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

Computes the contrastive loss $ E = \frac{1}{2N} \sum\limits_{n=1}^N \left(y\right) d^2 + \left(1-y\right) \max \left(margin-d, 0\right)^2 $ where $ d = \left| \left| a_n - b_n \right| \right|_2 $. This can be used to train siamese networks. More...

#include <contrastive_loss_layer.hpp>

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

Public Member Functions

 ContrastiveLossLayer (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 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 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 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 contrastive loss $ E = \frac{1}{2N} \sum\limits_{n=1}^N \left(y\right) d^2 + \left(1-y\right) \max \left(margin-d, 0\right)^2 $ where $ d = \left| \left| a_n - b_n \right| \right|_2 $. This can be used to train siamese networks. 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 Contrastive 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_
 
Blob< Dtype > dist_sq_
 
Blob< Dtype > diff_sq_
 
Blob< Dtype > summer_vec_
 
- 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::ContrastiveLossLayer< Dtype >

Computes the contrastive loss $ E = \frac{1}{2N} \sum\limits_{n=1}^N \left(y\right) d^2 + \left(1-y\right) \max \left(margin-d, 0\right)^2 $ where $ d = \left| \left| a_n - b_n \right| \right|_2 $. This can be used to train siamese networks.

Parameters
bottominput Blob vector (length 3)
  1. $ (N \times C \times 1 \times 1) $ the features $ a \in [-\infty, +\infty]$
  2. $ (N \times C \times 1 \times 1) $ the features $ b \in [-\infty, +\infty]$
  3. $ (N \times 1 \times 1 \times 1) $ the binary similarity $ s \in [0, 1]$
topoutput Blob vector (length 1)
  1. $ (1 \times 1 \times 1 \times 1) $ the computed contrastive loss: $ E = \frac{1}{2N} \sum\limits_{n=1}^N \left(y\right) d^2 + \left(1-y\right) \max \left(margin-d, 0\right)^2 $ where $ d = \left| \left| a_n - b_n \right| \right|_2 $. This can be used to train siamese networks.

Member Function Documentation

§ AllowForceBackward()

template<typename Dtype >
virtual bool caffe::ContrastiveLossLayer< Dtype >::AllowForceBackward ( const int  bottom_index) const
inlinevirtual

Unlike most loss layers, in the ContrastiveLossLayer we can backpropagate to the first two inputs.

Reimplemented from caffe::LossLayer< Dtype >.

§ Backward_cpu()

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

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

Computes the gradients with respect to the two input vectors (bottom[0] and bottom[1]), but not the similarity label (bottom[2]).

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.
bottominput Blob vector (length 2)
  1. $ (N \times C \times 1 \times 1) $ the features $a$; Backward fills their diff with gradients if propagate_down[0]
  2. $ (N \times C \times 1 \times 1) $ the features $b$; Backward fills their diff with gradients if propagate_down[1]

Implements caffe::Layer< Dtype >.

§ ExactNumBottomBlobs()

template<typename Dtype >
virtual int caffe::ContrastiveLossLayer< Dtype >::ExactNumBottomBlobs ( ) const
inlinevirtual

Returns the exact number of bottom 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 bottom blobs.

Reimplemented from caffe::LossLayer< Dtype >.

§ Forward_cpu()

template<typename Dtype >
void caffe::ContrastiveLossLayer< Dtype >::Forward_cpu ( const vector< Blob< Dtype > *> &  bottom,
const vector< Blob< Dtype > *> &  top 
)
protectedvirtual

Computes the contrastive loss $ E = \frac{1}{2N} \sum\limits_{n=1}^N \left(y\right) d^2 + \left(1-y\right) \max \left(margin-d, 0\right)^2 $ where $ d = \left| \left| a_n - b_n \right| \right|_2 $. This can be used to train siamese networks.

Parameters
bottominput Blob vector (length 3)
  1. $ (N \times C \times 1 \times 1) $ the features $ a \in [-\infty, +\infty]$
  2. $ (N \times C \times 1 \times 1) $ the features $ b \in [-\infty, +\infty]$
  3. $ (N \times 1 \times 1 \times 1) $ the binary similarity $ s \in [0, 1]$
topoutput Blob vector (length 1)
  1. $ (1 \times 1 \times 1 \times 1) $ the computed contrastive loss: $ E = \frac{1}{2N} \sum\limits_{n=1}^N \left(y\right) d^2 + \left(1-y\right) \max \left(margin-d, 0\right)^2 $ where $ d = \left| \left| a_n - b_n \right| \right|_2 $. This can be used to train siamese networks.

Implements caffe::Layer< Dtype >.

§ LayerSetUp()

template<typename Dtype >
void caffe::ContrastiveLossLayer< 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 >.


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