Tool [deprecated] Neural Networks (OpenCV)
Integration of the OpenCV Neural Networks library.
http://docs.opencv.org/modules/ml/doc/neural_networks.html
- Author: Luca Piras
- Menu: Imagery|Classification
Parameters
Name | Type | Identifier | Description | Constraints | |
---|---|---|---|---|---|
Input | Train INPUT | Table (input) | TRAIN_INPUT_TABLE | Input data to train the network. | - |
Prediction INPUT | Table (input) | EVAL_INPUT_TABLE | Input data for the trained network. | - | |
Train INPUT | Grid list (input) | TRAIN_INPUT_GRIDS | Input grids to train the network. | - | |
Select training areas | Shapes (input) | TRAIN_INPUT_AREAS | The areas used to train the neural network. | - | |
Sample weights (*) | Table (optional input) | WEIGHTS | Optional floating-point vector of weights for each sample. Some samples may be more important than others for training. | - | |
Indices (*) | Table (optional input) | INDICES | Optional integer vector indicating the samples (rows of inputs and outputs) that are taken into account. | - | |
Output | OUTPUT | Table (output) | EVAL_OUTPUT_TABLE | Predicted responses (probabilities) for corresponding samples. | - |
OUTPUT classes | Grid (output) | EVAL_OUTPUT_GRID_CLASSES | These are the winner class vectors. | - | |
OUTPUT certainty (*) | Grid (optional output) | EVAL_OUTPUT_GRID_CERTAINTY | These are the probabilities for the winner classes given by the neural network. | - | |
Options | Grid system | Grid system | PARAMETERS_GRID_SYSTEM | - | - |
Select training output features | Parameters | TRAIN_FEATURES_TABLE | Select the features that should be used as the OUTPUT features. | 0 Parameters: | |
Select class identifier | Table field | TRAIN_INPUT_AREAS_CLASS_FIELD | The class field used to classify the shape. All classes will be vectorized. | - | |
Data type | Choice | DATA_TYPE | Choose the type of data used in this model. | Available Choices: [0] Table [1] Grid Default: 0 | |
Number of layers | Integer | NNET_LAYER | You can specify the number of layers in the network (including input and output layer). | Minimum: 1 Default: 3 | |
Number of neurons | Integer | NNET_NEURONS | You can specify the number of neurons in each layer of the network. | Minimum: 1 Default: 3 | |
Maximum number of iterations | Integer | MAX_ITER | Termination criteria of the training algorithm. You can specify the maximum number of iterations. | Default: 1000 | |
Error change (epsilon) | Floating point | EPSILON | Termination criteria of the training algorithm. You can specify how much the error could change between the iterations to make the algorithm continue (epsilon). | Default: 0.010000 | |
Activation function | Choice | ACTIVATION_FUNCTION | Choose the activation function used by the neronal network. | Available Choices: [0] Identity [1] Sigmoid [2] Gaussian Default: 1 | |
Alpha | Floating point | ALPHA | This is the alpha parameter value for the sigmoid function. | Default: 1.000000 | |
Beta | Floating point | BETA | This is the beta parameter value for the sigmoid function. | Default: 1.000000 | |
Training method | Choice | TRAINING_METHOD | Choose the training method used for the neronal network. | Available Choices: [0] Resilent propagation (RPROP) [1] Backpropagation algorithm Default: 1 | |
Initial update value | Floating point | RP_DW0 | Initial value delta_0 of update-values delta_ij. | Default: 0.000000 | |
Increase factor | Floating point | RP_DW_PLUS | Increase factor n_plus. Must be > 1. | Minimum: 1.010000 Default: 1.200000 | |
Decrease factor | Floating point | RP_DW_MINUS | Decrease factor n_minus. Must be < 1. | Minimum: 0.010000 Maximum: 0.990000 Default: 0.500000 | |
Update values lower limit | Floating point | RP_DW_MIN | Corresponds to delta_min. Must be > 0 | Minimum: 0.010000 Default: 0.100000 | |
Update values upper limit | Floating point | RP_DW_MAX | Corresponds to delta_max. Must be > 1 | Minimum: 1.010000 Default: 1.100000 | |
Weight gradient term | Floating point | BP_DW_SCALE | Strength of the weight gradient term. The recommended value is about 0.1. | Default: 0.100000 | |
Moment term | Floating point | BP_MOMENT_SCALE | Strength of the momentum term (the difference between weights on the 2 previous iterations). This parameter provides some inertia to smooth the random fluctuations of the weights. It can vary from 0 (the feature is disabled) to 1 and beyond. The value 0.1 or so is good enough. | Default: 0.100000 | |
Update the network weights | Boolean | UPDATE_WEIGHTS | - | Default: 0 | |
No INPUT vector normalization | Boolean | NO_INPUT_SCALE | If false, the training algorithm normalizes each input feature independently, shifting its mean value to 0 and making the standard deviation equal to 1. | Default: 1 | |
No OUTPUT vector normalization | Boolean | NO_OUTPUT_SCALE | If false, the training algorithm normalizes each output feature independently, by transforming it to the certain range depending on the used activation function. | Default: 1 | |
(*) optional |
Command-line
Usage: saga_cmd imagery_opencv 3 [-TRAIN_INPUT_TABLE <str>] [-EVAL_INPUT_TABLE <str>] [-EVAL_OUTPUT_TABLE <str>] [-TRAIN_INPUT_GRIDS <str>] [-TRAIN_INPUT_AREAS <str>] [-TRAIN_INPUT_AREAS_CLASS_FIELD <str>] [-EVAL_OUTPUT_GRID_CLASSES <str>] [-EVAL_OUTPUT_GRID_CERTAINTY <str>] [-DATA_TYPE <str>] [-NNET_LAYER <num>] [-NNET_NEURONS <num>] [-MAX_ITER <num>] [-EPSILON <double>] [-ACTIVATION_FUNCTION <str>] [-ALPHA <double>] [-BETA <double>] [-TRAINING_METHOD <str>] [-RP_DW0 <double>] [-RP_DW_PLUS <double>] [-RP_DW_MINUS <double>] [-RP_DW_MIN <double>] [-RP_DW_MAX <double>] [-BP_DW_SCALE <double>] [-BP_MOMENT_SCALE <double>] [-WEIGHTS <str>] [-INDICES <str>] [-UPDATE_WEIGHTS <str>] [-NO_INPUT_SCALE <str>] [-NO_OUTPUT_SCALE <str>] -TRAIN_INPUT_TABLE:<str> Train INPUT Table (input) -EVAL_INPUT_TABLE:<str> Prediction INPUT Table (input) -EVAL_OUTPUT_TABLE:<str> OUTPUT Table (output) -TRAIN_INPUT_GRIDS:<str> Train INPUT Grid list (input) -TRAIN_INPUT_AREAS:<str> Select training areas Shapes (input) -TRAIN_INPUT_AREAS_CLASS_FIELD:<str> Select class identifier Table field -EVAL_OUTPUT_GRID_CLASSES:<str> OUTPUT classes Grid (output) -EVAL_OUTPUT_GRID_CERTAINTY:<str> OUTPUT certainty Grid (optional output) -DATA_TYPE:<str> Data type Choice Available Choices: [0] Table [1] Grid Default: 0 -NNET_LAYER:<num> Number of layers Integer Minimum: 1 Default: 3 -NNET_NEURONS:<num> Number of neurons Integer Minimum: 1 Default: 3 -MAX_ITER:<num> Maximum number of iterations Integer Default: 1000 -EPSILON:<double> Error change (epsilon) Floating point Default: 0.010000 -ACTIVATION_FUNCTION:<str> Activation function Choice Available Choices: [0] Identity [1] Sigmoid [2] Gaussian Default: 1 -ALPHA:<double> Alpha Floating point Default: 1.000000 -BETA:<double> Beta Floating point Default: 1.000000 -TRAINING_METHOD:<str> Training method Choice Available Choices: [0] Resilent propagation (RPROP) [1] Backpropagation algorithm Default: 1 -RP_DW0:<double> Initial update value Floating point Default: 0.000000 -RP_DW_PLUS:<double> Increase factor Floating point Minimum: 1.010000 Default: 1.200000 -RP_DW_MINUS:<double> Decrease factor Floating point Minimum: 0.010000 Maximum: 0.990000 Default: 0.500000 -RP_DW_MIN:<double> Update values lower limit Floating point Minimum: 0.010000 Default: 0.100000 -RP_DW_MAX:<double> Update values upper limit Floating point Minimum: 1.010000 Default: 1.100000 -BP_DW_SCALE:<double> Weight gradient term Floating point Default: 0.100000 -BP_MOMENT_SCALE:<double> Moment term Floating point Default: 0.100000 -WEIGHTS:<str> Sample weights Table (optional input) -INDICES:<str> Indices Table (optional input) -UPDATE_WEIGHTS:<str> Update the network weights Boolean Default: 0 -NO_INPUT_SCALE:<str> No INPUT vector normalization Boolean Default: 1 -NO_OUTPUT_SCALE:<str> No OUTPUT vector normalization Boolean Default: 1