ZigZag - Deep Learning Hardware Design Space Exploration
This repository presents the novel version of our tried-and-tested hardware Architecture-Mapping Design Space Exploration (DSE) Framework for Deep Learning (DL) accelerators. ZigZag bridges the gap between algorithmic DL decisions and their acceleration cost on specialized accelerators through a fast and accurate hardware cost estimation.
|
Represents a single layer of a workload in any form. More...
Public Member Functions | |
def | __init__ (self, int node_id, str node_name) |
str | __repr__ (self) |
str | __str__ (self) |
def | __jsonrepr__ (self) |
JSON representation used for saving this object to a json file. More... | |
Public Attributes | |
id | |
name | |
Represents a single layer of a workload in any form.
def __init__ | ( | self, | |
int | node_id, | ||
str | node_name | ||
) |
def __jsonrepr__ | ( | self | ) |
JSON representation used for saving this object to a json file.
Reimplemented in LayerNode.
str __repr__ | ( | self | ) |
str __str__ | ( | self | ) |
id |
name |