haq icon indicating copy to clipboard operation
haq copied to clipboard

fused mobilenet v1

Open HKLee2040 opened this issue 6 years ago • 1 comments
trafficstars

If we applied haq on fused mobilenet v1, i.e., fuse convolutional and batch norm layer together, it seems very difficult to quantize such model in 1~8bits. Do you have any comment on such case?

HKLee2040 avatar Oct 03 '19 06:10 HKLee2040

This is really confusing me a lot. Did you try to fold the batch norm layer? What the performance is?

densechen avatar Dec 09 '20 08:12 densechen