All Classes
| Class | Description |
|---|---|
| ActivationReLU<T extends Tensor> |
Rectified Linear Unit (ReLU) activation function.
|
| ActivationReLU_F32 |
Implementation of
ActivationReLU for Tensor_F32. |
| ActivationReLU_F64 |
Implementation of
ActivationReLU for Tensor_F64. |
| ActivationSigmoid<T extends Tensor> |
The sigmoid is defined as:
|
| ActivationSigmoid_F32 |
Implementation of
ActivationSigmoid for Tensor_F32. |
| ActivationSigmoid_F64 |
Implementation of
ActivationSigmoid for Tensor_F64. |
| ActivationTanH<T extends Tensor> |
The hyperbolic tangent (tanh) is defined as:
|
| ActivationTanH_F32 |
Implementation of
ActivationTanH for Tensor_F32. |
| ActivationTanH_F64 |
Implementation of
ActivationTanH for Tensor_F64. |
| BaseFunction<T extends Tensor> |
Base class which implements common functionality between all
functions |
| BaseSpatialPadding2D<T extends Tensor<T>> |
Abstract class fo all virtual 2D spatial padding implementation.
|
| BaseSpatialWindow<T extends Tensor<T>,P extends SpatialPadding2D<T>> |
Common class for implementations of
SpatialConvolve2D. |
| BaseTensor |
Base class for all Tensor data types.
|
| BatchNorm |
Batch Normalization [1] determines the mean and standard deviation (stdev) of each input element individually
using the training data.
|
| ClippedPadding2D<T extends Tensor<T>> |
Interface for padding in which the region being sampled has been clipped so that it will be
entirely contained inside the original image.
|
| ClippedPadding2D_F32 |
Implementation of
ConstantPadding2D_F32. |
| ClippedPadding2D_F64 |
Implementation of
ConstantPadding2D_F64. |
| ConfigConvolve2D |
Configuration for 2D convolution.
|
| ConfigPadding |
Configuration for spatial padding.
|
| ConfigSpatial |
Common configuration for many spatial functions
|
| Configuration |
Complex algorithms with several parameters can specify their parameters using a separate class.
|
| ConstantPadding2D<T extends Tensor<T>> |
Interface for padding which applies a constant padding to the output of the image
|
| ConstantPadding2D_F32 |
Pads pixels outside the input image with a user specified constant value.
|
| ConstantPadding2D_F64 |
Pads pixels outside the input image with a user specified constant value.
|
| DeepBoofConstants |
Various constants used throughout DeepBoof
|
| DeepBoofOps | |
| DeepBoofVersion |
Automatically generated file containing build version information.
|
| DFunction<T extends Tensor<T>> |
Functions which also implement the backwards step and compute the gradient for all inputs. |
| ElementWiseFunction<T extends Tensor> |
Base class for element-wise functions
|
| FactoryForwards | |
| Function<T extends Tensor> |
High level interface for functions in an Artificial Neural Network.
|
| FunctionBatchNorm<T extends Tensor<T>> |
Implementation of a forward only Batch Normalization.
|
| FunctionBatchNorm_F32 |
Implementation of
FunctionBatchNorm for Tensor_F32. |
| FunctionBatchNorm_F64 |
Implementation of
FunctionBatchNorm for Tensor_F64. |
| FunctionElementWiseMult<T extends Tensor> |
Multiplies each element in a tensor by the same value.
|
| FunctionElementWiseMult_F32 |
Implementation of
FunctionElementWiseMult for Tensor_F32. |
| FunctionElementWiseMult_F64 |
Implementation of
FunctionElementWiseMult for Tensor_F64. |
| FunctionLinear<T extends Tensor> |
Applies a linear (or affine) equation to input array.
|
| FunctionLinear_F32 |
Implementation of
FunctionLinear for Tensor_F32. |
| FunctionLinear_F64 |
Implementation of
FunctionLinear for Tensor_F64. |
| FunctionSequence<T extends Tensor<T>,F extends Function<T>> |
Processes a sequence of forward functions.
|
| InputAddress |
Address which points to the input of a node
|
| ITensor |
Tensor Interface
|
| Node<T extends Tensor<T>,F extends Function<T>> |
Node in a network graph which describes the network's processing sequence.
|
| PaddingType |
Specifies the type of padding applied to a spacial function.
|
| SequenceForwardOrder |
Orders an unsorted list of nodes so that they can be processed in sequence and have all of their dependencies meet
prior to being invoked.
|
| SequenceForwardOrder.NodeData | |
| SpatialAveragePooling<T extends Tensor> |
Max spatial pooling find the average value inside the pooling region.
|
| SpatialAveragePooling_F32 |
Implementation of
SpatialAveragePooling for Tensor_F32. |
| SpatialAveragePooling_F64 |
Implementation of
SpatialAveragePooling for Tensor_F64. |
| SpatialBatchNorm<T extends Tensor<T>> |
Spatial
Batch Normalization seeks to maintain the convolutional property, "that
different elements of the same feature map, at different locations, are normalized in the same way." [1]
Thus the input tensor (N,C,H,W) is "reshaped" such that it is (N*H*W,C) and it's treated like a mini-batch
with N*H*W elements. |
| SpatialBatchNorm_F32 |
Implementation of
SpatialBatchNorm for Tensor_F32 |
| SpatialBatchNorm_F64 |
Implementation of
SpatialBatchNorm for Tensor_F64 |
| SpatialConvolve2D<T extends Tensor<T>> |
Performs convolutions across an input image with special kernels that have 'C' channels, one for each input image.
|
| SpatialConvolve2D_F32 |
Implementation of
SpatialConvolve2D for Tensor_F32 |
| SpatialConvolve2D_F64 |
Implementation of
SpatialConvolve2D for Tensor_F64 |
| SpatialMaxPooling<T extends Tensor> |
Max spatial pooling find the maximum value inside the pooling region.
|
| SpatialMaxPooling_F32 |
Implementation of
SpatialMaxPooling for Tensor_F32. |
| SpatialMaxPooling_F64 |
Implementation of
SpatialMaxPooling for Tensor_F64. |
| SpatialPadding2D<T extends Tensor<T>> |
Interface for all virtual 2D spatial padding implementation.
|
| SpatialPadding2D_F32 |
Abstract class for F64 implementations of
BaseSpatialPadding2D. |
| SpatialPadding2D_F64 |
Abstract class for F64 implementations of
BaseSpatialPadding2D. |
| SpatialPooling<T extends Tensor> |
Spatial pooling down samples the input spatial tensors by finding a representative value inside
each pooling region.
|
| SpatialWindowChannel<T extends Tensor<T>,VT extends SpatialPadding2D<T>> |
Implementation of
BaseSpatialWindow which processes the spatial tensor is processed in
BCHW (mini-batch, channel, height, width) order |
| SpatialWindowImage<T extends Tensor<T>,P extends SpatialPadding2D<T>> |
Implementation of
BaseSpatialWindow which processes the spatial tensor is one
image in a mini batch at a time. |
| Tensor<T extends Tensor> |
Base class for Tensors.
|
| Tensor_F32 | |
| Tensor_F64 | |
| Tensor_S32 | |
| Tensor_S64 | |
| Tensor_U8 | |
| TensorFactory<T extends Tensor> | |
| TensorFactory_F32 |
Various functions for unit tests
|
| TensorFactory_F64 |
Various functions for unit tests
|
| TensorMerger<T extends Tensor<T>> |
Merged multiple input tensors into a single output which can be processed by a
Function. |
| TensorOps | |
| TensorOps_F32 | |
| TensorOps_F64 | |
| VTensor |
A virtual tensor doesn't physically store in memory the entire tensor, instead it uses an equation
to generate on the fly some or all of a tensor.
|
| VTensor_F32 |
Virtual tensor for 64bit float types.
|
| VTensor_F64 |
Virtual tensor for 64bit float types.
|