mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double Class Reference

Test Fixture - layer of input size 4x4x1 and with filter bank of 3 filters of size 1x1 with stride 3, double. Math example taken from my own calculations;) More...

#include <Convolution_tests.hpp>

Inheritance diagram for mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double:

Collaboration diagram for mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double:

Public Member Functions
	Conv4x4x1Filter3x1x1s3Double ()

Protected Member Functions
virtual void	SetUp ()

Private Attributes
mic::mlnn::convolution::Convolution < double >	layer
	Object to be tested. More...
mic::neural_nets::loss::SquaredErrorLoss < double >	loss
mic::types::MatrixPtr< double >	x
	Test x - used in forward pass. More...
mic::types::MatrixPtr< double >	desired_y
	Desired output for a given x. More...
mic::types::MatrixPtr< double >	dy
	Gradient passed to backpropagation. More...
mic::types::MatrixPtr< double >	desired_dx
	Target y values. More...
mic::types::MatrixPtr< double >	desired_dW
	Desired gradient dW from backpropagation. More...
mic::types::MatrixPtr< double >	desired_db
	Desired gradient db from backpropagation. More...

Detailed Description

Test Fixture - layer of input size 4x4x1 and with filter bank of 3 filters of size 1x1 with stride 3, double. Math example taken from my own calculations;)

Author

tkornuta

Definition at line 239 of file Convolution_tests.hpp.

Constructor & Destructor Documentation

mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double::Conv4x4x1Filter3x1x1s3Double ( )

inline

Definition at line 242 of file Convolution_tests.hpp.

References desired_db, desired_dW, desired_dx, desired_y, dy, and x.

Member Function Documentation

virtual void mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double::SetUp ( )

inlineprotectedvirtual

Definition at line 261 of file Convolution_tests.hpp.

References layer, and mic::mlnn::Layer< eT >::p.

Member Data Documentation

mic::types::MatrixPtr<double> mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double::desired_db

private

Desired gradient db from backpropagation.

Definition at line 306 of file Convolution_tests.hpp.

Referenced by Conv4x4x1Filter3x1x1s3Double().

mic::types::MatrixPtr<double> mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double::desired_dW

private

Desired gradient dW from backpropagation.

Definition at line 303 of file Convolution_tests.hpp.

Referenced by Conv4x4x1Filter3x1x1s3Double().

mic::types::MatrixPtr<double> mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double::desired_dx

private

Target y values.

Desired gradient dx from backpropagation.

Definition at line 300 of file Convolution_tests.hpp.

Referenced by Conv4x4x1Filter3x1x1s3Double().

mic::types::MatrixPtr<double> mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double::desired_y

private

Desired output for a given x.

Definition at line 291 of file Convolution_tests.hpp.

Referenced by Conv4x4x1Filter3x1x1s3Double().

mic::types::MatrixPtr<double> mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double::dy

private

Gradient passed to backpropagation.

Definition at line 294 of file Convolution_tests.hpp.

Referenced by Conv4x4x1Filter3x1x1s3Double().

mic::mlnn::convolution::Convolution<double> mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double::layer

private

Object to be tested.

Definition at line 282 of file Convolution_tests.hpp.

Referenced by SetUp().

mic::neural_nets::loss::SquaredErrorLoss<double> mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double::loss

private

Definition at line 285 of file Convolution_tests.hpp.

mic::types::MatrixPtr<double> mic::neural_nets::unit_tests::Conv4x4x1Filter3x1x1s3Double::x

private

Test x - used in forward pass.

Definition at line 288 of file Convolution_tests.hpp.

Referenced by Conv4x4x1Filter3x1x1s3Double().

---

The documentation for this class was generated from the following file:

• src/mlnn/convolution/Convolution_tests.hpp