Dnn.Modules.Softmax Module Reference

Exported Modules
module	Compute.UnaryOperation
module	Dnn.TensorHelpers
module	Compute.OperationBase
module	Compute.CpuMemoryResource
module	Compute.MemoryResource
module	Compute.DeviceType
module	Compute.OperationAttributes
module	Dnn.Module
module	Dnn.Tensor
module	Dnn.TensorTraits
module	Compute.Precision
module	Compute.OperationRegistry
module	Compute.CudaMemoryResource
module	Compute.DeviceContext
module	Compute.ComputeDevice
module	Serialization.ModelArchive

Classes
class	Mila::Dnn::Softmax< TDeviceType, TInput, TOutput >
	Softmax module for neural networks. More...
class	Mila::Dnn::SoftmaxConfig
	Configuration class for Softmax module. More...

Typedefs
template<typename TInput = float, typename TOutput = TInput>
using	Mila::Dnn::CpuSoftmax = Softmax< DeviceType::Cpu, TInput, TOutput >
	Type alias for CPU-based softmax module with customizable tensor types.
template<typename TInput = float, typename TOutput = TInput>
using	Mila::Dnn::CudaSoftmax = Softmax< DeviceType::Cuda, TInput, TOutput >
	Type alias for CUDA-based softmax module with customizable tensor types.
using	ModuleBase = Module< TDeviceType, TInput, TOutput >
	Alias for base module type.
using	MR = std::conditional_t< TDeviceType==DeviceType::Cuda, CudaMemoryResource, CpuMemoryResource >
	Memory resource type used for tensors, selected based on device type.

Functions
	Softmax (const std::string &device_name, const SoftmaxConfig &config)
	Constructs a new Softmax module with a device name.
	Softmax (std::shared_ptr< DeviceContext > device_context, const SoftmaxConfig &config)
	Constructs a new Softmax module with a provided device context.
void	backward (const Tensor< TInput, MR > &input, const Tensor< TOutput, MR > &output_grad, Tensor< TInput, MR > &input_grad)
	Performs the backward pass of the Softmax operation.
void	createOperation ()
	Creates the appropriate softmax operation for the current device.
void	forward (const Tensor< TInput, MR > &input, Tensor< TOutput, MR > &output)
	Performs the forward pass of the softmax operation.
int64_t	getAxis () const
	Gets the axis used for softmax computation.
void	load (ModelArchive &archive) override
	Deserializes the module state from a ZIP archive.
size_t	parameterCount () const override
	Gets the number of trainable parameters in this module.
void	save (ModelArchive &zip) const override
	Serializes the module state to a ZIP archive.
std::string	toString () const override
	Generates a string representation of this module's configuration.

Variables
OperationAttributes	attributes_
	Operation attributes and configuration.
SoftmaxConfig	config_
	Configuration for the Softmax module.
std::shared_ptr< UnaryOperation< TDeviceType, TInput, TOutput > >	operation_ { nullptr }
	The operation that implements the softmax calculation.
std::vector< std::shared_ptr< Tensor< TOutput, MR > > >	output_state_
	Collection of output state tensors for caching.
std::vector< std::shared_ptr< Tensor< TInput, MR > > >	parameters_
	Collection of parameters for this module (empty for Softmax).

Files
file	/home/runner/work/Mila/Mila/Mila/Src/Dnn/Modules/Layers/Softmax.ixx
	Implementation of the Softmax activation function module.
file	/home/runner/work/Mila/Mila/Mila/Src/Dnn/Modules/Layers/SoftmaxConfig.ixx
	Configuration interface for the Softmax module in the Mila DNN framework.