submission2019 / cnn-quantization

Quantization of Convolutional Neural networks.
237 stars 59 forks source link

Reproduce the results of Resnet18 @a4w4 #10

Open talenz opened 4 years ago

talenz commented 4 years ago

The command I run: python3 inference/inference_sim.py -a resnet18 -b 256 -pcq_w -pcq_a -sh --qtype int4 -qw int4 -c laplace -baa -baw -bcw And it gives: Prec@1 64.622 Prec@5 85.802

But the results reported in paper is 67.0

Did I do something wrong?