 |
NeuZephyr
Simple DL Framework
|
|
NeuZephyr
Simple DL Framework
|
Contains classes and functionality for computation nodes in a neural network or computational graph. More...
Classes | |
| class | AddNode |
| Represents a node that performs element-wise addition between two input tensors. More... | |
| class | AveragePoolingNode |
| Implements average pooling operation for spatial downsampling in neural networks. More... | |
| class | Col2ImgNode |
| Reconstructs spatial tensors from column matrices generated by im2col transformation. More... | |
| class | ELUNode |
| Represents an Exponential Linear Unit (ELU) activation function node in a computational graph. More... | |
| class | ExpandNode |
| Expands tensors with batch size 1 to arbitrary batch dimensions through data replication. More... | |
| class | GlobalAvgPoolNode |
| Performs global average pooling operation across spatial dimensions of input tensor. More... | |
| class | GlobalMaxPoolNode |
| Performs global max pooling operation across spatial dimensions of input tensor. More... | |
| class | HardSigmoidNode |
| Represents a Hard Sigmoid activation function node in a computational graph. More... | |
| class | HardSwishNode |
| Represents a Hard Swish activation function node in a computational graph. More... | |
| class | Img2ColNode |
| Implements im2col transformation for efficient convolution operations in neural networks. More... | |
| class | LeakyReLUNode |
| Represents a Leaky Rectified Linear Unit (LeakyReLU) activation function node in a computational graph. More... | |
| class | MatMulNode |
| Represents a matrix multiplication operation node in a computational graph. More... | |
| class | MaxPoolingNode |
| Implements max pooling operation for spatial downsampling with feature preservation. More... | |
| class | ReLUNode |
| Represents a Rectified Linear Unit (ReLU) operation node in a computational graph. More... | |
| class | ReshapeNode |
| Implements tensor shape transformation within a neural network computational graph. More... | |
| class | ScalarAddNode |
| Represents a scalar addition operation node in a computational graph. More... | |
| class | ScalarDivNode |
| Represents a scalar division operation node in a computational graph. More... | |
| class | ScalarMulNode |
| Represents a scalar multiplication operation node in a computational graph. More... | |
| class | ScalarSubNode |
| Represents a scalar subtraction operation node in a computational graph. More... | |
| class | SigmoidNode |
| Represents a Sigmoid activation function node in a computational graph. More... | |
| class | SoftmaxNode |
| Implements the Softmax activation function as a node in a neural network computational graph. More... | |
| class | SubNode |
| Represents a subtraction operation node in a computational graph. More... | |
| class | SwishNode |
| Represents a Swish activation function node in a computational graph. More... | |
| class | TanhNode |
| Represents a hyperbolic tangent (tanh) activation function node in a computational graph. More... | |
Contains classes and functionality for computation nodes in a neural network or computational graph.
The nz::nodes::calc namespace provides a collection of classes that represent various computational operations within a neural network. These nodes perform essential mathematical operations during the forward pass in a computational graph.
This namespace includes:
ReLUNode, SigmoidNode, TanhNode, LeakyReLUNode, etc., which apply non-linear transformations to the input data.AddNode, MatMulNode, ScalarMulNode, ScalarDivNode, and others for performing basic arithmetic and matrix operations.The nodes in this namespace interact with Tensor objects, performing data manipulation operations necessary for building neural network layers and facilitating the forward propagation of information through the network.
1.12.0