Thanks for the great codebase. I tried Experiment W4A4 + ACIQ + Bit Alloc(A) + Bit Alloc(W) + Bias correction by
python inference/inference_sim.py -a resnet50 -b 512 -pcq_w -pcq_a -sh --qtype int4 -qw int4 -c laplace -baa -baw -bcw
but only get accuracy 71.6. Is there any particular setting that should be followed? Thanks.
Hello,
Thanks for the great codebase. I tried
Experiment W4A4 + ACIQ + Bit Alloc(A) + Bit Alloc(W) + Bias correction
bypython inference/inference_sim.py -a resnet50 -b 512 -pcq_w -pcq_a -sh --qtype int4 -qw int4 -c laplace -baa -baw -bcw
but only get accuracy 71.6. Is there any particular setting that should be followed? Thanks.My environment: Pytorch 1.3 Torchvision 0.4.2