet(BasicBlockGl, [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 gluon_resnet101_v1b(num_classes=1000,
in_chans=3,
pretrained=False,
**kwargs):
"""Constructs a ResNet-101 model.
"""
default_cfg = default_cfgs['gluon_resnet101_v1b']
model = GluonResNet(BottleneckGl, [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 inception_resnet_v2(num_classes=1000,
in_chans=3,
pretrained=False,
**kwargs):
r"""InceptionResnetV2 model architecture from the
`"InceptionV4, Inception-ResNet..." <https://arxiv.org/abs/1602.07261>`_ paper.
"""
default_cfg = default_cfgs['inception_resnet_v2']
model = InceptionResnetV2(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 gluon_resnet152_v1s(num_classes=1000,
in_chans=3,
pretrained=False,
**kwargs):
"""Constructs a ResNet-152 model.
"""
default_cfg = default_cfgs['gluon_resnet152_v1s']
model = GluonResNet(BottleneckGl, [3, 8, 36, 3],
num_classes=num_classes,
in_chans=in_chans,
stem_width=64,
deep_stem=True,
**kwargs)
model.default_cfg = default_cfg
if pretrained:
load_pretrained(model, default_cfg, num_classes, in_chans)
return model
def gluon_resnext101_64x4d(num_classes=1000,
in_chans=3,
pretrained=False,
**kwargs):
"""Constructs a ResNeXt-101 model.
"""
default_cfg = default_cfgs['gluon_resnext101_64x4d']
model = GluonResNet(BottleneckGl, [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
