All SMAUG Operators

All operators supported by SMAUG. More...

Classes
class	smaug::BatchNormOp< Backend >
	Implements the batch normalization layer. More...
class	smaug::ConcatOp< Backend >
	Concatenates N Tensors along a specified axis. More...
class	smaug::SwitchOp< Backend >
	Conditionally forwards an input to one of two outputs. More...
class	smaug::MergeOp< Backend >
	Forwards the first live input to its output. More...
class	smaug::ConvolutionOp< Backend >
	The base class for all 4D spatial convolution operators. More...
class	smaug::DataOp< Backend >
	Exposes a Tensor as its only output. More...
class	smaug::DepthwiseConvolutionOp< Backend >
	Implements the depthwise convolution operator. More...
class	smaug::EltwiseAddOp< Backend >
	Adds two Tensors elementwise. More...
class	smaug::EltwiseMulOp< Backend >
	Multiplies two Tensors elementwise. More...
class	smaug::EltwiseOp< Backend >
	The base class of all elementwise operators. More...
class	smaug::EluOp< Backend >
	Implements the exponential linear unit function. More...
class	smaug::SeluOp< Backend >
	Implements the scaled exponential linear unit function. More...
class	smaug::FusedActivationOp
	An Operator fused with an activation function. More...
class	smaug::GreaterOp< Backend >
	Implements an elementwise greater than operator. More...
class	smaug::GreaterEqualOp< Backend >
	Implements an elementwise greater than or equal to operator. More...
class	smaug::InnerProductOp< Backend >
	Implements the inner product operator. More...
class	smaug::LessOp< Backend >
	Implements an elementwise less-than operator. More...
class	smaug::LessEqualOp< Backend >
	Implements an elementwise less-than-or-equal-to operator. More...
class	smaug::PaddingOp< Backend >
	Pad a given tensor in any number of dimensions with arbitrary size. More...
class	smaug::PoolingOp< Backend >
	Implements a pooling operator. More...
class	smaug::MaxPoolingOp< Backend >
	Implements the max-pooling operator. More...
class	smaug::AvgPoolingOp< Backend >
	Implements the arithmetic-average-pooling operator. More...
class	smaug::ReluOp< Backend >
	Implements the rectified linear unit operator: max(slope * x, 0). More...
class	smaug::ReorderOp< Backend >
	Implements a Tensor reordering operation to convert between different DataLayouts. More...
class	smaug::RepeatOp< Backend >
	Replicates a Tensor's data among all dimensions. More...
class	smaug::ReshapeOp< Backend >
	Changes the Tensor's shape while retaining the number of elements. More...
class	smaug::SigmoidOp< Backend >
	Implements the sigmoid operator, defined as 1/(1 + exp(-input)). More...
class	smaug::SoftmaxOp< Backend >
	Implements the softmax operator. More...
class	smaug::SplitOp< Backend >
	Implements the split operator, which divides a Tensor into N output Tensors along a specified dimension. More...
class	smaug::TanhOp< Backend >
	Implements the tanh operator. More...
class	smaug::HardTanhOp< Backend >
	Implements the hard tanh operator, which bounds the min and max value of the tanh operator. More...
class	smaug::UnaryOp< Backend >
	Base class for all operators with one input. More...

Detailed Description

All operators supported by SMAUG.