Computes the Euclidean (L2) loss $E = \frac{1}{2N} \sum\limits_{n=1}^N \left| \left| \hat{y}_n - y_n \right| \right|_2^2$ for real-valued regression tasks. More...

#include <euclidean_loss_layer.hpp>

Inheritance diagram for caffe::EuclideanLossLayer< Dtype >:

Public Member Functions
	EuclideanLossLayer (const LayerParameter &param)

virtual void	Reshape (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)
	Adjust the shapes of top blobs and internal buffers to accommodate the shapes of the bottom blobs. More...

virtual const char *	type () const
	Returns the layer type.

virtual bool	AllowForceBackward (const int bottom_index) const

Public Member Functions inherited from caffe::LossLayer< Dtype >
	LossLayer (const LayerParameter &param)

virtual void	LayerSetUp (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)
	Does layer-specific setup: your layer should implement this function as well as Reshape. More...

virtual int	ExactNumBottomBlobs () const
	Returns the exact number of bottom blobs required by the layer, or -1 if no exact number is required. More...

virtual bool	AutoTopBlobs () const
	For convenience and backwards compatibility, instruct the Net to automatically allocate a single top Blob for LossLayers, into which they output their singleton loss, (even if the user didn't specify one in the prototxt, etc.).

virtual int	ExactNumTopBlobs () const
	Returns the exact number of top blobs required by the layer, or -1 if no exact number is required. More...

Public Member Functions inherited from caffe::Layer< Dtype >
	Layer (const LayerParameter &param)

void	SetUp (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)
	Implements common layer setup functionality. More...

Dtype	Forward (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)
	Given the bottom blobs, compute the top blobs and the loss. More...

void	Backward (const vector< Blob< Dtype > > &top, const vector< bool > &propagate_down, const vector< Blob< Dtype > > &bottom)
	Given the top blob error gradients, compute the bottom blob error gradients. More...

vector< shared_ptr< Blob< Dtype > > > &	blobs ()
	Returns the vector of learnable parameter blobs.

const LayerParameter &	layer_param () const
	Returns the layer parameter.

virtual void	ToProto (LayerParameter *param, bool write_diff=false)
	Writes the layer parameter to a protocol buffer.

Dtype	loss (const int top_index) const
	Returns the scalar loss associated with a top blob at a given index.

void	set_loss (const int top_index, const Dtype value)
	Sets the loss associated with a top blob at a given index.

virtual int	MinBottomBlobs () const
	Returns the minimum number of bottom blobs required by the layer, or -1 if no minimum number is required. More...

virtual int	MaxBottomBlobs () const
	Returns the maximum number of bottom blobs required by the layer, or -1 if no maximum number is required. More...

virtual int	MinTopBlobs () const
	Returns the minimum number of top blobs required by the layer, or -1 if no minimum number is required. More...

virtual int	MaxTopBlobs () const
	Returns the maximum number of top blobs required by the layer, or -1 if no maximum number is required. More...

virtual bool	EqualNumBottomTopBlobs () const
	Returns true if the layer requires an equal number of bottom and top blobs. More...

bool	param_propagate_down (const int param_id)
	Specifies whether the layer should compute gradients w.r.t. a parameter at a particular index given by param_id. More...

void	set_param_propagate_down (const int param_id, const bool value)
	Sets whether the layer should compute gradients w.r.t. a parameter at a particular index given by param_id.

Protected Member Functions
virtual void	Forward_cpu (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)
	Computes the Euclidean (L2) loss $E = \frac{1}{2N} \sum\limits_{n=1}^N \left\| \left\| \hat{y}_n - y_n \right\| \right\|_2^2$ for real-valued regression tasks. More...

virtual void	Forward_gpu (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)
	Using the GPU device, compute the layer output. Fall back to Forward_cpu() if unavailable.

virtual void	Backward_cpu (const vector< Blob< Dtype > > &top, const vector< bool > &propagate_down, const vector< Blob< Dtype > > &bottom)
	Computes the Euclidean error gradient w.r.t. the inputs. More...

virtual void	Backward_gpu (const vector< Blob< Dtype > > &top, const vector< bool > &propagate_down, const vector< Blob< Dtype > > &bottom)
	Using the GPU device, compute the gradients for any parameters and for the bottom blobs if propagate_down is true. Fall back to Backward_cpu() if unavailable.

Protected Member Functions inherited from caffe::Layer< Dtype >
virtual void	CheckBlobCounts (const vector< Blob< Dtype > > &bottom, const vector< Blob< Dtype > > &top)

void	SetLossWeights (const vector< Blob< Dtype > *> &top)

Protected Attributes
Blob< Dtype >	diff_

Protected Attributes inherited from caffe::Layer< Dtype >
LayerParameter	layer_param_

Phase	phase_

vector< shared_ptr< Blob< Dtype > > >	blobs_

vector< bool >	param_propagate_down_

vector< Dtype >	loss_

Detailed Description

template<typename Dtype>
class caffe::EuclideanLossLayer< Dtype >

Computes the Euclidean (L2) loss $E = \frac{1}{2N} \sum\limits_{n=1}^N \left| \left| \hat{y}_n - y_n \right| \right|_2^2$ for real-valued regression tasks.

Parameters

bottom	input Blob vector (length 2) $(N \times C \times H \times W)$ the predictions $\hat{y} \in [-\infty, +\infty]$ $(N \times C \times H \times W)$ the targets $y \in [-\infty, +\infty]$
top	output Blob vector (length 1) $(1 \times 1 \times 1 \times 1)$ the computed Euclidean loss: $E = \frac{1}{2n} \sum\limits_{n=1}^N \left\| \left\| \hat{y}_n - y_n \right\| \right\|_2^2$

This can be used for least-squares regression tasks. An InnerProductLayer input to a EuclideanLossLayer exactly formulates a linear least squares regression problem. With non-zero weight decay the problem becomes one of ridge regression – see src/caffe/test/test_sgd_solver.cpp for a concrete example wherein we check that the gradients computed for a Net with exactly this structure match hand-computed gradient formulas for ridge regression.

(Note: Caffe, and SGD in general, is certainly not the best way to solve linear least squares problems! We use it only as an instructive example.)

Member Function Documentation

◆ AllowForceBackward()

template<typename Dtype >

virtual bool caffe::EuclideanLossLayer< Dtype >::AllowForceBackward ( const int bottom_index ) const

inlinevirtual

Unlike most loss layers, in the EuclideanLossLayer we can backpropagate to both inputs – override to return true and always allow force_backward.

Reimplemented from caffe::LossLayer< Dtype >.

◆ Backward_cpu()

template<typename Dtype >

void caffe::EuclideanLossLayer< Dtype >::Backward_cpu	(	const vector< Blob< Dtype > *> &	top,
		const vector< bool > &	propagate_down,
		const vector< Blob< Dtype > *> &	bottom
	)

protectedvirtual

Computes the Euclidean error gradient w.r.t. the inputs.

Unlike other children of LossLayer, EuclideanLossLayer can compute gradients with respect to the label inputs bottom[1] (but still only will if propagate_down[1] is set, due to being produced by learnable parameters or if force_backward is set). In fact, this layer is "commutative" – the result is the same regardless of the order of the two bottoms.

Parameters

top	output Blob vector (length 1), providing the error gradient with respect to the outputs $(1 \times 1 \times 1 \times 1)$ This Blob's diff will simply contain the loss_weight* $\lambda$ , as $\lambda$ is the coefficient of this layer's output $\ell_i$ in the overall Net loss $E = \lambda_i \ell_i + \mbox{other loss terms}$ ; hence $\frac{\partial E}{\partial \ell_i} = \lambda_i$ . (*Assuming that this top Blob is not used as a bottom (input) by any other layer of the Net.)
propagate_down	see Layer::Backward.
bottom	input Blob vector (length 2) $(N \times C \times H \times W)$ the predictions $\hat{y}$ ; Backward fills their diff with gradients $\frac{\partial E}{\partial \hat{y}} = \frac{1}{n} \sum\limits_{n=1}^N (\hat{y}_n - y_n)$ if propagate_down[0] $(N \times C \times H \times W)$ the targets ; Backward fills their diff with gradients $\frac{\partial E}{\partial y} = \frac{1}{n} \sum\limits_{n=1}^N (y_n - \hat{y}_n)$ if propagate_down[1]

Implements caffe::Layer< Dtype >.

◆ Forward_cpu()

template<typename Dtype >

void caffe::EuclideanLossLayer< Dtype >::Forward_cpu	(	const vector< Blob< Dtype > *> &	bottom,
		const vector< Blob< Dtype > *> &	top
	)

protectedvirtual

Computes the Euclidean (L2) loss $E = \frac{1}{2N} \sum\limits_{n=1}^N \left| \left| \hat{y}_n - y_n \right| \right|_2^2$ for real-valued regression tasks.

Parameters

bottom	input Blob vector (length 2) $(N \times C \times H \times W)$ the predictions $\hat{y} \in [-\infty, +\infty]$ $(N \times C \times H \times W)$ the targets $y \in [-\infty, +\infty]$
top	output Blob vector (length 1) $(1 \times 1 \times 1 \times 1)$ the computed Euclidean loss: $E = \frac{1}{2n} \sum\limits_{n=1}^N \left\| \left\| \hat{y}_n - y_n \right\| \right\|_2^2$

This can be used for least-squares regression tasks. An InnerProductLayer input to a EuclideanLossLayer exactly formulates a linear least squares regression problem. With non-zero weight decay the problem becomes one of ridge regression – see src/caffe/test/test_sgd_solver.cpp for a concrete example wherein we check that the gradients computed for a Net with exactly this structure match hand-computed gradient formulas for ridge regression.

(Note: Caffe, and SGD in general, is certainly not the best way to solve linear least squares problems! We use it only as an instructive example.)

Implements caffe::Layer< Dtype >.

◆ Reshape()

template<typename Dtype >

void caffe::EuclideanLossLayer< Dtype >::Reshape	(	const vector< Blob< Dtype > *> &	bottom,
		const vector< Blob< Dtype > *> &	top
	)

virtual

Adjust the shapes of top blobs and internal buffers to accommodate the shapes of the bottom blobs.

Parameters

bottom	the input blobs, with the requested input shapes
top	the top blobs, which should be reshaped as needed

This method should reshape top blobs as needed according to the shapes of the bottom (input) blobs, as well as reshaping any internal buffers and making any other necessary adjustments so that the layer can accommodate the bottom blobs.

Reimplemented from caffe::LossLayer< Dtype >.

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

include/caffe/layers/euclidean_loss_layer.hpp
src/caffe/layers/euclidean_loss_layer.cpp

Public Member Functions

Protected Member Functions

Protected Attributes

Detailed Description

template<typename Dtype> class caffe::EuclideanLossLayer< Dtype >

Member Function Documentation

◆ AllowForceBackward()

◆ Backward_cpu()

◆ Forward_cpu()

◆ Reshape()

template<typename Dtype>
class caffe::EuclideanLossLayer< Dtype >