Uses of Interface
deepnetts.tensor.Tensor

Packages that use Tensor

Package	Description
deepnetts.accl.spi
deepnetts.net	Neural network architectures with their corresponding builders.
deepnetts.net.layers	Neural network layers, which are main building blocks of a neural network.
deepnetts.net.layers.activation	Activation functions for neural network layers.
deepnetts.tensor
deepnetts.util	Various utility classes including Tensor, image operations, multithreading, exceptions etc.

Uses of Tensor in deepnetts.accl.spi

Methods in deepnetts.accl.spi with parameters of type Tensor

Modifier and Type	Method	Description
void	ActivationVectorizationProvider.leakyRelu(Tensor tensor, float a)
void	ActivationVectorizationProvider.relu(Tensor tensor)
void	ActivationVectorizationProvider.sigmoid(Tensor tensor)
void	ActivationVectorizationProvider.tanh(Tensor tensor)

Uses of Tensor in deepnetts.net

Methods in deepnetts.net that return types with arguments of type Tensor

Modifier and Type	Method	Description
Preprocessing<Tensor>	NeuralNetwork.getPreprocessing()	Gets preprocessing that needs to be performed before input is fed to this network.

Method parameters in deepnetts.net with type arguments of type Tensor

Modifier and Type	Method	Description
void	NeuralNetwork.setPreprocessing(Preprocessing<Tensor> preprocessing)	Sets preprocessing that needs to be performed before input is fed to this network.

Uses of Tensor in deepnetts.net.layers

Classes in deepnetts.net.layers with type parameters of type Tensor

Modifier and Type	Interface	Description
interface	Layer<O extends Tensor>	Common base interface for all types of neural network layers.

Uses of Tensor in deepnetts.net.layers.activation

Subinterfaces with type arguments of type Tensor in deepnetts.net.layers.activation

Modifier and Type	Interface	Description
interface	ActivationFunction	Common base interface for all activation functions used in layers.

Methods in deepnetts.net.layers.activation with parameters of type Tensor

Modifier and Type	Method	Description
default void	ActivationFunction.accept(Tensor tensor)
void	ActivationFunction.apply(Tensor tensor, int from, int to)
void	LeakyRelu.apply(Tensor tensor, int from, int to)
void	Linear.apply(Tensor tensor, int from, int to)
void	Relu.apply(Tensor tensor, int from, int to)
void	Sigmoid.apply(Tensor tensor, int from, int to)
void	SoftSign.apply(Tensor tensor, int from, int to)
void	Tanh.apply(Tensor tensor, int from, int to)

Uses of Tensor in deepnetts.tensor

Classes in deepnetts.tensor that implement Tensor

Modifier and Type	Class	Description
class	Tensor1D	One dimensional tensor - a vector or an array.
final class	Tensor2D	A 2D tensor / matrix with specified number of rows and columns..
class	Tensor3D	A 3D tensor/matrix, with rows, columns and depth.
class	Tensor4D
class	TensorBase	The base call for multidimensional array/tensors.

Methods in deepnetts.tensor that return Tensor

Modifier and Type	Method	Description
static Tensor	Tensors.fromFile(String filePath)

Methods in deepnetts.tensor with parameters of type Tensor

Modifier and Type	Method	Description
static TensorBase	Tensors.absMax(Tensor t, Tensor max)	Returns tensors with max value for each component of input tensors.
static final void	Tensors.copy(Tensor src, Tensor dest)
static void	Tensors.max(Tensor t1, Tensor t2, Tensor result)
static void	Tensors.min(Tensor t1, Tensor t2, Tensor result)

Uses of Tensor in deepnetts.util

Classes in deepnetts.util that implement interfaces with type arguments of type Tensor

Modifier and Type	Class	Description
class	ImagePreprocessing	Image pre-processing to be used at inference time, after feeding input to the network.

Methods in deepnetts.util with parameters of type Tensor

Modifier and Type	Method	Description
void	ImagePreprocessing.apply(Tensor input)