TensorToSegmentation class
A process object which converts a Tensor to a Segmentation object.
Contents
Base classes
- class ProcessObject
- Abstract base class for all process objects.
Public functions
- auto create(float threshold, bool hasBackgroundClass, std::vector<int> channelsToIgnore) -> std::shared_ptr<TensorToSegmentation>
- Create instance.
- auto getThreshold() const -> float
- void setBackgroundClass(bool hasBackgroundClass)
- void setChannelsToIgnore(std::vector<int> channels)
- Specify list of output channels to ignore.
- void loadAttributes() virtual
Protected functions
- void execute() override
Protected variables
- float m_threshold
- bool m_hasBackgroundClass
- std::set<int> m_channelsToIgnore
Function documentation
std::shared_ptr<TensorToSegmentation> fast::
Create instance.
| Parameters | |
|---|---|
| threshold | |
| hasBackgroundClass | Whether the neural network has a channel 0 which represents the "background". Default: true |
| channelsToIgnore | List of output channels to ignore |
| Returns | instance Threshold to accept a channel X as being class X. |
void fast::
| Parameters | |
|---|---|
| hasBackgroundClass | |
Set whether channel 0 of segmentation tensor is the "background" class, thereby getting the label 0 in the resulting Segmentation.
void fast::
Specify list of output channels to ignore.
| Parameters | |
|---|---|
| channels | |