caffe::DataTransformer< Dtype > Class Template Reference

Applies common transformations to the input data, such as scaling, mirroring, substracting the image mean... More...

#include <data_transformer.hpp>

Public Member Functions
	DataTransformer (const TransformationParameter &param, Phase phase)
void	InitRand ()
	Initialize the Random number generations if needed by the transformation.
void	Transform (const Datum &datum, Blob< Dtype > *transformed_blob)
	Applies the transformation defined in the data layer's transform_param block to the data. More...
void	Transform (const vector< Datum > &datum_vector, Blob< Dtype > *transformed_blob)
	Applies the transformation defined in the data layer's transform_param block to a vector of Datum. More...
void	Transform (Blob< Dtype > *input_blob, Blob< Dtype > *transformed_blob)
	Applies the same transformation defined in the data layer's transform_param block to all the num images in a input_blob. More...
vector< int >	InferBlobShape (const Datum &datum)
	Infers the shape of transformed_blob will have when the transformation is applied to the data. More...
vector< int >	InferBlobShape (const vector< Datum > &datum_vector)
	Infers the shape of transformed_blob will have when the transformation is applied to the data. It uses the first element to infer the shape of the blob. More...

Protected Member Functions
virtual int	Rand (int n)
	Infers the shape of transformed_blob will have when the transformation is applied to the data. It uses the first element to infer the shape of the blob. More...
void	Transform (const Datum &datum, Dtype *transformed_data)

Protected Attributes
TransformationParameter	param_
shared_ptr< Caffe::RNG >	rng_
Phase	phase_
Blob< Dtype >	data_mean_
vector< Dtype >	mean_values_

Detailed Description

template<typename Dtype>
class caffe::DataTransformer< Dtype >

Applies common transformations to the input data, such as scaling, mirroring, substracting the image mean...

Member Function Documentation

InferBlobShape() [1/2]

template<typename Dtype >

vector< int > caffe::DataTransformer< Dtype >::InferBlobShape

(

const Datum &

datum

)

Infers the shape of transformed_blob will have when the transformation is applied to the data.

Parameters

datum

Datum containing the data to be transformed.

InferBlobShape() [2/2]

template<typename Dtype >

vector< int > caffe::DataTransformer< Dtype >::InferBlobShape

(

const vector< Datum > &

datum_vector

)

Infers the shape of transformed_blob will have when the transformation is applied to the data. It uses the first element to infer the shape of the blob.

Parameters

datum_vector

A vector of Datum containing the data to be transformed.

Rand()

template<typename Dtype >

int caffe::DataTransformer< Dtype >::Rand ( int  n )

protectedvirtual

Infers the shape of transformed_blob will have when the transformation is applied to the data. It uses the first element to infer the shape of the blob.

Parameters

mat_vector	A vector of Mat containing the data to be transformed. Generates a random integer from Uniform({0, 1, ..., n-1}).
n	The upperbound (exclusive) value of the random number.

Returns

A uniformly random integer value from ({0, 1, ..., n-1}).

Transform() [1/3]

template<typename Dtype >

void caffe::DataTransformer< Dtype >::Transform	(	const Datum &	datum,
		Blob< Dtype > *	transformed_blob
	)

Applies the transformation defined in the data layer's transform_param block to the data.

Parameters

datum	Datum containing the data to be transformed.
transformed_blob	This is destination blob. It can be part of top blob's data if set_cpu_data() is used. See data_layer.cpp for an example.

Transform() [2/3]

template<typename Dtype >

void caffe::DataTransformer< Dtype >::Transform	(	const vector< Datum > &	datum_vector,
		Blob< Dtype > *	transformed_blob
	)

Applies the transformation defined in the data layer's transform_param block to a vector of Datum.

Parameters

datum_vector	A vector of Datum containing the data to be transformed.
transformed_blob	This is destination blob. It can be part of top blob's data if set_cpu_data() is used. See memory_layer.cpp for an example.

Transform() [3/3]

template<typename Dtype >

void caffe::DataTransformer< Dtype >::Transform	(	Blob< Dtype > *	input_blob,
		Blob< Dtype > *	transformed_blob
	)

Applies the same transformation defined in the data layer's transform_param block to all the num images in a input_blob.

Parameters

input_blob	A Blob containing the data to be transformed. It applies the same transformation to all the num images in the blob.
transformed_blob	This is destination blob, it will contain as many images as the input blob. It can be part of top blob's data.

---

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

• include/caffe/data_transformer.hpp
• src/caffe/data_transformer.cpp