Deeploy.DeeployTypes.ConstantBuffer

class Deeploy.DeeployTypes.ConstantBuffer(name: str = '', shape=[1], values=[0])

Bases: VariableBuffer

Class to represent compile-time constant tensors (weights, biases, other parameters) within Deeploy.

Methods

__init__(name: str = '', shape=[1], values=[0])

`__init__`([name, shape, values])
`alloc`()	Return a string representation of the C code required to allocated this memory buffer
`dealloc`()	Return a string representation of the C code to deallocate/free this memory buffer at runtime
`fromNode`(node)
`fromVariableBuffer`(buffer, values)
`init`()	Return a string representation of the C code to declare this memory buffer

Attributes

`values`	Stores the underlying weights in Python-type representation
`initTemplate`	Holds the buffer's initialization code
`allocTemplate`	Holds the buffer's allocation code
`deallocTemplate`	Holds the buffer's deallocation code
`name`	Canonical name that this buffer is registered as in the NetworkContext
`shape`	Represents the dimensions of the underlying tensor as a sequence of dimension sizes

values

Stores the underlying weights in Python-type representation

Type:: np.array

alloc() → str

Return a string representation of the C code required to allocated this memory buffer

Returns:: C Code to allocate this buffer
Return type:: str

dealloc() → str

Return a string representation of the C code to deallocate/free this memory buffer at runtime

Returns:: C Code to free this buffer
Return type:: str

init() → str

Return a string representation of the C code to declare this memory buffer

Returns:: C Code to declare this buffer
Return type:: str

initTemplate: NodeTemplate

Holds the buffer’s initialization code

Type:: NodeTemplate

allocTemplate: NodeTemplate

Holds the buffer’s allocation code

Type:: NodeTemplate

deallocTemplate: NodeTemplate

Holds the buffer’s deallocation code

Type:: NodeTemplate

name: str

Canonical name that this buffer is registered as in the NetworkContext

Type:: str

shape: Sequence[int]

Represents the dimensions of the underlying tensor as a sequence of dimension sizes

Type:: Sequence[int]