LibtorchANNSurrogate

Surrogate that evaluates a feedforward artificial neural net.

Overview

The details of a simple feedforward neural network is discussed in LibtorchArtificialNeuralNet. This class is dedicated to evaluating the following function:

(1)var element = document.getElementById("moose-equation-35743dc9-5d42-43f3-84ec-21c1b5b433cf");katex.render("\\textbf{y} = \\sigma(\\textbf{W}^{(n)}\\sigma(\\textbf{W}^{(n-1)} \\sigma( ... \\sigma(\\textbf{W}^{(1)}\\textbf{x}+\\textbf{b}^{(1)}) ... )+\\textbf{b}^{(n-1)})+\\textbf{b}^{(n)}),", element, {displayMode:true,throwOnError:false,macros:{"\\eqc":"\\,,","\\eqp":"\\,.","\\pd":"\\frac{\\partial #1}{\\partial #2}","\\pr":"\\left(#1\\right)","\\ddt":"\\frac{d #1}{d t}"}});

which describes a neural network of $var element = document.getElementById("moose-equation-42f4019d-4b8d-4203-baac-a3c1a66bb2eb");katex.render("n", element, {displayMode:false,throwOnError:false,macros:{"\\eqc":"\\,,","\\eqp":"\\,.","\\pd":"\\frac{\\partial #1}{\\partial #2}","\\pr":"\\left(#1\\right)","\\ddt":"\\frac{d #1}{d t}"}});$ layers. In this context, $var element = document.getElementById("moose-equation-6843ebf2-5696-4fe6-abf4-9dd94de4bf4a");katex.render("\\sigma", element, {displayMode:false,throwOnError:false,macros:{"\\eqc":"\\,,","\\eqp":"\\,.","\\pd":"\\frac{\\partial #1}{\\partial #2}","\\pr":"\\left(#1\\right)","\\ddt":"\\frac{d #1}{d t}"}});$ denotes an activation function, while $var element = document.getElementById("moose-equation-9c8713cf-fb42-4371-9293-4492b0064c2d");katex.render("\\textbf{x}", element, {displayMode:false,throwOnError:false,macros:{"\\eqc":"\\,,","\\eqp":"\\,.","\\pd":"\\frac{\\partial #1}{\\partial #2}","\\pr":"\\left(#1\\right)","\\ddt":"\\frac{d #1}{d t}"}});$ and $var element = document.getElementById("moose-equation-936048ea-0c5b-4527-9d47-d6883bbaa04f");katex.render("\\textbf{y}", element, {displayMode:false,throwOnError:false,macros:{"\\eqc":"\\,,","\\eqp":"\\,.","\\pd":"\\frac{\\partial #1}{\\partial #2}","\\pr":"\\left(#1\\right)","\\ddt":"\\frac{d #1}{d t}"}});$ are the input and output arguments. respectively. The weight matrices ( $var element = document.getElementById("moose-equation-0670e6a0-0033-4b4d-bdef-11d649eff7ef");katex.render("\\textbf{W}", element, {displayMode:false,throwOnError:false,macros:{"\\eqc":"\\,,","\\eqp":"\\,.","\\pd":"\\frac{\\partial #1}{\\partial #2}","\\pr":"\\left(#1\\right)","\\ddt":"\\frac{d #1}{d t}"}});$ ) and bias vectors ( $var element = document.getElementById("moose-equation-5f1f485e-b09a-4755-852d-8dadf5878470");katex.render("\\textbf{b}", element, {displayMode:false,throwOnError:false,macros:{"\\eqc":"\\,,","\\eqp":"\\,.","\\pd":"\\frac{\\partial #1}{\\partial #2}","\\pr":"\\left(#1\\right)","\\ddt":"\\frac{d #1}{d t}"}});$ ) are optimized by LibtorchANNTrainer and are fixed in the evaluation phase.

Example Input File Syntax

Let us consider an example where we evaluate the neural network trained here. For this, prepare another set of samples of from the same parameter space:

[Samplers]
  [test]
    type = CartesianProduct
    linear_space_items = '0 0.05 2
                          0 0.05 2
                          0 0.05 2'
  []
[]

Following this, we load the surrogate from a file saved by the trainer:

[Surrogates]
  [surr]
    type = LibtorchANNSurrogate
    filename = 'train_out_train.rd'
  []
[]

And evaluate it using a reporter which uses the samples and the surrogate to compute the approximate values of the target function at the new sample points:

[Reporters]
  [results]
    type = EvaluateSurrogate
    model = surr
    sampler = test
    execute_on = FINAL
    parallel_type = ROOT
  []
[]

Input Parameters

filenameFilename containing the trained data.
C++ Type:FileName
Controllable:No
Description:Filename containing the trained data.
trainerThe SurrogateTrainer object. If this is specified the trainer data is automatically gathered and available in this SurrogateModel object.
C++ Type:UserObjectName
Controllable:No
Description:The SurrogateTrainer object. If this is specified the trainer data is automatically gathered and available in this SurrogateModel object.

Optional Parameters

control_tagsAdds user-defined labels for accessing object parameters via control logic.
C++ Type:std::vector<std::string>
Controllable:No
Description:Adds user-defined labels for accessing object parameters via control logic.
enableTrueSet the enabled status of the MooseObject.
Default:True
C++ Type:bool
Controllable:No
Description:Set the enabled status of the MooseObject.

Advanced Parameters

Input Files

(modules/stochastic_tools/test/tests/surrogates/libtorch_nn/train_and_evaluate.i)
(modules/stochastic_tools/test/tests/surrogates/libtorch_nn/retrain.i)
(modules/stochastic_tools/test/tests/surrogates/libtorch_nn/evaluate.i)

(modules/stochastic_tools/test/tests/surrogates/libtorch_nn/evaluate.i)

[StochasticTools]
[]

[Samplers]
  [test]
    type = CartesianProduct
    linear_space_items = '0 0.05 2
                          0 0.05 2
                          0 0.05 2'
  []
[]

[Surrogates]
  [surr]
    type = LibtorchANNSurrogate
    filename = 'train_out_train.rd'
  []
[]

[Reporters]
  [results]
    type = EvaluateSurrogate
    model = surr
    sampler = test
    execute_on = FINAL
    parallel_type = ROOT
  []
[]

[Outputs]
  csv = true
  execute_on = FINAL
[]

(modules/stochastic_tools/test/tests/surrogates/libtorch_nn/evaluate.i)

[StochasticTools]
[]

[Samplers]
  [test]
    type = CartesianProduct
    linear_space_items = '0 0.05 2
                          0 0.05 2
                          0 0.05 2'
  []
[]

[Surrogates]
  [surr]
    type = LibtorchANNSurrogate
    filename = 'train_out_train.rd'
  []
[]

[Reporters]
  [results]
    type = EvaluateSurrogate
    model = surr
    sampler = test
    execute_on = FINAL
    parallel_type = ROOT
  []
[]

[Outputs]
  csv = true
  execute_on = FINAL
[]

(modules/stochastic_tools/test/tests/surrogates/libtorch_nn/evaluate.i)

[StochasticTools]
[]

[Samplers]
  [test]
    type = CartesianProduct
    linear_space_items = '0 0.05 2
                          0 0.05 2
                          0 0.05 2'
  []
[]

[Surrogates]
  [surr]
    type = LibtorchANNSurrogate
    filename = 'train_out_train.rd'
  []
[]

[Reporters]
  [results]
    type = EvaluateSurrogate
    model = surr
    sampler = test
    execute_on = FINAL
    parallel_type = ROOT
  []
[]

[Outputs]
  csv = true
  execute_on = FINAL
[]

(modules/stochastic_tools/test/tests/surrogates/libtorch_nn/train_and_evaluate.i)

[StochasticTools]
[]

[Samplers]
  [sample]
    type = CartesianProduct
    linear_space_items = '0 0.0125 5
                          0 0.0125 5
                          0 0.0125 5'
  []
  [test]
    type = CartesianProduct
    linear_space_items = '0 0.05 2
                          0 0.05 2
                          0 0.05 2'
  []
[]

[VectorPostprocessors]
  [values]
    type = GFunction
    sampler = sample
    q_vector = '0 0 0'
    execute_on = INITIAL
    outputs = none
  []
[]

[Trainers]
  [train]
    type = LibtorchANNTrainer
    sampler = sample
    response = values/g_values
    num_epochs = 40
    num_batches = 10
    num_neurons_per_layer = '64 32'
    learning_rate = 0.001
    filename = mynet_tne.pt
    read_from_file = false
    print_epoch_loss = 10
  []
[]

[Surrogates]
  [surr]
    type = LibtorchANNSurrogate
    trainer = train
  []
[]

[Reporters]
  [results]
    type = EvaluateSurrogate
    model = surr
    sampler = test
    execute_on = FINAL
    parallel_type = ROOT
  []
[]

[Outputs]
  csv = true
  execute_on = FINAL
[]

(modules/stochastic_tools/test/tests/surrogates/libtorch_nn/retrain.i)

[StochasticTools]
[]

[Samplers]
  [train_sample]
    type = CartesianProduct
    linear_space_items = '0 0.0125 5
                          0 0.0125 5
                          0 0.0125 5'
  []
  [test_sample]
    type = CartesianProduct
    linear_space_items = '0 0.05 2
                          0 0.05 2
                          0 0.05 2'
  []
[]

[VectorPostprocessors]
  [values]
    type = GFunction
    sampler = train_sample
    q_vector = '0 0 0'
    execute_on = INITIAL
    outputs = none
  []
[]

[Trainers]
  [train]
    type = LibtorchANNTrainer
    sampler = train_sample
    response = values/g_values
    num_epochs = 40
    num_batches = 10
    num_neurons_per_layer = '64 32'
    learning_rate = 0.001
    filename = mynet.pt
    read_from_file = false
    print_epoch_loss = 10
  []
[]

[Surrogates]
  [surr]
    type = LibtorchANNSurrogate
    trainer = train
  []
[]

[Reporters]
  [results]
    type = EvaluateSurrogate
    model = surr
    sampler = test_sample
    execute_on = FINAL
    parallel_type = ROOT
  []
[]

[Outputs]
  csv=true
  execute_on = FINAL
[]

(modules/stochastic_tools/test/tests/surrogates/libtorch_nn/evaluate.i)

[StochasticTools]
[]

[Samplers]
  [test]
    type = CartesianProduct
    linear_space_items = '0 0.05 2
                          0 0.05 2
                          0 0.05 2'
  []
[]

[Surrogates]
  [surr]
    type = LibtorchANNSurrogate
    filename = 'train_out_train.rd'
  []
[]

[Reporters]
  [results]
    type = EvaluateSurrogate
    model = surr
    sampler = test
    execute_on = FINAL
    parallel_type = ROOT
  []
[]

[Outputs]
  csv = true
  execute_on = FINAL
[]

Overview
Example Input File Syntax
Input Parameters
Input Files

Install MOOSE

New Users

Examples and Tutorials

Application Usage

Physics and Syntax

Application Development

Framework Development

MOOSEDocs

Infrastructure

Questions

Information and Tools

INL Applications and Remote Access

LibtorchANNSurrogate

Overview

Example Input File Syntax

Input Parameters

Optional Parameters

Advanced Parameters

Input Files