Caffe
Public Member Functions | Protected Member Functions | List of all members
caffe::PythonLayer< Dtype > Class Template Reference
Inheritance diagram for caffe::PythonLayer< Dtype >:

Public Member Functions

  PythonLayer (PyObject *self, 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.
 
- 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  ExactNumBottomBlobs () const
  Returns the exact number of bottom blobs required by the layer, or -1 if no exact number is required. More...
 
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  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...
 
virtual bool  EqualNumBottomTopBlobs () const
  Returns true if the layer requires an equal number of bottom and top blobs. More...
 
virtual bool  AutoTopBlobs () const
  Return whether "anonymous" top blobs are created automatically by the layer. More...
 
virtual bool  AllowForceBackward (const int bottom_index) const
  Return whether to allow force_backward for a given bottom blob index. 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  Backward_cpu (const vector< Blob< Dtype > *> &top, const vector< bool > &propagate_down, const vector< Blob< Dtype > *> &bottom)
  Using the CPU device, compute the gradients for any parameters and for the bottom blobs if propagate_down is true.
 
- Protected Member Functions inherited from caffe::Layer< Dtype >
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_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 void  CheckBlobCounts (const vector< Blob< Dtype > *> &bottom, const vector< Blob< Dtype > *> &top)
 
void  SetLossWeights (const vector< Blob< Dtype > *> &top)
 

Additional Inherited Members

- 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_
 

Member Function Documentation

LayerSetUp()

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

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

Parameters
bottom the preshaped input blobs, whose data fields store the input data for this layer
top the 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::Layer< Dtype >.

Reshape()

template<typename Dtype >
virtual void caffe::PythonLayer< Dtype >::Reshape ( const vector< Blob< Dtype > *> &  bottom,
const vector< Blob< Dtype > *> &  top 
)
inlinevirtual

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.

Implements caffe::Layer< Dtype >.


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

Generated on Thu Aug 3 2017 23:11:28 for Caffe by   doxygen 1.8.13

AltStyle によって変換されたページ (->オリジナル) /