NeuZephyr
Simple DL Framework
Class Hierarchy

Go to the graphical class hierarchy

This inheritance list is sorted roughly, but not completely, alphabetically:
[detail level 123]
 Cnz::graph::ComputeGraphRepresents a computational graph, which manages nodes and the computation flow
 Cnz::CudaExceptionA final class that represents CUDA exceptions, inheriting from std::runtime_error
 Cnz::data::DimensionRepresents a multi - dimensional shape, typically used in deep learning for tensor dimensions
 Cnz::cuStrm::EventPoolInternal event management system for CUDA stream synchronization (Part of StreamManager)
 Cnz::data::MappedTensorA class for representing multidimensional arrays in CUDA zero-copy memory, providing host-accessible container-like interfaces
 Cnz::ModelBase class for constructing neural network models with automatic computation graph management
 Cnz::nodes::NodeBase class for nodes in a neural network or computational graph
 Cnz::nodes::calc::AddNodeRepresents a node that performs element-wise addition between two input tensors
 Cnz::nodes::calc::AveragePoolingNodeImplements average pooling operation for spatial downsampling in neural networks
 Cnz::nodes::calc::Col2ImgNodeReconstructs spatial tensors from column matrices generated by im2col transformation
 Cnz::nodes::calc::ELUNodeRepresents an Exponential Linear Unit (ELU) activation function node in a computational graph
 Cnz::nodes::calc::ExpandNodeExpands tensors with batch size 1 to arbitrary batch dimensions through data replication
 Cnz::nodes::calc::GlobalAvgPoolNodePerforms global average pooling operation across spatial dimensions of input tensor
 Cnz::nodes::calc::GlobalMaxPoolNodePerforms global max pooling operation across spatial dimensions of input tensor
 Cnz::nodes::calc::HardSigmoidNodeRepresents a Hard Sigmoid activation function node in a computational graph
 Cnz::nodes::calc::HardSwishNodeRepresents a Hard Swish activation function node in a computational graph
 Cnz::nodes::calc::Img2ColNodeImplements im2col transformation for efficient convolution operations in neural networks
 Cnz::nodes::calc::LeakyReLUNodeRepresents a Leaky Rectified Linear Unit (LeakyReLU) activation function node in a computational graph
 Cnz::nodes::calc::MatMulNodeRepresents a matrix multiplication operation node in a computational graph
 Cnz::nodes::calc::MaxPoolingNodeImplements max pooling operation for spatial downsampling with feature preservation
 Cnz::nodes::calc::ReLUNodeRepresents a Rectified Linear Unit (ReLU) operation node in a computational graph
 Cnz::nodes::calc::ReshapeNodeImplements tensor shape transformation within a neural network computational graph
 Cnz::nodes::calc::ScalarAddNodeRepresents a scalar addition operation node in a computational graph
 Cnz::nodes::calc::ScalarDivNodeRepresents a scalar division operation node in a computational graph
 Cnz::nodes::calc::ScalarMulNodeRepresents a scalar multiplication operation node in a computational graph
 Cnz::nodes::calc::ScalarSubNodeRepresents a scalar subtraction operation node in a computational graph
 Cnz::nodes::calc::SigmoidNodeRepresents a Sigmoid activation function node in a computational graph
 Cnz::nodes::calc::SoftmaxNodeImplements the Softmax activation function as a node in a neural network computational graph
 Cnz::nodes::calc::SubNodeRepresents a subtraction operation node in a computational graph
 Cnz::nodes::calc::SwishNodeRepresents a Swish activation function node in a computational graph
 Cnz::nodes::calc::TanhNodeRepresents a hyperbolic tangent (tanh) activation function node in a computational graph
 Cnz::nodes::io::InputNodeRepresents an input node in a computational graph
 Cnz::nodes::io::OutputNodeBase class for loss function nodes in a computational graph
 Cnz::nodes::loss::BinaryCrossEntropyNodeRepresents the Binary Cross-Entropy (BCE) loss function node in a computational graph
 Cnz::nodes::loss::MeanSquaredErrorNodeRepresents the Mean Squared Error (MSE) loss function node in a computational graph
 Cnz::opt::OptimizerBase class for optimization algorithms in deep learning
 Cnz::opt::AdaDeltaAdaDelta optimizer for deep learning models
 Cnz::opt::AdaGradAdaGrad optimizer for deep learning models
 Cnz::opt::AdamAdam optimizer for deep learning models
 Cnz::opt::MomentumMomentum optimizer for deep learning models
 Cnz::opt::NAdamNAdam optimizer for deep learning models
 Cnz::opt::RMSpropRMSprop optimizer for deep learning models
 Cnz::opt::SGDStochastic Gradient Descent (SGD) optimizer for deep learning models
 Cnz::cuStrm::StreamManager< T >Centralized CUDA stream and resource management system with automatic dependency tracking
 Cnz::data::TensorA class for representing and manipulating multidimensional arrays (tensors) in GPU memory