Apache Singa
A General Distributed Deep Learning Library
 All Classes Namespaces Functions Variables Typedefs
Class List
Here are the classes, structs, unions and interfaces with brief descriptions:
[detail level 123]
oNsingaLicensed to the Apache Software Foundation (ASF) under one or more contributor license agreements
|oCBlockBlock represent a chunk of memory (on device or host)
|oCDeviceAllocate memory and execute Tensor operations
|oCCppCPURepresent a CPU device which may have multiple threads/executors
|oCPlatformThis class queries all available calculating devices on a given machine grouped according to manufacturer or device drivers
|oCVirtualMemoryManage device memory pool including garbage collection, memory opt
|oCSchedulerScheduling Tensor operations with dependency detection
|oCTensorA Tensor instance is a multi-dimensional array resident on a Device (default device is the host CPU)
|oCDecoderThe base decoder that converts a string into a set of tensors
|oCCSVDecoderDecode the string of csv formated data into data tensor (dtype is kFloat32) and optionally a label tensor (dtype is kInt)
|oCEncoderBase encoder class that convert a set of tensors into string for storage
|oCCSVEncoderConvert values from tensors into a csv formated string
|oCSnapshotThe snapshot management
|oCTransformerBase apply class that does data transformations in pre-processing stage
|oCFeedForwardNetThe feed-forward neural net
|oCLayerThe base layer class
|oCLossThe base loss class, which declares the APIs for computing the objective score (loss) for a pair of prediction (from the model) and the target (i.e
|oCMSEMSE is for mean squared error or squared euclidean distance
|oCSoftmaxCrossEntropySoftmax + cross entropy for multi-category classification
|oCMetricThe base metric class, which declares the APIs for computing the performance evaluation metrics given the prediction of the model and the ground truth, i.e., the target
|oCAccuracyCompute the accuray of the prediction, which is matched against the ground truth labels
|oCOptimizerThe base class for gradient descent algorithms used to update the model parameters in order to optimize the objective (loss) function
|oCConstraintApply constraints for parameters (gradient)
|oCRegularizerApply regularization for parameters (gradient), e.g., L1 norm and L2 norm
|oCUpdaterBasic Updater class just forward all the method function call to the wrapped Optimizer
|oCLocalUpdaterLocalUpdater do gradient aggregation and update gradient calling the wrapped Optimizer on a specific device (i.e., CPU or GPU)
|oCChannelChannel for appending metrics or other information into files or screen
|oCTokenizerTokenize a string
|oCTimerFor benchmarking the time cost of operations
oCFactoryFactory template to generate class (or a sub-class) object based on id
oCPriorityQueueThread safe priority queue
oCSafeQueueThread-safe queue
oCSingletonThread-safe implementation for C++11 according to