haq
haq copied to clipboard
fused mobilenet v1
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?
This is really confusing me a lot. Did you try to fold the batch norm layer? What the performance is?