deepdraw.models.driu#
Functions
|
Builds DRIU for vessel segmentation by adding backbone and head together. |
Classes
Takes in four feature maps with 16 channels each, concatenates them and applies a 1x1 convolution with 1 output channel. |
|
|
DRIU head module. |
- class deepdraw.models.driu.ConcatFuseBlock[source]#
Bases:
Module
Takes in four feature maps with 16 channels each, concatenates them and applies a 1x1 convolution with 1 output channel.
- forward(x1, x2, x3, x4)[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
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
- class deepdraw.models.driu.DRIU(in_channels_list=None)[source]#
Bases:
Module
DRIU head module.
Based on paper by [MANINIS-2016].
- Parameters:
in_channels_list (list) – number of channels for each feature map that is returned from backbone
- forward(x)[source]#
- Parameters:
x (list) – list of tensors as returned from the backbone network. First element: height and width of input image. Remaining elements: feature maps for each feature level.
- Returns:
tensor (
torch.Tensor
)
- deepdraw.models.driu.driu(pretrained_backbone=True, progress=True)[source]#
Builds DRIU for vessel segmentation by adding backbone and head together.
- Parameters:
pretrained_backbone (
bool
, Optional) – If set toTrue
, then loads a pre-trained version of the backbone (not the head) for the DRIU network using VGG-16 trained for ImageNet classification.progress (
bool
, Optional) – If set toTrue
, and you decided to use apretrained_backbone
, then, shows a progress bar of the backbone model downloading if download is necesssary.
- Returns:
module (
torch.nn.Module
) – Network model for DRIU (vessel segmentation)