bob.ip.binseg.models.backbones.vgg¶
Functions
|
VGG 16-layer model (configuration “D”) with batch normalization “Very Deep Convolutional Networks For Large-Scale Image Recognition” |
|
VGG 16-layer model (configuration “D”) “Very Deep Convolutional Networks For Large-Scale Image Recognition” |
Classes
|
Adaptation of base VGG functionality to U-Net style segmentation |
-
class
bob.ip.binseg.models.backbones.vgg.VGG4Segmentation(*args, **kwargs)[source]¶ Bases:
torchvision.models.vgg.VGGAdaptation of base VGG functionality to U-Net style segmentation
This version of VGG is slightly modified so it can be used through torchvision’s API. It outputs intermediate features which are normally not output by the base VGG implementation, but are required for segmentation operations.
- Parameters
return_features (
list, Optional) – A list of integers indicating the feature layers to be returned from the original module.
-
forward(x)[source]¶ Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Moduleinstance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
-
bob.ip.binseg.models.backbones.vgg.vgg16_for_segmentation(pretrained=False, progress=True, **kwargs)[source]¶ VGG 16-layer model (configuration “D”) “Very Deep Convolutional Networks For Large-Scale Image Recognition”
-
bob.ip.binseg.models.backbones.vgg.vgg16_bn_for_segmentation(pretrained=False, progress=True, **kwargs)[source]¶ VGG 16-layer model (configuration “D”) with batch normalization “Very Deep Convolutional Networks For Large-Scale Image Recognition”