def mobilenetv2(self):
model = MobileNetV2()
model = ModuleHelper.load_model(model,
pretrained=self.configer.get(
'network', 'pretrained'),
all_match=False)
return model
def squeezenet(self):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
model = SqueezeNet()
model = ModuleHelper.load_model(model, pretrained=self.configer.get('network', 'pretrained'), all_match=False)
return model
def dfnetv2(pretrained=None):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
model = DFNetV2(num_classes=1000)
model = ModuleHelper.load_model(model, pretrained=pretrained, all_match=False)
return model
def vgg(self, vgg_cfg=None):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
backbone = self.configer.get('network', 'backbone')
model = VGG(cfg_name=backbone, vgg_cfg=vgg_cfg, bn=False)
model = ModuleHelper.load_model(model, pretrained=self.configer.get('network', 'pretrained'), all_match=False)
return model
def densenet161(self, pretrained=None, **kwargs):
r"""Densenet-161 model from
`"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`_
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = DenseNet(num_init_features=96, growth_rate=48,
block_config=(6, 12, 36, 24), norm_type=self.configer.get('network', 'norm_type'), **kwargs)
model = ModuleHelper.load_model(model, pretrained=pretrained)
return model
def vgg(self, backbone=None, pretrained=None):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
model = VGG(cfg_name=backbone, bn=False)
model = ModuleHelper.load_model(model,
pretrained=pretrained,
all_match=False)
return model
def mobilenetv2_dilated8(self, pretrained=None):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
model = MobileNetV2Dilated8()
model = ModuleHelper.load_model(model,
pretrained=pretrained,
all_match=False)
return model
def squeezenet(self, pretrained=None):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
model = SqueezeNet()
model = ModuleHelper.load_model(model,
pretrained=pretrained,
all_match=False)
return model
def deepbase_resnet101(self, **kwargs):
"""Constructs a ResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
model = ResNet(Bottleneck, [3, 4, 23, 3],
deep_base=True,
norm_type=self.configer.get('network', 'norm_type'),
**kwargs)
model = ModuleHelper.load_model(model,
pretrained=self.configer.get(
'network', 'pretrained'))
return model
def resnet34(self, **kwargs):
"""Constructs a ResNet-34 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
model = ResNet(BasicBlock, [3, 4, 6, 3],
deep_base=False,
norm_type=self.configer.get('network', 'norm_type'),
**kwargs)
model = ModuleHelper.load_model(model,
pretrained=self.configer.get(
'network', 'pretrained'))
return model
def deepbase_resnet101(num_classes=1000,
pretrained=None,
norm_type='batchnorm',
**kwargs):
"""Constructs a ResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
model = ResNet(Bottleneck, [3, 4, 23, 3],
num_classes=num_classes,
deep_base=True,
norm_type=norm_type)
model = ModuleHelper.load_model(model, pretrained=pretrained)
return model
def resnet34(num_classes=1000,
pretrained=None,
norm_type='batchnorm',
**kwargs):
"""Constructs a ResNet-34 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
model = ResNet(BasicBlock, [3, 4, 6, 3],
num_classes=num_classes,
deep_base=False,
norm_type=norm_type)
model = ModuleHelper.load_model(model, pretrained=pretrained)
return model
def deepbase_resnet18(num_classes=1000,
pretrained=None,
norm_type='batchnorm',
**kwargs):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on Places
"""
model = ResNet(BasicBlock, [2, 2, 2, 2],
num_classes=num_classes,
deep_base=True,
norm_type=norm_type)
model = ModuleHelper.load_model(model,
all_match=False,
pretrained=pretrained)
return model
def _shufflenetv2(arch, pretrained, progress, *args, **kwargs):
model = ShuffleNetV2(*args, **kwargs)
model = ModuleHelper.load_model(model, pretrained=pretrained)
return model
def squeezenet_dilated8(self, pretrained):
model = DilatedSqueezeNet()
model = ModuleHelper.load_model(model,
pretrained=pretrained,
all_match=False)
return model
def mobilenetv2(self, pretrained=None):
model = MobileNetV2()
model = ModuleHelper.load_model(model,
pretrained=pretrained,
all_match=False)
return model
def vgg_bn(self, vgg_cfg=None):
backbone = self.configer.get('network', 'backbone')
model = VGG(cfg_name=backbone, vgg_cfg=vgg_cfg, bn=True)
model = ModuleHelper.load_model(model, pretrained=self.configer.get('network', 'pretrained'), all_match=False)
return model
def dfnetv1(pretrained=None):
model = DFNetV1(num_classes=1000)
model = ModuleHelper.load_model(model, pretrained=pretrained, all_match=False)
return model
def darknet53(self, pretrained=None):
"""Constructs a darknet-53 model.
"""
model = DarkNet([1, 2, 8, 8, 4])
model = ModuleHelper.load_model(model, pretrained=pretrained, all_match=False)
return model
def darknet53(self):
"""Constructs a darknet-53 model.
"""
model = DarkNet([1, 2, 8, 8, 4])
model = ModuleHelper.load_model(model, pretrained=self.configer.get('network', 'pretrained'), all_match=False)
return model
def vgg_bn(self, backbone=None, pretrained=None):
model = VGG(cfg_name=backbone, bn=True)
model = ModuleHelper.load_model(model,
pretrained=pretrained,
all_match=False)
return model
def squeezenet_dilated8(self):
model = DilatedSqueezeNet()
model = ModuleHelper.load_model(model, pretrained=self.configer.get('network', 'pretrained'), all_match=False)
return model
