musco-pytorch icon indicating copy to clipboard operation
musco-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon musco-ai

how to calculate the speedup in the paper

Open liusiping10 opened this issue 5 years ago • 0 comments

when I run the compressed VGG16 model, the runtime is even longer than VGG16 before compressed. how to run the compressed models getting the same results (Table 5) in the paper https://arxiv.org/abs/1903.09973?

liusiping10 avatar Nov 13 '19 17:11 liusiping10