A layer factory that allows one to register layers. During runtime, registered layers can be called by passing a LayerParameter protobuffer to the CreateLayer function: More...

Namespaces
	SolverAction
	Enumeration of actions that a client of the Solver may request by implementing the Solver's action request function, which a client may optionally provide in order to request early termination or saving a snapshot without exiting. In the executable caffe, this mechanism is used to allow the snapshot to be saved when stopping execution with a SIGINT (Ctrl-C).

Classes
class	AbsValLayer
	Computes . More...

class	AccuracyLayer
	Computes the classification accuracy for a one-of-many classification task. More...

class	AdaDeltaSolver

class	AdaGradSolver

class	AdamSolver
	AdamSolver, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. Described in [1]. More...

class	ArgMaxLayer
	Compute the index of the max values for each datum across all dimensions $(C \times H \times W)$ . More...

class	BaseConvolutionLayer
	Abstract base class that factors out the BLAS code common to ConvolutionLayer and DeconvolutionLayer. More...

class	BaseDataLayer
	Provides base for data layers that feed blobs to the Net. More...

class	BasePrefetchingDataLayer

class	Batch

class	BatchNormLayer
	Normalizes the input to have 0-mean and/or unit (1) variance across the batch. More...

class	BatchReindexLayer
	Index into the input blob along its first axis. More...

class	BiasLayer
	Computes a sum of two input Blobs, with the shape of the latter Blob "broadcast" to match the shape of the former. Equivalent to tiling the latter Blob, then computing the elementwise sum. More...

class	BilinearFiller
	Fills a Blob with coefficients for bilinear interpolation. More...

class	Blob
	A wrapper around SyncedMemory holders serving as the basic computational unit through which Layers, Nets, and Solvers interact. More...

class	BlockingQueue

class	BNLLLayer
	Computes $y = x + \log(1 + \exp(-x))$ if ; $y = \log(1 + \exp(x))$ otherwise. More...

class	Caffe

class	ConcatLayer
	Takes at least two Blobs and concatenates them along either the num or channel dimension, outputting the result. More...

class	ConstantFiller
	Fills a Blob with constant values . More...

class	ContrastiveLossLayer
	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...

class	ConvolutionLayer
	Convolves the input image with a bank of learned filters, and (optionally) adds biases. More...

class	CPUTimer

class	CropLayer
	Takes a Blob and crop it, to the shape specified by the second input Blob, across all dimensions after the specified axis. More...

class	DataLayer

class	DataTransformer
	Applies common transformations to the input data, such as scaling, mirroring, substracting the image mean... More...

class	DeconvolutionLayer
	Convolve the input with a bank of learned filters, and (optionally) add biases, treating filters and convolution parameters in the opposite sense as ConvolutionLayer. More...

class	DropoutLayer
	During training only, sets a random portion of to 0, adjusting the rest of the vector magnitude accordingly. More...

class	DummyDataLayer
	Provides data to the Net generated by a Filler. More...

class	EltwiseLayer
	Compute elementwise operations, such as product and sum, along multiple input Blobs. More...

class	ELULayer
	Exponential Linear Unit non-linearity $y = \left\{ \begin{array}{lr} x & \mathrm{if} \; x > 0 \\ \alpha (\exp(x)-1) & \mathrm{if} \; x \le 0 \end{array} \right.$ . More...

class	EmbedLayer
	A layer for learning "embeddings" of one-hot vector input. Equivalent to an InnerProductLayer with one-hot vectors as input, but for efficiency the input is the "hot" index of each column itself. More...

class	EuclideanLossLayer
	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...

class	ExpLayer
	Computes $y = \gamma ^ {\alpha x + \beta}$ , as specified by the scale $\alpha$ , shift $\beta$ , and base $\gamma$ . More...

class	Filler
	Fills a Blob with constant or randomly-generated data. More...

class	FilterLayer
	Takes two+ Blobs, interprets last Blob as a selector and filter remaining Blobs accordingly with selector data (0 means that the corresponding item has to be filtered, non-zero means that corresponding item needs to stay). More...

class	FlattenLayer
	Reshapes the input Blob into flat vectors. More...

class	GaussianFiller
	Fills a Blob with Gaussian-distributed values . More...

class	HDF5DataLayer
	Provides data to the Net from HDF5 files. More...

class	HDF5OutputLayer
	Write blobs to disk as HDF5 files. More...

class	HingeLossLayer
	Computes the hinge loss for a one-of-many classification task. More...

class	Im2colLayer
	A helper for image operations that rearranges image regions into column vectors. Used by ConvolutionLayer to perform convolution by matrix multiplication. More...

class	ImageDataLayer
	Provides data to the Net from image files. More...

class	InfogainLossLayer
	A generalization of MultinomialLogisticLossLayer that takes an "information gain" (infogain) matrix specifying the "value" of all label pairs. More...

class	InnerProductLayer
	Also known as a "fully-connected" layer, computes an inner product with a set of learned weights, and (optionally) adds biases. More...

class	InputLayer
	Provides data to the Net by assigning tops directly. More...

class	InternalThread

class	Layer
	An interface for the units of computation which can be composed into a Net. More...

class	LayerRegisterer

class	LayerRegistry

class	LogLayer
	Computes $y = log_{\gamma}(\alpha x + \beta)$ , as specified by the scale $\alpha$ , shift $\beta$ , and base $\gamma$ . More...

class	LossLayer
	An interface for Layers that take two Blobs as input – usually (1) predictions and (2) ground-truth labels – and output a singleton Blob representing the loss. More...

class	LRNLayer
	Normalize the input in a local region across or within feature maps. More...

class	LSTMLayer
	Processes sequential inputs using a "Long Short-Term Memory" (LSTM) [1] style recurrent neural network (RNN). Implemented by unrolling the LSTM computation through time. More...

class	LSTMUnitLayer
	A helper for LSTMLayer: computes a single timestep of the non-linearity of the LSTM, producing the updated cell and hidden states. More...

class	MemoryDataLayer
	Provides data to the Net from memory. More...

class	MSRAFiller
	Fills a Blob with values $x \sim N(0, \sigma^2)$ where $\sigma^2$ is set inversely proportional to number of incoming nodes, outgoing nodes, or their average. More...

class	MultinomialLogisticLossLayer
	Computes the multinomial logistic loss for a one-of-many classification task, directly taking a predicted probability distribution as input. More...

class	MVNLayer
	Normalizes the input to have 0-mean and/or unit (1) variance. More...

class	NesterovSolver

class	Net
	Connects Layers together into a directed acyclic graph (DAG) specified by a NetParameter. More...

class	NeuronLayer
	An interface for layers that take one blob as input ( ) and produce one equally-sized blob as output ( ), where each element of the output depends only on the corresponding input element. More...

class	ParameterLayer

class	PoolingLayer
	Pools the input image by taking the max, average, etc. within regions. More...

class	PositiveUnitballFiller
	Fills a Blob with values $x \in [0, 1]$ such that $\forall i \sum_j x_{ij} = 1$ . More...

class	PowerLayer
	Computes $y = (\alpha x + \beta) ^ \gamma$ , as specified by the scale $\alpha$ , shift $\beta$ , and power $\gamma$ . More...

class	PReLULayer
	Parameterized Rectified Linear Unit non-linearity $y_i = \max(0, x_i) + a_i \min(0, x_i)$ . The differences from ReLULayer are 1) negative slopes are learnable though backprop and 2) negative slopes can vary across channels. The number of axes of input blob should be greater than or equal to 2. The 1st axis (0-based) is seen as channels. More...

class	PythonLayer

class	RecurrentLayer
	An abstract class for implementing recurrent behavior inside of an unrolled network. This Layer type cannot be instantiated – instead, you should use one of its implementations which defines the recurrent architecture, such as RNNLayer or LSTMLayer. More...

class	ReductionLayer
	Compute "reductions" – operations that return a scalar output Blob for an input Blob of arbitrary size, such as the sum, absolute sum, and sum of squares. More...

class	ReLULayer
	Rectified Linear Unit non-linearity $y = \max(0, x)$ . The simple max is fast to compute, and the function does not saturate. More...

class	ReshapeLayer

class	RMSPropSolver

class	RNNLayer
	Processes time-varying inputs using a simple recurrent neural network (RNN). Implemented as a network unrolling the RNN computation in time. More...

class	ScaleLayer
	Computes the elementwise product of two input Blobs, with the shape of the latter Blob "broadcast" to match the shape of the former. Equivalent to tiling the latter Blob, then computing the elementwise product. Note: for efficiency and convenience, this layer can additionally perform a "broadcast" sum too when `bias_term: true` is set. More...

class	SGDSolver
	Optimizes the parameters of a Net using stochastic gradient descent (SGD) with momentum. More...

class	SigmoidCrossEntropyLossLayer
	Computes the cross-entropy (logistic) loss $E = \frac{-1}{n} \sum\limits_{n=1}^N \left[ p_n \log \hat{p}_n + (1 - p_n) \log(1 - \hat{p}_n) \right]$ , often used for predicting targets interpreted as probabilities. More...

class	SigmoidLayer
	Sigmoid function non-linearity $y = (1 + \exp(-x))^{-1}$ , a classic choice in neural networks. More...

class	SignalHandler

class	SilenceLayer
	Ignores bottom blobs while producing no top blobs. (This is useful to suppress outputs during testing.) More...

class	SliceLayer
	Takes a Blob and slices it along either the num or channel dimension, outputting multiple sliced Blob results. More...

class	SoftmaxLayer
	Computes the softmax function. More...

class	SoftmaxWithLossLayer
	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...

class	Solver
	An interface for classes that perform optimization on Nets. More...

class	SolverRegisterer

class	SolverRegistry

class	SplitLayer
	Creates a "split" path in the network by copying the bottom Blob into multiple top Blobs to be used by multiple consuming layers. More...

class	SPPLayer
	Does spatial pyramid pooling on the input image by taking the max, average, etc. within regions so that the result vector of different sized images are of the same size. More...

class	SyncedMemory
	Manages memory allocation and synchronization between the host (CPU) and device (GPU). More...

class	TanHLayer
	TanH hyperbolic tangent non-linearity $y = \frac{\exp(2x) - 1}{\exp(2x) + 1}$ , popular in auto-encoders. More...

class	ThresholdLayer
	Tests whether the input exceeds a threshold: outputs 1 for inputs above threshold; 0 otherwise. More...

class	TileLayer
	Copy a Blob along specified dimensions. More...

class	Timer

class	UniformFiller
	Fills a Blob with uniformly distributed values $x\sim U(a, b)$ . More...

class	WindowDataLayer
	Provides data to the Net from windows of images files, specified by a window data file. This layer is DEPRECATED and only kept for archival purposes for use by the original R-CNN. More...

class	XavierFiller
	Fills a Blob with values $x \sim U(-a, +a)$ where is set inversely proportional to number of incoming nodes, outgoing nodes, or their average. More...

Typedefs
typedef boost::function< SolverAction::Enum()>	ActionCallback
	Type of a function that returns a Solver Action enumeration.

typedef boost::mt19937	rng_t

Functions
void	GlobalInit (int pargc, char **pargv)

template<typename Dtype >
Filler< Dtype > *	GetFiller (const FillerParameter &param)
	Get a specific filler from the specification given in FillerParameter. More...

void	CaffeMallocHost (void *ptr, size_t size, bool use_cuda)

void	CaffeFreeHost (void *ptr, bool use_cuda)

const char *	cublasGetErrorString (cublasStatus_t error)

const char *	curandGetErrorString (curandStatus_t error)

int	CAFFE_GET_BLOCKS (const int N)

std::string	format_int (int n, int numberOfLeadingZeros=0)

template<typename Dtype >
void	hdf5_load_nd_dataset_helper (hid_t file_id, const char dataset_name_, int min_dim, int max_dim, Blob< Dtype > blob, bool reshape)

template<typename Dtype >
void	hdf5_load_nd_dataset (hid_t file_id, const char dataset_name_, int min_dim, int max_dim, Blob< Dtype > blob, bool reshape=false)

template<typename Dtype >
void	hdf5_save_nd_dataset (const hid_t file_id, const string &dataset_name, const Blob< Dtype > &blob, bool write_diff=false)

int	hdf5_load_int (hid_t loc_id, const string &dataset_name)

void	hdf5_save_int (hid_t loc_id, const string &dataset_name, int i)

string	hdf5_load_string (hid_t loc_id, const string &dataset_name)

void	hdf5_save_string (hid_t loc_id, const string &dataset_name, const string &s)

int	hdf5_get_num_links (hid_t loc_id)

string	hdf5_get_name_by_idx (hid_t loc_id, int idx)

template<typename Dtype >
void	im2col_nd_cpu (const Dtype data_im, const int num_spatial_axes, const int im_shape, const int col_shape, const int kernel_shape, const int pad, const int stride, const int dilation, Dtype data_col)

template<typename Dtype >
void	im2col_cpu (const Dtype data_im, const int channels, const int height, const int width, const int kernel_h, const int kernel_w, const int pad_h, const int pad_w, const int stride_h, const int stride_w, const int dilation_h, const int dilation_w, Dtype data_col)

template<typename Dtype >
void	col2im_nd_cpu (const Dtype data_col, const int num_spatial_axes, const int im_shape, const int col_shape, const int kernel_shape, const int pad, const int stride, const int dilation, Dtype data_im)

template<typename Dtype >
void	col2im_cpu (const Dtype data_col, const int channels, const int height, const int width, const int kernel_h, const int kernel_w, const int pad_h, const int pad_w, const int stride_h, const int stride_w, const int dilation_h, const int dilation_w, Dtype data_im)

template<typename Dtype >
void	im2col_nd_gpu (const Dtype data_im, const int num_spatial_axes, const int col_size, const int im_shape, const int col_shape, const int kernel_shape, const int pad, const int stride, const int dilation, Dtype data_col)

template<typename Dtype >
void	im2col_gpu (const Dtype data_im, const int channels, const int height, const int width, const int kernel_h, const int kernel_w, const int pad_h, const int pad_w, const int stride_h, const int stride_w, const int dilation_h, const int dilation_w, Dtype data_col)

template<typename Dtype >
void	col2im_nd_gpu (const Dtype data_col, const int num_spatial_axes, const int im_size, const int im_shape, const int col_shape, const int kernel_shape, const int pad, const int stride, const int dilation, Dtype data_im)

template<typename Dtype >
void	col2im_gpu (const Dtype data_col, const int channels, const int height, const int width, const int kernel_h, const int kernel_w, const int pad_h, const int pad_w, const int stride_h, const int stride_w, const int dilation_h, const int dilation_w, Dtype data_im)

void	InsertSplits (const NetParameter &param, NetParameter *param_split)

void	ConfigureSplitLayer (const string &layer_name, const string &blob_name, const int blob_idx, const int split_count, const float loss_weight, LayerParameter *split_layer_param)

string	SplitLayerName (const string &layer_name, const string &blob_name, const int blob_idx)

string	SplitBlobName (const string &layer_name, const string &blob_name, const int blob_idx, const int split_idx)

void	MakeTempDir (string *temp_dirname)

void	MakeTempFilename (string *temp_filename)

bool	ReadProtoFromTextFile (const char filename, Message proto)

bool	ReadProtoFromTextFile (const string &filename, Message *proto)

void	ReadProtoFromTextFileOrDie (const char filename, Message proto)

void	ReadProtoFromTextFileOrDie (const string &filename, Message *proto)

void	WriteProtoToTextFile (const Message &proto, const char *filename)

void	WriteProtoToTextFile (const Message &proto, const string &filename)

bool	ReadProtoFromBinaryFile (const char filename, Message proto)

bool	ReadProtoFromBinaryFile (const string &filename, Message *proto)

void	ReadProtoFromBinaryFileOrDie (const char filename, Message proto)

void	ReadProtoFromBinaryFileOrDie (const string &filename, Message *proto)

void	WriteProtoToBinaryFile (const Message &proto, const char *filename)

void	WriteProtoToBinaryFile (const Message &proto, const string &filename)

bool	ReadFileToDatum (const string &filename, const int label, Datum *datum)

bool	ReadFileToDatum (const string &filename, Datum *datum)

bool	ReadImageToDatum (const string &filename, const int label, const int height, const int width, const bool is_color, const std::string &encoding, Datum *datum)

bool	ReadImageToDatum (const string &filename, const int label, const int height, const int width, const bool is_color, Datum *datum)

bool	ReadImageToDatum (const string &filename, const int label, const int height, const int width, Datum *datum)

bool	ReadImageToDatum (const string &filename, const int label, const bool is_color, Datum *datum)

bool	ReadImageToDatum (const string &filename, const int label, Datum *datum)

bool	ReadImageToDatum (const string &filename, const int label, const std::string &encoding, Datum *datum)

bool	DecodeDatumNative (Datum *datum)

bool	DecodeDatum (Datum *datum, bool is_color)

template<typename Dtype >
void	caffe_cpu_gemm (const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB, const int M, const int N, const int K, const Dtype alpha, const Dtype A, const Dtype B, const Dtype beta, Dtype *C)

template<typename Dtype >
void	caffe_cpu_gemv (const CBLAS_TRANSPOSE TransA, const int M, const int N, const Dtype alpha, const Dtype A, const Dtype x, const Dtype beta, Dtype *y)

template<typename Dtype >
void	caffe_axpy (const int N, const Dtype alpha, const Dtype X, Dtype Y)

template<typename Dtype >
void	caffe_cpu_axpby (const int N, const Dtype alpha, const Dtype X, const Dtype beta, Dtype Y)

template<typename Dtype >
void	caffe_copy (const int N, const Dtype X, Dtype Y)

template<typename Dtype >
void	caffe_set (const int N, const Dtype alpha, Dtype *X)

void	caffe_memset (const size_t N, const int alpha, void *X)

template<typename Dtype >
void	caffe_add_scalar (const int N, const Dtype alpha, Dtype *X)

template<typename Dtype >
void	caffe_scal (const int N, const Dtype alpha, Dtype *X)

template<typename Dtype >
void	caffe_sqr (const int N, const Dtype a, Dtype y)

template<typename Dtype >
void	caffe_sqrt (const int N, const Dtype a, Dtype y)

template<typename Dtype >
void	caffe_add (const int N, const Dtype a, const Dtype b, Dtype *y)

template<typename Dtype >
void	caffe_sub (const int N, const Dtype a, const Dtype b, Dtype *y)

template<typename Dtype >
void	caffe_mul (const int N, const Dtype a, const Dtype b, Dtype *y)

template<typename Dtype >
void	caffe_div (const int N, const Dtype a, const Dtype b, Dtype *y)

template<typename Dtype >
void	caffe_powx (const int n, const Dtype a, const Dtype b, Dtype y)

unsigned int	caffe_rng_rand ()

template<typename Dtype >
Dtype	caffe_nextafter (const Dtype b)

template<typename Dtype >
void	caffe_rng_uniform (const int n, const Dtype a, const Dtype b, Dtype *r)

template<typename Dtype >
void	caffe_rng_gaussian (const int n, const Dtype mu, const Dtype sigma, Dtype *r)

template<typename Dtype >
void	caffe_rng_bernoulli (const int n, const Dtype p, int *r)

template<typename Dtype >
void	caffe_rng_bernoulli (const int n, const Dtype p, unsigned int *r)

template<typename Dtype >
void	caffe_exp (const int n, const Dtype a, Dtype y)

template<typename Dtype >
void	caffe_log (const int n, const Dtype a, Dtype y)

template<typename Dtype >
void	caffe_abs (const int n, const Dtype a, Dtype y)

template<typename Dtype >
Dtype	caffe_cpu_dot (const int n, const Dtype x, const Dtype y)

template<typename Dtype >
Dtype	caffe_cpu_strided_dot (const int n, const Dtype x, const int incx, const Dtype y, const int incy)

template<typename Dtype >
Dtype	caffe_cpu_asum (const int n, const Dtype *x)

template<typename Dtype >
int8_t	caffe_sign (Dtype val)

	DEFINE_CAFFE_CPU_UNARY_FUNC (sgnbit, y[i]=static_cast< bool >((std::signbit)(x[i]))) template< typename Dtype > void caffe_cpu_scale(const int n

template<typename Dtype >
void	caffe_gpu_gemm (const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB, const int M, const int N, const int K, const Dtype alpha, const Dtype A, const Dtype B, const Dtype beta, Dtype *C)

template<typename Dtype >
void	caffe_gpu_gemv (const CBLAS_TRANSPOSE TransA, const int M, const int N, const Dtype alpha, const Dtype A, const Dtype x, const Dtype beta, Dtype *y)

template<typename Dtype >
void	caffe_gpu_axpy (const int N, const Dtype alpha, const Dtype X, Dtype Y)

template<typename Dtype >
void	caffe_gpu_axpby (const int N, const Dtype alpha, const Dtype X, const Dtype beta, Dtype Y)

void	caffe_gpu_memcpy (const size_t N, const void X, void Y)

template<typename Dtype >
void	caffe_gpu_set (const int N, const Dtype alpha, Dtype *X)

void	caffe_gpu_memset (const size_t N, const int alpha, void *X)

template<typename Dtype >
void	caffe_gpu_add_scalar (const int N, const Dtype alpha, Dtype *X)

template<typename Dtype >
void	caffe_gpu_scal (const int N, const Dtype alpha, Dtype *X)

template<typename Dtype >
void	caffe_gpu_scal (const int N, const Dtype alpha, Dtype *X, cudaStream_t str)

template<typename Dtype >
void	caffe_gpu_add (const int N, const Dtype a, const Dtype b, Dtype *y)

template<typename Dtype >
void	caffe_gpu_sub (const int N, const Dtype a, const Dtype b, Dtype *y)

template<typename Dtype >
void	caffe_gpu_mul (const int N, const Dtype a, const Dtype b, Dtype *y)

template<typename Dtype >
void	caffe_gpu_div (const int N, const Dtype a, const Dtype b, Dtype *y)

template<typename Dtype >
void	caffe_gpu_abs (const int n, const Dtype a, Dtype y)

template<typename Dtype >
void	caffe_gpu_exp (const int n, const Dtype a, Dtype y)

template<typename Dtype >
void	caffe_gpu_log (const int n, const Dtype a, Dtype y)

template<typename Dtype >
void	caffe_gpu_powx (const int n, const Dtype a, const Dtype b, Dtype y)

template<typename Dtype >
void	caffe_gpu_sqrt (const int n, const Dtype a, Dtype y)

void	caffe_gpu_rng_uniform (const int n, unsigned int *r)

template<typename Dtype >
void	caffe_gpu_rng_uniform (const int n, const Dtype a, const Dtype b, Dtype *r)

template<typename Dtype >
void	caffe_gpu_rng_gaussian (const int n, const Dtype mu, const Dtype sigma, Dtype *r)

template<typename Dtype >
void	caffe_gpu_rng_bernoulli (const int n, const Dtype p, int *r)

template<typename Dtype >
void	caffe_gpu_dot (const int n, const Dtype x, const Dtype y, Dtype *out)

template<typename Dtype >
void	caffe_gpu_asum (const int n, const Dtype x, Dtype y)

template<typename Dtype >
void	caffe_gpu_sign (const int n, const Dtype x, Dtype y)

template<typename Dtype >
void	caffe_gpu_sgnbit (const int n, const Dtype x, Dtype y)

template<typename Dtype >
void	caffe_gpu_fabs (const int n, const Dtype x, Dtype y)

template<typename Dtype >
void	caffe_gpu_scale (const int n, const Dtype alpha, const Dtype x, Dtype y)

rng_t *	caffe_rng ()

template<class RandomAccessIterator , class RandomGenerator >
void	shuffle (RandomAccessIterator begin, RandomAccessIterator end, RandomGenerator *gen)

template<class RandomAccessIterator >
void	shuffle (RandomAccessIterator begin, RandomAccessIterator end)

bool	NetNeedsUpgrade (const NetParameter &net_param)

bool	UpgradeNetAsNeeded (const string &param_file, NetParameter *param)

void	ReadNetParamsFromTextFileOrDie (const string &param_file, NetParameter *param)

void	ReadNetParamsFromBinaryFileOrDie (const string &param_file, NetParameter *param)

bool	NetNeedsV0ToV1Upgrade (const NetParameter &net_param)

bool	UpgradeV0Net (const NetParameter &v0_net_param, NetParameter *net_param)

void	UpgradeV0PaddingLayers (const NetParameter &param, NetParameter *param_upgraded_pad)

bool	UpgradeV0LayerParameter (const V1LayerParameter &v0_layer_connection, V1LayerParameter *layer_param)

V1LayerParameter_LayerType	UpgradeV0LayerType (const string &type)

bool	NetNeedsDataUpgrade (const NetParameter &net_param)

void	UpgradeNetDataTransformation (NetParameter *net_param)

bool	NetNeedsV1ToV2Upgrade (const NetParameter &net_param)

bool	UpgradeV1Net (const NetParameter &v1_net_param, NetParameter *net_param)

bool	UpgradeV1LayerParameter (const V1LayerParameter &v1_layer_param, LayerParameter *layer_param)

const char *	UpgradeV1LayerType (const V1LayerParameter_LayerType type)

bool	NetNeedsInputUpgrade (const NetParameter &net_param)

void	UpgradeNetInput (NetParameter *net_param)

bool	NetNeedsBatchNormUpgrade (const NetParameter &net_param)

void	UpgradeNetBatchNorm (NetParameter *net_param)

bool	SolverNeedsTypeUpgrade (const SolverParameter &solver_param)

bool	UpgradeSolverType (SolverParameter *solver_param)

bool	UpgradeSolverAsNeeded (const string &param_file, SolverParameter *param)

void	ReadSolverParamsFromTextFileOrDie (const string &param_file, SolverParameter *param)

	INSTANTIATE_CLASS (Blob)

int64_t	cluster_seedgen (void)

	INSTANTIATE_CLASS (DataTransformer)

	INSTANTIATE_CLASS (Layer)

template<typename Dtype >
shared_ptr< Layer< Dtype > >	GetConvolutionLayer (const LayerParameter &param)

	REGISTER_LAYER_CREATOR (Convolution, GetConvolutionLayer)

template<typename Dtype >
shared_ptr< Layer< Dtype > >	GetPoolingLayer (const LayerParameter &param)

	REGISTER_LAYER_CREATOR (Pooling, GetPoolingLayer)

template<typename Dtype >
shared_ptr< Layer< Dtype > >	GetLRNLayer (const LayerParameter &param)

	REGISTER_LAYER_CREATOR (LRN, GetLRNLayer)

template<typename Dtype >
shared_ptr< Layer< Dtype > >	GetReLULayer (const LayerParameter &param)

	REGISTER_LAYER_CREATOR (ReLU, GetReLULayer)

template<typename Dtype >
shared_ptr< Layer< Dtype > >	GetSigmoidLayer (const LayerParameter &param)

	REGISTER_LAYER_CREATOR (Sigmoid, GetSigmoidLayer)

template<typename Dtype >
shared_ptr< Layer< Dtype > >	GetSoftmaxLayer (const LayerParameter &param)

	REGISTER_LAYER_CREATOR (Softmax, GetSoftmaxLayer)

template<typename Dtype >
shared_ptr< Layer< Dtype > >	GetTanHLayer (const LayerParameter &param)

	REGISTER_LAYER_CREATOR (TanH, GetTanHLayer)

	INSTANTIATE_CLASS (AbsValLayer)

	REGISTER_LAYER_CLASS (AbsVal)

	INSTANTIATE_CLASS (AccuracyLayer)

	REGISTER_LAYER_CLASS (Accuracy)

	INSTANTIATE_CLASS (ArgMaxLayer)

	REGISTER_LAYER_CLASS (ArgMax)

	INSTANTIATE_CLASS (BaseConvolutionLayer)

	INSTANTIATE_CLASS (BaseDataLayer)

	INSTANTIATE_CLASS (BasePrefetchingDataLayer)

	INSTANTIATE_CLASS (BatchNormLayer)

	REGISTER_LAYER_CLASS (BatchNorm)

	INSTANTIATE_CLASS (BatchReindexLayer)

	REGISTER_LAYER_CLASS (BatchReindex)

	INSTANTIATE_CLASS (BiasLayer)

	REGISTER_LAYER_CLASS (Bias)

	INSTANTIATE_CLASS (BNLLLayer)

	REGISTER_LAYER_CLASS (BNLL)

	INSTANTIATE_CLASS (ConcatLayer)

	REGISTER_LAYER_CLASS (Concat)

	INSTANTIATE_CLASS (ContrastiveLossLayer)

	REGISTER_LAYER_CLASS (ContrastiveLoss)

	INSTANTIATE_CLASS (ConvolutionLayer)

	INSTANTIATE_CLASS (CropLayer)

	REGISTER_LAYER_CLASS (Crop)

	INSTANTIATE_CLASS (DataLayer)

	REGISTER_LAYER_CLASS (Data)

	INSTANTIATE_CLASS (DeconvolutionLayer)

	REGISTER_LAYER_CLASS (Deconvolution)

	INSTANTIATE_CLASS (DropoutLayer)

	REGISTER_LAYER_CLASS (Dropout)

	INSTANTIATE_CLASS (DummyDataLayer)

	REGISTER_LAYER_CLASS (DummyData)

	INSTANTIATE_CLASS (EltwiseLayer)

	REGISTER_LAYER_CLASS (Eltwise)

	INSTANTIATE_CLASS (ELULayer)

	REGISTER_LAYER_CLASS (ELU)

	INSTANTIATE_CLASS (EmbedLayer)

	REGISTER_LAYER_CLASS (Embed)

	INSTANTIATE_CLASS (EuclideanLossLayer)

	REGISTER_LAYER_CLASS (EuclideanLoss)

	INSTANTIATE_CLASS (ExpLayer)

	REGISTER_LAYER_CLASS (Exp)

	INSTANTIATE_CLASS (FilterLayer)

	REGISTER_LAYER_CLASS (Filter)

	INSTANTIATE_CLASS (FlattenLayer)

	REGISTER_LAYER_CLASS (Flatten)

	INSTANTIATE_CLASS (HDF5DataLayer)

	REGISTER_LAYER_CLASS (HDF5Data)

	INSTANTIATE_CLASS (HDF5OutputLayer)

	REGISTER_LAYER_CLASS (HDF5Output)

	INSTANTIATE_CLASS (HingeLossLayer)

	REGISTER_LAYER_CLASS (HingeLoss)

	INSTANTIATE_CLASS (Im2colLayer)

	REGISTER_LAYER_CLASS (Im2col)

	INSTANTIATE_CLASS (InfogainLossLayer)

	REGISTER_LAYER_CLASS (InfogainLoss)

	INSTANTIATE_CLASS (InnerProductLayer)

	REGISTER_LAYER_CLASS (InnerProduct)

	INSTANTIATE_CLASS (InputLayer)

	REGISTER_LAYER_CLASS (Input)

	INSTANTIATE_CLASS (LogLayer)

	REGISTER_LAYER_CLASS (Log)

	INSTANTIATE_CLASS (LossLayer)

	INSTANTIATE_CLASS (LRNLayer)

	INSTANTIATE_CLASS (LSTMLayer)

	REGISTER_LAYER_CLASS (LSTM)

template<typename Dtype >
Dtype	sigmoid (Dtype x)

template<typename Dtype >
Dtype	tanh (Dtype x)

	INSTANTIATE_CLASS (LSTMUnitLayer)

	REGISTER_LAYER_CLASS (LSTMUnit)

	INSTANTIATE_CLASS (MemoryDataLayer)

	REGISTER_LAYER_CLASS (MemoryData)

	INSTANTIATE_CLASS (MultinomialLogisticLossLayer)

	REGISTER_LAYER_CLASS (MultinomialLogisticLoss)

	INSTANTIATE_CLASS (MVNLayer)

	REGISTER_LAYER_CLASS (MVN)

	INSTANTIATE_CLASS (NeuronLayer)

	INSTANTIATE_CLASS (ParameterLayer)

	REGISTER_LAYER_CLASS (Parameter)

	INSTANTIATE_CLASS (PoolingLayer)

	INSTANTIATE_CLASS (PowerLayer)

	REGISTER_LAYER_CLASS (Power)

	INSTANTIATE_CLASS (PReLULayer)

	REGISTER_LAYER_CLASS (PReLU)

	INSTANTIATE_CLASS (RecurrentLayer)

	INSTANTIATE_CLASS (ReductionLayer)

	REGISTER_LAYER_CLASS (Reduction)

	INSTANTIATE_CLASS (ReLULayer)

	INSTANTIATE_CLASS (ReshapeLayer)

	REGISTER_LAYER_CLASS (Reshape)

	INSTANTIATE_CLASS (RNNLayer)

	REGISTER_LAYER_CLASS (RNN)

	INSTANTIATE_CLASS (ScaleLayer)

	REGISTER_LAYER_CLASS (Scale)

	INSTANTIATE_CLASS (SigmoidCrossEntropyLossLayer)

	REGISTER_LAYER_CLASS (SigmoidCrossEntropyLoss)

	INSTANTIATE_CLASS (SigmoidLayer)

	INSTANTIATE_CLASS (SilenceLayer)

	REGISTER_LAYER_CLASS (Silence)

	INSTANTIATE_CLASS (SliceLayer)

	REGISTER_LAYER_CLASS (Slice)

	INSTANTIATE_CLASS (SoftmaxLayer)

	INSTANTIATE_CLASS (SoftmaxWithLossLayer)

	REGISTER_LAYER_CLASS (SoftmaxWithLoss)

	INSTANTIATE_CLASS (SplitLayer)

	REGISTER_LAYER_CLASS (Split)

	INSTANTIATE_CLASS (SPPLayer)

	REGISTER_LAYER_CLASS (SPP)

	INSTANTIATE_CLASS (TanHLayer)

	INSTANTIATE_CLASS (ThresholdLayer)

	REGISTER_LAYER_CLASS (Threshold)

	INSTANTIATE_CLASS (TileLayer)

	REGISTER_LAYER_CLASS (Tile)

	INSTANTIATE_CLASS (Net)

	INSTANTIATE_CLASS (Solver)

template<typename Dtype >
void	adadelta_update_gpu (int N, Dtype g, Dtype h, Dtype *h2, Dtype momentum, Dtype delta, Dtype local_rate)

	INSTANTIATE_CLASS (AdaDeltaSolver)

	REGISTER_SOLVER_CLASS (AdaDelta)

template<typename Dtype >
void	adagrad_update_gpu (int N, Dtype g, Dtype h, Dtype delta, Dtype local_rate)

	INSTANTIATE_CLASS (AdaGradSolver)

	REGISTER_SOLVER_CLASS (AdaGrad)

template<typename Dtype >
void	adam_update_gpu (int N, Dtype g, Dtype m, Dtype *v, Dtype beta1, Dtype beta2, Dtype eps_hat, Dtype corrected_local_rate)

	INSTANTIATE_CLASS (AdamSolver)

	REGISTER_SOLVER_CLASS (Adam)

template<typename Dtype >
void	nesterov_update_gpu (int N, Dtype g, Dtype h, Dtype momentum, Dtype local_rate)

	INSTANTIATE_CLASS (NesterovSolver)

	REGISTER_SOLVER_CLASS (Nesterov)

template<typename Dtype >
void	rmsprop_update_gpu (int N, Dtype g, Dtype h, Dtype rms_decay, Dtype delta, Dtype local_rate)

	INSTANTIATE_CLASS (RMSPropSolver)

	REGISTER_SOLVER_CLASS (RMSProp)

template<typename Dtype >
void	sgd_update_gpu (int N, Dtype g, Dtype h, Dtype momentum, Dtype local_rate)

	INSTANTIATE_CLASS (SGDSolver)

	REGISTER_SOLVER_CLASS (SGD)

template<>
void	hdf5_load_nd_dataset< float > (hid_t file_id, const char dataset_name_, int min_dim, int max_dim, Blob< float > blob, bool reshape)

template<>
void	hdf5_load_nd_dataset< double > (hid_t file_id, const char dataset_name_, int min_dim, int max_dim, Blob< double > blob, bool reshape)

template<>
void	hdf5_save_nd_dataset< float > (const hid_t file_id, const string &dataset_name, const Blob< float > &blob, bool write_diff)

template<>
void	hdf5_save_nd_dataset< double > (hid_t file_id, const string &dataset_name, const Blob< double > &blob, bool write_diff)

bool	is_a_ge_zero_and_a_lt_b (int a, int b)

template void	im2col_cpu< float > (const float data_im, const int channels, const int height, const int width, const int kernel_h, const int kernel_w, const int pad_h, const int pad_w, const int stride_h, const int stride_w, const int dilation_h, const int dilation_w, float data_col)

template void	im2col_cpu< double > (const double data_im, const int channels, const int height, const int width, const int kernel_h, const int kernel_w, const int pad_h, const int pad_w, const int stride_h, const int stride_w, const int dilation_h, const int dilation_w, double data_col)

template<typename Dtype >
void	im2col_nd_core_cpu (const Dtype data_input, const bool im2col, const int num_spatial_axes, const int im_shape, const int col_shape, const int kernel_shape, const int pad, const int stride, const int dilation, Dtype data_output)

template void	im2col_nd_cpu< float > (const float data_im, const int num_spatial_axes, const int im_shape, const int col_shape, const int kernel_shape, const int pad, const int stride, const int dilation, float data_col)

template void	im2col_nd_cpu< double > (const double data_im, const int num_spatial_axes, const int im_shape, const int col_shape, const int kernel_shape, const int pad, const int stride, const int dilation, double data_col)

template void	col2im_cpu< float > (const float data_col, const int channels, const int height, const int width, const int kernel_h, const int kernel_w, const int pad_h, const int pad_w, const int stride_h, const int stride_w, const int dilation_h, const int dilation_w, float data_im)

template void	col2im_cpu< double > (const double data_col, const int channels, const int height, const int width, const int kernel_h, const int kernel_w, const int pad_h, const int pad_w, const int stride_h, const int stride_w, const int dilation_h, const int dilation_w, double data_im)

template void	col2im_nd_cpu< float > (const float data_col, const int num_spatial_axes, const int im_shape, const int col_shape, const int kernel_shape, const int pad, const int stride, const int dilation, float data_im)

template void	col2im_nd_cpu< double > (const double data_col, const int num_spatial_axes, const int im_shape, const int col_shape, const int kernel_shape, const int pad, const int stride, const int dilation, double data_im)

template<>
void	caffe_cpu_gemm< float > (const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB, const int M, const int N, const int K, const float alpha, const float A, const float B, const float beta, float *C)

template<>
void	caffe_cpu_gemm< double > (const CBLAS_TRANSPOSE TransA, const CBLAS_TRANSPOSE TransB, const int M, const int N, const int K, const double alpha, const double A, const double B, const double beta, double *C)

template<>
void	caffe_cpu_gemv< float > (const CBLAS_TRANSPOSE TransA, const int M, const int N, const float alpha, const float A, const float x, const float beta, float *y)

template<>
void	caffe_cpu_gemv< double > (const CBLAS_TRANSPOSE TransA, const int M, const int N, const double alpha, const double A, const double x, const double beta, double *y)

template<>
void	caffe_axpy< float > (const int N, const float alpha, const float X, float Y)

template<>
void	caffe_axpy< double > (const int N, const double alpha, const double X, double Y)

template void	caffe_set< int > (const int N, const int alpha, int *Y)

template void	caffe_set< float > (const int N, const float alpha, float *Y)

template void	caffe_set< double > (const int N, const double alpha, double *Y)

template<>
void	caffe_add_scalar (const int N, const float alpha, float *Y)

template<>
void	caffe_add_scalar (const int N, const double alpha, double *Y)

template void	caffe_copy< int > (const int N, const int X, int Y)

template void	caffe_copy< unsigned int > (const int N, const unsigned int X, unsigned int Y)

template void	caffe_copy< float > (const int N, const float X, float Y)

template void	caffe_copy< double > (const int N, const double X, double Y)

template<>
void	caffe_scal< float > (const int N, const float alpha, float *X)

template<>
void	caffe_scal< double > (const int N, const double alpha, double *X)

template<>
void	caffe_cpu_axpby< float > (const int N, const float alpha, const float X, const float beta, float Y)

template<>
void	caffe_cpu_axpby< double > (const int N, const double alpha, const double X, const double beta, double Y)

template<>
void	caffe_add< float > (const int n, const float a, const float b, float *y)

template<>
void	caffe_add< double > (const int n, const double a, const double b, double *y)

template<>
void	caffe_sub< float > (const int n, const float a, const float b, float *y)

template<>
void	caffe_sub< double > (const int n, const double a, const double b, double *y)

template<>
void	caffe_mul< float > (const int n, const float a, const float b, float *y)

template<>
void	caffe_mul< double > (const int n, const double a, const double b, double *y)

template<>
void	caffe_div< float > (const int n, const float a, const float b, float *y)

template<>
void	caffe_div< double > (const int n, const double a, const double b, double *y)

template<>
void	caffe_powx< float > (const int n, const float a, const float b, float y)

template<>
void	caffe_powx< double > (const int n, const double a, const double b, double y)

template<>
void	caffe_sqr< float > (const int n, const float a, float y)

template<>
void	caffe_sqr< double > (const int n, const double a, double y)

template<>
void	caffe_sqrt< float > (const int n, const float a, float y)

template<>
void	caffe_sqrt< double > (const int n, const double a, double y)

template<>
void	caffe_exp< float > (const int n, const float a, float y)

template<>
void	caffe_exp< double > (const int n, const double a, double y)

template<>
void	caffe_log< float > (const int n, const float a, float y)

template<>
void	caffe_log< double > (const int n, const double a, double y)

template<>
void	caffe_abs< float > (const int n, const float a, float y)

template<>
void	caffe_abs< double > (const int n, const double a, double y)

template float	caffe_nextafter (const float b)

template double	caffe_nextafter (const double b)

template void	caffe_rng_uniform< float > (const int n, const float a, const float b, float *r)

template void	caffe_rng_uniform< double > (const int n, const double a, const double b, double *r)

template void	caffe_rng_gaussian< float > (const int n, const float mu, const float sigma, float *r)

template void	caffe_rng_gaussian< double > (const int n, const double mu, const double sigma, double *r)

template void	caffe_rng_bernoulli< double > (const int n, const double p, int *r)

template void	caffe_rng_bernoulli< float > (const int n, const float p, int *r)

template void	caffe_rng_bernoulli< double > (const int n, const double p, unsigned int *r)

template void	caffe_rng_bernoulli< float > (const int n, const float p, unsigned int *r)

template<>
float	caffe_cpu_strided_dot< float > (const int n, const float x, const int incx, const float y, const int incy)

template<>
double	caffe_cpu_strided_dot< double > (const int n, const double x, const int incx, const double y, const int incy)

template float	caffe_cpu_dot< float > (const int n, const float x, const float y)

template double	caffe_cpu_dot< double > (const int n, const double x, const double y)

template<>
float	caffe_cpu_asum< float > (const int n, const float *x)

template<>
double	caffe_cpu_asum< double > (const int n, const double *x)

template<>
void	caffe_cpu_scale< float > (const int n, const float alpha, const float x, float y)

template<>
void	caffe_cpu_scale< double > (const int n, const double alpha, const double x, double y)

Variables
const float	kLOG_THRESHOLD = 1e-20

const int	CAFFE_CUDA_NUM_THREADS = 512

const Dtype	alpha

const Dtype const Dtype *	x

const Dtype const Dtype Dtype *	y

const float	kBNLL_THRESHOLD = 50.

Detailed Description

A layer factory that allows one to register layers. During runtime, registered layers can be called by passing a LayerParameter protobuffer to the CreateLayer function:

A solver factory that allows one to register solvers, similar to layer factory. During runtime, registered solvers could be called by passing a SolverParameter protobuffer to the CreateSolver function:

LayerRegistry<Dtype>::CreateLayer(param);

There are two ways to register a layer. Assuming that we have a layer like:

template <typename dtype>=""> class MyAwesomeLayer : public Layer<Dtype> { // your implementations };

and its type is its C++ class name, but without the "Layer" at the end ("MyAwesomeLayer" -> "MyAwesome").

If the layer is going to be created simply by its constructor, in your c++ file, add the following line:

REGISTER_LAYER_CLASS(MyAwesome);

Or, if the layer is going to be created by another creator function, in the format of:

template <typename dtype>=""> Layer<Dtype*> GetMyAwesomeLayer(const LayerParameter& param) { // your implementation }

(for example, when your layer has multiple backends, see GetConvolutionLayer for a use case), then you can register the creator function instead, like

REGISTER_LAYER_CREATOR(MyAwesome, GetMyAwesomeLayer)

Note that each layer type should only be registered once.

SolverRegistry<Dtype>::CreateSolver(param);

There are two ways to register a solver. Assuming that we have a solver like:

template <typename dtype>=""> class MyAwesomeSolver : public Solver<Dtype> { // your implementations };

and its type is its C++ class name, but without the "Solver" at the end ("MyAwesomeSolver" -> "MyAwesome").

If the solver is going to be created simply by its constructor, in your C++ file, add the following line:

REGISTER_SOLVER_CLASS(MyAwesome);

Or, if the solver is going to be created by another creator function, in the format of:

template <typename dtype>=""> Solver<Dtype*> GetMyAwesomeSolver(const SolverParameter& param) { // your implementation }

then you can register the creator function instead, like

REGISTER_SOLVER_CREATOR(MyAwesome, GetMyAwesomeSolver)

Note that each solver type should only be registered once.

Function Documentation

◆ GetFiller()

template<typename Dtype >

Filler<Dtype>* caffe::GetFiller ( const FillerParameter & param )

Get a specific filler from the specification given in FillerParameter.

Ideally this would be replaced by a factory pattern, but we will leave it this way for now.

Namespaces

Classes

Typedefs

Functions

Variables

Detailed Description

Function Documentation

◆ GetFiller()