ImageToImageNetwork class
Image-to-Image neural network process object.
Contents
This class is a convenience class for a neural network which performs image to image transformation by having 1 input image, and outputs 1 image. Internally it uses TensorToImage. If you need multi-input or multi-output support, use NeuralNetwork with TensorToImage instead.
Base classes
- class NeuralNetwork
- Neural network process object.
Public types
- enum class Normalization { CLIP_0_1 = 0, CLIP_0_SQUEEZE, NONE }
- Normalization method of image after each iteration.
Public functions
- auto create(std::string modelFilename, float scaleFactor, int iterations, bool residualNetwork, bool resizeBackToOriginalSize, bool castBackToOriginalType, std::vector<int> channelsToExtract, Normalization normalization, float meanIntensity, float standardDeviationIntensity, std::vector<NeuralNetworkNode> inputNodes, std::vector<NeuralNetworkNode> outputNodes, std::string inferenceEngine, std::vector<std::string> customPlugins) -> std::shared_ptr<ImageToImageNetwork>
- Create instance.
- auto create(std::string modelFilename, std::vector<NeuralNetworkNode> inputNodes, std::vector<NeuralNetworkNode> outputNodes, std::string inferenceEngine, std::vector<std::string> customPlugins) -> std::shared_ptr<ImageToImageNetwork>
- Create instance C++ friendly create with parameters that must be set before loading.
- void loadAttributes() virtual
- void setIterations(int iterations)
- auto getIterations() const -> int
- void setResidualNetwork(bool residual)
- void setResizeOutput(bool resizeOutput)
- void setCastOutput(bool castOutput)
- void setChannels(std::vector<int> channels)
- void setNormalization(Normalization norm)
- Specify normalization to be performed after each iteration.
- void setDisabled(bool disabled)
- Set disabled state When disabled, this PO will just forward the input image instead of processing it.
- auto isDisabled() const -> bool
- Check if disabled.
Private functions
- void execute() virtual
Enum documentation
enum class fast::
Normalization method of image after each iteration.
| Enumerators | |
|---|---|
| CLIP_0_1 |
Clip image intensities at 0 and 1 |
| CLIP_0_SQUEEZE |
Clip image intensities at 0 and squeeze intensity range if max is above 1.0 |
| NONE |
No normalization |
Function documentation
std::shared_ptr<ImageToImageNetwork> fast::
Create instance.
| Parameters | |
|---|---|
| modelFilename | path to model to load |
| scaleFactor | A value which is multiplied with each pixel of input image before it is sent to the neural network. Use this to scale your pixels values. Default: 1.0 |
| iterations | Number of iterations to run the network |
| residualNetwork | Whether this image-to-image network is a residual network. If true, the output is added to the input image to create the final output image. |
| resizeBackToOriginalSize | Whether to resize the output image to its original input image size |
| castBackToOriginalType | Whether to cast the output image to its input image type |
| channelsToExtract | Which channels to extract from the output tensor. Default (empty list) is to extract all channels. |
| normalization | |
| meanIntensity | Mean intensity to subtract from each pixel of the input image |
| standardDeviationIntensity | Standard deviation to divide each pixel of the input image by |
| inputNodes | Specify names, and potentially shapes, of input nodes. Not necessary unless you only want to use certain inputs or specify the input shape manually. |
| outputNodes | Specify names, and potentially shapes, of output nodes to use. Not necessary unless you only want to use certain outputs or specify the output shape manually. |
| inferenceEngine | Specify which inference engine to use (TensorFlow, TensorRT, OpenVINO). By default, FAST will select the best inference engine available on your system. |
| customPlugins | Specify path to any custom plugins/operators to load |
| Returns | instance |
std::shared_ptr<ImageToImageNetwork> fast::
Create instance C++ friendly create with parameters that must be set before loading.
| Parameters | |
|---|---|
| modelFilename | Path to model to load |
| inputNodes | Specify names, and potentially shapes, of input nodes. Not necessary unless you only want to use certain inputs or specify the input shape manually. |
| outputNodes | Specify names, and potentially shapes, of output nodes to use. Not necessary unless you only want to use certain outputs or specify the output shape manually. |
| inferenceEngine | Specify which inference engine to use (TensorFlow, TensorRT, OpenVINO). By default, FAST will select the best inference engine available on your system. |
| customPlugins | Specify path to any custom plugins/operators to load |
| Returns | instance |
void fast::
Specify normalization to be performed after each iteration.
| Parameters | |
|---|---|
| norm | |
void fast::
Set disabled state When disabled, this PO will just forward the input image instead of processing it.
| Parameters | |
|---|---|
| disabled | |
bool fast::
Check if disabled.