![]() |
NeuZephyr
Simple DL Framework
|
Cnz::graph::ComputeGraph | Represents a computational graph, which manages nodes and the computation flow |
Cnz::CudaException | A final class that represents CUDA exceptions, inheriting from std::runtime_error |
Cnz::data::Dimension | Represents a multi - dimensional shape, typically used in deep learning for tensor dimensions |
Cnz::cuStrm::EventPool | Internal event management system for CUDA stream synchronization (Part of StreamManager) |
Cnz::data::MappedTensor | A class for representing multidimensional arrays in CUDA zero-copy memory, providing host-accessible container-like interfaces |
Cnz::Model | Base class for constructing neural network models with automatic computation graph management |
▼Cnz::nodes::Node | Base class for nodes in a neural network or computational graph |
Cnz::nodes::calc::AddNode | Represents a node that performs element-wise addition between two input tensors |
Cnz::nodes::calc::AveragePoolingNode | Implements average pooling operation for spatial downsampling in neural networks |
Cnz::nodes::calc::Col2ImgNode | Reconstructs spatial tensors from column matrices generated by im2col transformation |
Cnz::nodes::calc::ELUNode | Represents an Exponential Linear Unit (ELU) activation function node in a computational graph |
Cnz::nodes::calc::ExpandNode | Expands tensors with batch size 1 to arbitrary batch dimensions through data replication |
Cnz::nodes::calc::GlobalAvgPoolNode | Performs global average pooling operation across spatial dimensions of input tensor |
Cnz::nodes::calc::GlobalMaxPoolNode | Performs global max pooling operation across spatial dimensions of input tensor |
Cnz::nodes::calc::HardSigmoidNode | Represents a Hard Sigmoid activation function node in a computational graph |
Cnz::nodes::calc::HardSwishNode | Represents a Hard Swish activation function node in a computational graph |
Cnz::nodes::calc::Img2ColNode | Implements im2col transformation for efficient convolution operations in neural networks |
Cnz::nodes::calc::LeakyReLUNode | Represents a Leaky Rectified Linear Unit (LeakyReLU) activation function node in a computational graph |
Cnz::nodes::calc::MatMulNode | Represents a matrix multiplication operation node in a computational graph |
Cnz::nodes::calc::MaxPoolingNode | Implements max pooling operation for spatial downsampling with feature preservation |
Cnz::nodes::calc::ReLUNode | Represents a Rectified Linear Unit (ReLU) operation node in a computational graph |
Cnz::nodes::calc::ReshapeNode | Implements tensor shape transformation within a neural network computational graph |
Cnz::nodes::calc::ScalarAddNode | Represents a scalar addition operation node in a computational graph |
Cnz::nodes::calc::ScalarDivNode | Represents a scalar division operation node in a computational graph |
Cnz::nodes::calc::ScalarMulNode | Represents a scalar multiplication operation node in a computational graph |
Cnz::nodes::calc::ScalarSubNode | Represents a scalar subtraction operation node in a computational graph |
Cnz::nodes::calc::SigmoidNode | Represents a Sigmoid activation function node in a computational graph |
Cnz::nodes::calc::SoftmaxNode | Implements the Softmax activation function as a node in a neural network computational graph |
Cnz::nodes::calc::SubNode | Represents a subtraction operation node in a computational graph |
Cnz::nodes::calc::SwishNode | Represents a Swish activation function node in a computational graph |
Cnz::nodes::calc::TanhNode | Represents a hyperbolic tangent (tanh) activation function node in a computational graph |
Cnz::nodes::io::InputNode | Represents an input node in a computational graph |
▼Cnz::nodes::io::OutputNode | Base class for loss function nodes in a computational graph |
Cnz::nodes::loss::BinaryCrossEntropyNode | Represents the Binary Cross-Entropy (BCE) loss function node in a computational graph |
Cnz::nodes::loss::MeanSquaredErrorNode | Represents the Mean Squared Error (MSE) loss function node in a computational graph |
▼Cnz::opt::Optimizer | Base class for optimization algorithms in deep learning |
Cnz::opt::AdaDelta | AdaDelta optimizer for deep learning models |
Cnz::opt::AdaGrad | AdaGrad optimizer for deep learning models |
Cnz::opt::Adam | Adam optimizer for deep learning models |
Cnz::opt::Momentum | Momentum optimizer for deep learning models |
Cnz::opt::NAdam | NAdam optimizer for deep learning models |
Cnz::opt::RMSprop | RMSprop optimizer for deep learning models |
Cnz::opt::SGD | Stochastic 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::Tensor | A class for representing and manipulating multidimensional arrays (tensors) in GPU memory |