| ActivationReLU<T extends Tensor> |
Rectified Linear Unit (ReLU) activation function.
|
| ActivationSigmoid<T extends Tensor> |
The sigmoid is defined as:
|
| ActivationTanH<T extends Tensor> |
The hyperbolic tangent (tanh) is defined as:
|
| 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.
|
| ConstantPadding2D<T extends Tensor<T>> |
Interface for padding which applies a constant padding to the output of the image
|
| FunctionBatchNorm<T extends Tensor<T>> |
Implementation of a forward only Batch Normalization.
|
| FunctionElementWiseMult<T extends Tensor> |
Multiplies each element in a tensor by the same value.
|
| FunctionLinear<T extends Tensor> |
Applies a linear (or affine) equation to input array.
|
| SpatialAveragePooling<T extends Tensor> |
Max spatial pooling find the average value inside the pooling region.
|
| 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. |
| SpatialConvolve2D<T extends Tensor<T>> |
Performs convolutions across an input image with special kernels that have 'C' channels, one for each input image.
|
| SpatialMaxPooling<T extends Tensor> |
Max spatial pooling find the maximum value inside the pooling region.
|
| SpatialPadding2D<T extends Tensor<T>> |
Interface for all virtual 2D spatial padding implementation.
|
| SpatialPooling<T extends Tensor> |
Spatial pooling down samples the input spatial tensors by finding a representative value inside
each pooling region.
|