Deeploy.DeeployTypes.TransientBuffer
- class Deeploy.DeeployTypes.TransientBuffer(name: str = '', size=0)
Bases:
VariableBuffer
Class to represent memory space required by kernels that is not covered by input and output tensors, e.g. im2col buffers in convolutions
Methods
- __init__(name: str = '', size=0)
__init__
([name, size])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)init
()Return a string representation of the C code to declare this memory buffer
Attributes
Total BYTE size of this TransientBuffer
Holds the buffer's initialization code
Holds the buffer's allocation code
Holds the buffer's deallocation code
Canonical name that this buffer is registered as in the NetworkContext
Represents the dimensions of the underlying tensor as a sequence of dimension sizes
- name: str
Canonical name that this buffer is registered as in the NetworkContext
- Type:
str
- size
Total BYTE size of this TransientBuffer
- Type:
int
- 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:
- allocTemplate: NodeTemplate
Holds the buffer’s allocation code
- Type:
- deallocTemplate: NodeTemplate
Holds the buffer’s deallocation code
- Type:
- shape: Sequence[int]
Represents the dimensions of the underlying tensor as a sequence of dimension sizes
- Type:
Sequence[int]