Trait opencv::prelude::ANN_MLPConst

source ·

pub trait ANN_MLPConst: StatModelConst {
Show 16 methods
    fn as_raw_ANN_MLP(&self) -> *const c_void;

    fn get_train_method(&self) -> Result<i32> { ... }
    fn get_layer_sizes(&self) -> Result<Mat> { ... }
    fn get_term_criteria(&self) -> Result<TermCriteria> { ... }
    fn get_backprop_weight_scale(&self) -> Result<f64> { ... }
    fn get_backprop_momentum_scale(&self) -> Result<f64> { ... }
    fn get_rprop_dw0(&self) -> Result<f64> { ... }
    fn get_rprop_dw_plus(&self) -> Result<f64> { ... }
    fn get_rprop_dw_minus(&self) -> Result<f64> { ... }
    fn get_rprop_dw_min(&self) -> Result<f64> { ... }
    fn get_rprop_dw_max(&self) -> Result<f64> { ... }
    fn get_anneal_initial_t(&self) -> Result<f64> { ... }
    fn get_anneal_final_t(&self) -> Result<f64> { ... }
    fn get_anneal_cooling_ratio(&self) -> Result<f64> { ... }
    fn get_anneal_ite_per_step(&self) -> Result<i32> { ... }
    fn get_weights(&self, layer_idx: i32) -> Result<Mat> { ... }
}

Expand description

Artificial Neural Networks - Multi-Layer Perceptrons.

Unlike many other models in ML that are constructed and trained at once, in the MLP model these steps are separated. First, a network with the specified topology is created using the non-default constructor or the method ANN_MLP::create. All the weights are set to zeros. Then, the network is trained using a set of input and output vectors. The training procedure can be repeated more than once, that is, the weights can be adjusted based on the new training data.

Additional flags for StatModel::train are available: ANN_MLP::TrainFlags.

Required Methods

source

fn as_raw_ANN_MLP(&self) -> *const c_void

Provided Methods

source

fn get_train_method(&self) -> Result<i32>

Returns current training method

source

fn get_layer_sizes(&self) -> Result<Mat>

Integer vector specifying the number of neurons in each layer including the input and output layers. The very first element specifies the number of elements in the input layer. The last element - number of elements in the output layer.

fn get_term_criteria(&self) -> Result<TermCriteria>

Termination criteria of the training algorithm. You can specify the maximum number of iterations (maxCount) and/or how much the error could change between the iterations to make the algorithm continue (epsilon). Default value is TermCriteria(TermCriteria::MAX_ITER + TermCriteria::EPS, 1000, 0.01).

fn get_backprop_weight_scale(&self) -> Result<f64>

BPROP: Strength of the weight gradient term. The recommended value is about 0.1. Default value is 0.1.

fn get_backprop_momentum_scale(&self) -> Result<f64>

BPROP: 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 value is 0.1.