Deeploy.DeeployTypes
Classes
|
Encapsulates verbosity options for downstream configuration |
|
A dataclass to hold a NodeTemplate and its associated OperatorRepresentation; used to generate code |
|
Wrapper object to run multiple CodeTransformations sequentially |
Pass Object to update code generation; may either modify an executionBlock's existing code snippets or add new code snippets to an executionBlock |
|
|
Class to represent compile-time constant tensors (weights, biases, other parameters) within Deeploy. |
|
Deeploy abstraction to represent a compute engine without a complete host system, like an accelerator |
|
Deeploy abstraction for a complete system, including at least a host core capable of memory allocation |
|
Deeploy abstraction to represent a operator whose kernel has been determined. |
|
Helper class to hoist arbitrary C code into the global program scope; used to perform small amounts of global initialization, declare global synchronization objects, and similar. |
|
Deeploy abstraction for containing the information needed to describe a complete neural network to be deployed |
|
The global context of the compiler. |
|
Deeploy abstraction to contain an entire network and all necessary information to deploy it |
Pass to update the NetworkContext and Neural Network Graph in one go |
|
|
Wrapper class to run multiple NetworkOptimizationPasses sequentially |
|
Deeploy's class to bind individual NodeTypeChecker objects to NodeTemplate and associate a CodeTransformation. |
|
Deeploy class to link a NodeParser and several NodeBindings |
Deeploy's core Parser class. |
|
|
This class wraps a Mako.Template with additional functionality for hoisting transient buffers and adding expressions to the parsers' node representation |
|
Implements type checking according to user-defined rules to assign Deeploy-types to the Python-typed input graph |
|
Deeploy abstraction to represent one operator in an ONNX graph |
|
Class to represent Struct object needed by the generated C Code |
Abstract pass object which modifies an ONNX graph |
|
|
Wrapper object to apply multiple TopologyOptimizationPasses sequentially |
|
Class to represent memory space required by kernels that is not covered by input and output tensors, e.g. im2col buffers in convolutions. |
|
This class represents memory locations containing variable tensor data that is not transient, i.e. intermediate results or input- and output buffers. |