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.
onnx Directory Reference

Files

file  __init__.py
 
file  conv_parser.py
 
file  default_node_parser.py
 
file  gemm_parser.py
 
file  matmul_parser.py
 
file  onnx_model_parser.py
 
file  onnx_operator_parser.py
 
file  utils.py