RepNAS: Searching for Efficient Re-parameterizing Blocks. (arXiv:2109.03508v4 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2109.03508

In the past years, significant improvements in the field of neural
architecture search(NAS) have been made. However, it is still challenging to
search for efficient networks due to the gap between the searched constraint
and real inference time exists. To search for a high-performance network with
low inference time, several previous works set a computational complexity
constraint for the search algorithm. However, many factors affect the speed of
inference(e.g., FLOPs, MACs). The correlation between a single indicator and
the latency …

arxiv lg