CPU implementation of the cross entropy loss operation for neural networks. More...

Inheritance diagram for Mila::Dnn::Compute::CpuCrossEntropyOp:

[legend]

Collaboration diagram for Mila::Dnn::Compute::CpuCrossEntropyOp:

[legend]

Public Types
using	MR = typename CpuDevice::MR

using	OperationBase = UnaryOperation< DeviceType::Cpu, int, float >

Public Types inherited from Mila::Dnn::Compute::UnaryOperation< DeviceType::Cpu, int, float >
using	MR = std::conditional_t< TDeviceType==DeviceType::Cuda, CudaMemoryResource, HostMemoryResource >
	Memory resource type based on device type.

Public Member Functions
	CpuCrossEntropyOp (const CrossEntropyConfig &config)
	Constructs a new CPU Cross Entropy operation with the default device context.

	CpuCrossEntropyOp (std::shared_ptr< DeviceContext > context, const CrossEntropyConfig &config)
	Constructs a new CPU Cross Entropy operation with a specific device context.

void	backward (const Tensor< int, MR > &input, const Tensor< float, MR > &output, const Tensor< float, MR > &output_gradient, const std::vector< std::shared_ptr< Tensor< float, MR > > > &parameters, std::vector< std::shared_ptr< Tensor< float, MR > > > &parameter_gradients, Tensor< int, MR > &input_gradient, const OperationAttributes &attributes, const std::vector< std::shared_ptr< Tensor< float, MR > > > &output_state) const
	Performs the backward pass of the cross entropy operation.

void	backward_impl (float dlogits, const float dlosses, const float *probs, const Tensor< int, CpuMemoryResource > &targets, int B, int T, int V, int Vp) const
	Helper method for the backward pass implementation.

void	forward (const Tensor< int, MR > &input, const std::vector< std::shared_ptr< Tensor< float, MR > > > &parameters, const OperationAttributes &attributes, Tensor< float, MR > &output, std::vector< std::shared_ptr< Tensor< float, MR > > > &output_state) const override
	Performs the forward pass of the cross entropy operation.

std::string	getName () const override
	Gets the name of this operation.

Public Member Functions inherited from Mila::Dnn::Compute::UnaryOperation< DeviceType::Cpu, int, float >
	UnaryOperation (OperationType operation_type)
	Constructs a UnaryOperation with the specified operation type.

	UnaryOperation (OperationType operation_type, std::shared_ptr< DeviceContext > context)
	Constructs a UnaryOperation with the specified operation type and device context.

virtual	~UnaryOperation ()=default
	Virtual destructor for proper cleanup of derived classes.

virtual void	backward (const Tensor< int, MR > &grad, const std::vector< std::shared_ptr< Tensor< float, MR > > > &parameters, std::vector< std::shared_ptr< Tensor< float, MR > > > &output_grads) const
	Executes the backward pass of a unary operation.

virtual void	backward (const Tensor< int, MR > &input, const Tensor< float, MR > &output_grad, const std::vector< std::shared_ptr< Tensor< float, MR > > > &parameters, std::vector< std::shared_ptr< Tensor< float, MR > > > &parameter_grads, Tensor< int, MR > &input_grad, const OperationAttributes &properties, const std::vector< std::shared_ptr< Tensor< float, MR > > > &output_state) const
	Executes the comprehensive backward pass of a unary operation.

virtual void	forward (const Tensor< int, MR > &input, const std::vector< std::shared_ptr< Tensor< float, MR > > > &parameters, const OperationAttributes &properties, Tensor< float, MR > &output, std::vector< std::shared_ptr< Tensor< float, MR > > > &output_state) const=0
	Executes the forward pass of a unary operation.

Public Member Functions inherited from Mila::Dnn::Compute::OperationBase< TDeviceType, TInput1, TInput2, TOutput >
	OperationBase (OperationType operation_type, std::shared_ptr< DeviceContext > context)
	Constructs an OperationBase object with a specific device context and compute precision.

virtual	~OperationBase ()=default
	Virtual destructor for the OperationBase class.

std::shared_ptr< DeviceContext >	getDeviceContext () const
	Gets the device context associated with this operation.

DeviceType	getDeviceType () const
	Gets the device type for this operation.

OperationType	getOperationType () const
	Gets the operation type enumeration value.

Private Attributes
CrossEntropyConfig	config_
	Configuration for the CrossEntropy operation.

Detailed Description

CPU implementation of the cross entropy loss operation for neural networks.

This class provides a CPU-based implementation of the cross entropy loss function, which is commonly used in classification tasks. It computes the negative log likelihood of the correct class given the predicted probabilities.

Template Parameters

TInput	The data type of the input tensor elements (typically int for class indices).
TDataType	The data type used for computation and output (typically float).

Member Typedef Documentation

◆ MR

using Mila::Dnn::Compute::CpuCrossEntropyOp::MR = typename CpuDevice::MR

◆ OperationBase

using Mila::Dnn::Compute::CpuCrossEntropyOp::OperationBase = UnaryOperation<DeviceType::Cpu, int, float>

Constructor & Destructor Documentation

◆ CpuCrossEntropyOp() [1/2]

Mila::Dnn::Compute::CpuCrossEntropyOp::CpuCrossEntropyOp ( const CrossEntropyConfig & config )

inline

Constructs a new CPU Cross Entropy operation with the default device context.

Initializes the operation with a CPU device context.

◆ CpuCrossEntropyOp() [2/2]

Mila::Dnn::Compute::CpuCrossEntropyOp::CpuCrossEntropyOp	(	std::shared_ptr< DeviceContext >	context,
		const CrossEntropyConfig &	config
	)

inline

Constructs a new CPU Cross Entropy operation with a specific device context.

Parameters

context The device context to use for this operation.

Exceptions

std::runtime_error If the context is not for a CPU device.

Member Function Documentation

◆ backward()

void Mila::Dnn::Compute::CpuCrossEntropyOp::backward	(	const Tensor< int, MR > &	input,
		const Tensor< float, MR > &	output,
		const Tensor< float, MR > &	output_gradient,
		const std::vector< std::shared_ptr< Tensor< float, MR > > > &	parameters,
		std::vector< std::shared_ptr< Tensor< float, MR > > > &	parameter_gradients,
		Tensor< int, MR > &	input_gradient,
		const OperationAttributes &	attributes,
		const std::vector< std::shared_ptr< Tensor< float, MR > > > &	output_state
	)		const

inline

Performs the backward pass of the cross entropy operation.

Computes gradients with respect to inputs and probabilities.

Parameters

input	Input tensor from the forward pass (target indices).
output	Output tensor from the forward pass (loss values).
output_gradient	Gradient of the loss with respect to the output.
parameters	Parameters tensor from forward pass (probabilities).
parameter_gradients	Gradients for parameters (probabilities).
input_gradient	Gradient of the loss with respect to the input (unused for integer targets).
attributes	Additional attributes for the operation.
output_state	Cache tensors from forward pass.

Here is the call graph for this function:

◆ backward_impl()

void Mila::Dnn::Compute::CpuCrossEntropyOp::backward_impl	(	float *	dlogits,
		const float *	dlosses,
		const float *	probs,
		const Tensor< int, CpuMemoryResource > &	targets,
		int	B,
		int	T,
		int	V,
		int	Vp
	)		const

inline

Helper method for the backward pass implementation.

Computes gradients for the combined softmax and cross entropy operation.

Parameters

dlogits	Gradient buffer for logits/probabilities.
dlosses	Gradient buffer from output loss.
probs	Original probability values.
targets	Target class indices.
B	Batch size.
TDataType	Sequence length.
V	Vocabulary size (without padding).
Vp	Padded vocabulary size.

Here is the call graph for this function:

Here is the caller graph for this function:

◆ forward()

void Mila::Dnn::Compute::CpuCrossEntropyOp::forward	(	const Tensor< int, MR > &	input,
		const std::vector< std::shared_ptr< Tensor< float, MR > > > &	parameters,
		const OperationAttributes &	attributes,
		Tensor< float, MR > &	output,
		std::vector< std::shared_ptr< Tensor< float, MR > > > &	output_state
	)		const

inlineoverride

Performs the forward pass of the cross entropy operation.

Computes the negative log likelihood of the correct class for each sample.

Parameters

input	Input tensor containing target class indices of shape [B, TDataType].
parameters	Parameters tensor containing probabilities of shape [B, TDataType, V].
attributes	Additional attributes for the operation.
output	Output tensor to store the cross entropy losses of shape [B, TDataType].
output_state	Cache for storing intermediate results (used in backward pass).

Here is the call graph for this function:

◆ getName()

std::string Mila::Dnn::Compute::CpuCrossEntropyOp::getName ( ) const

inlineoverridevirtual

Gets the name of this operation.

Returns: std::string The name of the operation ("Cpu::CrossEntropyOp").

Implements Mila::Dnn::Compute::OperationBase< TDeviceType, TInput1, TInput2, TOutput >.

Member Data Documentation

◆ config_

CrossEntropyConfig Mila::Dnn::Compute::CpuCrossEntropyOp::config_

private

Configuration for the CrossEntropy operation.

The documentation for this class was generated from the following file:

/home/runner/work/Mila/Mila/Mila/Src/Dnn/Compute/Operations/Cpu/CpuCrossEntropyOp.ixx

Public Types

Public Member Functions

Private Attributes

Detailed Description

Member Typedef Documentation

◆ MR

◆ OperationBase

Constructor & Destructor Documentation

◆ CpuCrossEntropyOp() [1/2]

◆ CpuCrossEntropyOp() [2/2]

Member Function Documentation

◆ backward()

◆ backward_impl()

◆ forward()

◆ getName()

Member Data Documentation

◆ config_