Caffe
Public Member Functions | Protected Member Functions | Protected Attributes | List of all members
caffe::SoftmaxWithLossLayer< Dtype > Class Template Reference

Computes the multinomial logistic loss for a one-of-many classification task, passing real-valued predictions through a softmax to get a probability distribution over classes. More...

#include <softmax_loss_layer.hpp>

Inheritance diagram for caffe::SoftmaxWithLossLayer< Dtype >:
caffe::LossLayer< Dtype > caffe::Layer< Dtype >

Public Member Functions

 SoftmaxWithLossLayer (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 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 int ExactNumTopBlobs () const
 Returns the exact number of top blobs required by the layer, or -1 if no exact 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...
 
- Public Member Functions inherited from caffe::LossLayer< Dtype >
 LossLayer (const LayerParameter &param)
 
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 bool AllowForceBackward (const int bottom_index) const
 
- 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 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)
 Using the CPU device, compute the layer output.
 
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 softmax loss error gradient w.r.t. the predictions. 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.
 
virtual Dtype get_normalizer (LossParameter_NormalizationMode normalization_mode, int valid_count)
 
- 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

shared_ptr< Layer< Dtype > > softmax_layer_
 The internal SoftmaxLayer used to map predictions to a distribution.
 
Blob< Dtype > prob_
 prob stores the output probability predictions from the SoftmaxLayer.
 
vector< Blob< Dtype > * > softmax_bottom_vec_
 bottom vector holder used in call to the underlying SoftmaxLayer::Forward
 
vector< Blob< Dtype > * > softmax_top_vec_
 top vector holder used in call to the underlying SoftmaxLayer::Forward
 
bool has_ignore_label_
 Whether to ignore instances with a certain label.
 
int ignore_label_
 The label indicating that an instance should be ignored.
 
LossParameter_NormalizationMode normalization_
 How to normalize the output loss.
 
int softmax_axis_
 
int outer_num_
 
int inner_num_
 
- 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::SoftmaxWithLossLayer< Dtype >

Computes the multinomial logistic loss for a one-of-many classification task, passing real-valued predictions through a softmax to get a probability distribution over classes.

This layer should be preferred over separate SoftmaxLayer + MultinomialLogisticLossLayer as its gradient computation is more numerically stable. At test time, this layer can be replaced simply by a SoftmaxLayer.

Parameters
bottominput Blob vector (length 2)
  1. $ (N \times C \times H \times W) $ the predictions $ x $, a Blob with values in $ [-\infty, +\infty] $ indicating the predicted score for each of the $ K = CHW $ classes. This layer maps these scores to a probability distribution over classes using the softmax function $ \hat{p}_{nk} = \exp(x_{nk}) / \left[\sum_{k'} \exp(x_{nk'})\right] $ (see SoftmaxLayer).
  2. $ (N \times 1 \times 1 \times 1) $ the labels $ l $, an integer-valued Blob with values $ l_n \in [0, 1, 2, ..., K - 1] $ indicating the correct class label among the $ K $ classes
topoutput Blob vector (length 1)
  1. $ (1 \times 1 \times 1 \times 1) $ the computed cross-entropy classification loss: $ E = \frac{-1}{N} \sum\limits_{n=1}^N \log(\hat{p}_{n,l_n}) $, for softmax output class probabilites $ \hat{p} $

Constructor & Destructor Documentation

§ SoftmaxWithLossLayer()

template<typename Dtype >
caffe::SoftmaxWithLossLayer< Dtype >::SoftmaxWithLossLayer ( const LayerParameter &  param)
inlineexplicit
Parameters
paramprovides LossParameter loss_param, with options:
  • ignore_label (optional) Specify a label value that should be ignored when computing the loss.
  • normalize (optional, default true) If true, the loss is normalized by the number of (nonignored) labels present; otherwise the loss is simply summed over spatial locations.

Member Function Documentation

§ Backward_cpu()

template<typename Dtype >
void caffe::SoftmaxWithLossLayer< Dtype >::Backward_cpu ( const vector< Blob< Dtype > *> &  top,
const vector< bool > &  propagate_down,
const vector< Blob< Dtype > *> &  bottom 
)
protectedvirtual

Computes the softmax loss error gradient w.r.t. the predictions.

Gradients cannot be computed with respect to the label inputs (bottom[1]), so this method ignores bottom[1] and requires !propagate_down[1], crashing if propagate_down[1] is set.

Parameters
topoutput Blob vector (length 1), providing the error gradient with respect to the outputs
  1. $ (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_downsee Layer::Backward. propagate_down[1] must be false as we can't compute gradients with respect to the labels.
bottominput Blob vector (length 2)
  1. $ (N \times C \times H \times W) $ the predictions $ x $; Backward computes diff $ \frac{\partial E}{\partial x} $
  2. $ (N \times 1 \times 1 \times 1) $ the labels – ignored as we can't compute their error gradients

Implements caffe::Layer< Dtype >.

§ ExactNumTopBlobs()

template<typename Dtype >
virtual int caffe::SoftmaxWithLossLayer< Dtype >::ExactNumTopBlobs ( ) const
inlinevirtual

Returns the exact number of top blobs required by the layer, or -1 if no exact number is required.

This method should be overridden to return a non-negative value if your layer expects some exact number of top blobs.

Reimplemented from caffe::LossLayer< Dtype >.

§ get_normalizer()

template<typename Dtype >
Dtype caffe::SoftmaxWithLossLayer< Dtype >::get_normalizer ( LossParameter_NormalizationMode  normalization_mode,
int  valid_count 
)
protectedvirtual

Read the normalization mode parameter and compute the normalizer based on the blob size. If normalization_mode is VALID, the count of valid outputs will be read from valid_count, unless it is -1 in which case all outputs are assumed to be valid.

§ LayerSetUp()

template<typename Dtype >
void caffe::SoftmaxWithLossLayer< Dtype >::LayerSetUp ( const vector< Blob< Dtype > *> &  bottom,
const vector< Blob< Dtype > *> &  top 
)
virtual

Does layer-specific setup: your layer should implement this function as well as Reshape.

Parameters
bottomthe preshaped input blobs, whose data fields store the input data for this layer
topthe allocated but unshaped output blobs

This method should do one-time layer specific setup. This includes reading and processing relevent parameters from the layer_param_. Setting up the shapes of top blobs and internal buffers should be done in Reshape, which will be called before the forward pass to adjust the top blob sizes.

Reimplemented from caffe::LossLayer< Dtype >.

§ MaxTopBlobs()

template<typename Dtype >
virtual int caffe::SoftmaxWithLossLayer< Dtype >::MaxTopBlobs ( ) const
inlinevirtual

Returns the maximum number of top blobs required by the layer, or -1 if no maximum number is required.

This method should be overridden to return a non-negative value if your layer expects some maximum number of top blobs.

Reimplemented from caffe::Layer< Dtype >.

§ MinTopBlobs()

template<typename Dtype >
virtual int caffe::SoftmaxWithLossLayer< Dtype >::MinTopBlobs ( ) const
inlinevirtual

Returns the minimum number of top blobs required by the layer, or -1 if no minimum number is required.

This method should be overridden to return a non-negative value if your layer expects some minimum number of top blobs.

Reimplemented from caffe::Layer< Dtype >.

§ Reshape()

template<typename Dtype >
void caffe::SoftmaxWithLossLayer< 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
bottomthe input blobs, with the requested input shapes
topthe 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: