ConvNet
1.0
A GPU-based C++ implementation of Convolutional Neural Nets
|
Implements a layer with a softmax activation function. More...
#include <layer.h>
Public Member Functions | |
SoftmaxDistLayer (const config::Layer &config) | |
virtual void | AllocateMemory (int imgsize, int batch_size) |
Allocate memory for storing the state and derivative at this layer. More... | |
virtual void | ComputeDeriv () |
Compute derivative of loss function. More... | |
virtual float | GetLoss () |
Compute the value of the loss function that is displayed during training. More... | |
Public Member Functions inherited from SoftmaxLayer | |
SoftmaxLayer (const config::Layer &config) | |
virtual void | ApplyActivation (bool train) |
Apply the activation function. More... | |
virtual void | ApplyDerivativeOfActivation () |
Apply the derivative of the activation. More... | |
virtual float | GetLoss2 () |
Compute the value of the actual loss function. More... | |
Public Member Functions inherited from Layer | |
Layer (const config::Layer &config) | |
Instantiate a layer from config. More... | |
void | ApplyDropout (bool train) |
Apply dropout to this layer. More... | |
void | ApplyDerivativeofDropout () |
Apply derivative of dropout. More... | |
void | AccessStateBegin () |
void | AccessStateEnd () |
void | AccessDerivBegin () |
void | AccessDerivEnd () |
Edge * | GetIncomingEdge (int index) |
Returns the incoming edge by index. More... | |
Matrix & | GetState () |
Returns a reference to the state of the layer. More... | |
Matrix & | GetDeriv () |
Returns a reference to the deriv at this layer. More... | |
Matrix & | GetData () |
Returns a reference to the data at this layer. More... | |
void | Display () |
void | Display (int image_id) |
void | AddIncoming (Edge *e) |
Add an incoming edge to this layer. More... | |
void | AddOutgoing (Edge *e) |
Add an outgoing edge from this layer. More... | |
const string & | GetName () const |
int | GetNumChannels () const |
int | GetSize () const |
bool | IsInput () const |
bool | IsOutput () const |
int | GetGPUId () const |
void | AllocateMemoryOnOtherGPUs () |
Matrix & | GetOtherState (int gpu_id) |
Matrix & | GetOtherDeriv (int gpu_id) |
void | SyncIncomingState () |
void | SyncOutgoingState () |
void | SyncIncomingDeriv () |
void | SyncOutgoingDeriv () |
Additional Inherited Members | |
Static Public Member Functions inherited from Layer | |
static Layer * | ChooseLayerClass (const config::Layer &layer_config) |
Public Attributes inherited from Layer | |
vector< Edge * > | incoming_edge_ |
vector< Edge * > | outgoing_edge_ |
bool | has_incoming_from_same_gpu_ |
bool | has_outgoing_to_same_gpu_ |
bool | has_incoming_from_other_gpus_ |
bool | has_outgoing_to_other_gpus_ |
Protected Member Functions inherited from Layer | |
void | ApplyDropoutAtTrainTime () |
void | ApplyDropoutAtTestTime () |
Protected Attributes inherited from Layer | |
const string | name_ |
const int | num_channels_ |
const bool | is_input_ |
const bool | is_output_ |
const float | dropprob_ |
const bool | display_ |
const bool | dropout_scale_up_at_train_time_ |
const bool | gaussian_dropout_ |
const float | max_act_gaussian_dropout_ |
int | scale_targets_ |
int | image_size_ |
Matrix | state_ |
Matrix | deriv_ |
State (activation) of the layer. More... | |
Matrix | data_ |
Deriv of the loss function w.r.t. More... | |
Matrix | rand_gaussian_ |
Data (targets) associated with this layer. More... | |
map< int, Matrix > | other_states_ |
Need to store random variates when doing gaussian dropout. More... | |
map< int, Matrix > | other_derivs_ |
Copies of this layer's state on other gpus. More... | |
ImageDisplayer * | img_display_ |
Copies of this layer's deriv on other gpus. More... | |
const int | gpu_id_ |
set< int > | other_incoming_gpu_ids_ |
set< int > | other_outgoing_gpu_ids_ |
Implements a layer with a softmax activation function.
This must be an output layer. The target must be a distribution over K choices.
|
virtual |
Allocate memory for storing the state and derivative at this layer.
imgsize | The spatial size of the layer (width and height). |
batch_size | The mini-batch size. |
Reimplemented from SoftmaxLayer.
|
virtual |
Compute derivative of loss function.
This is applicable only if this layer is an output layer.
Reimplemented from SoftmaxLayer.
|
virtual |
Compute the value of the loss function that is displayed during training.
This is applicable only if this layer is an output layer.
Reimplemented from SoftmaxLayer.