yhhhli / BRECQ

Pytorch implementation of BRECQ, ICLR 2021

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

outcome is different with and without hyperparameter 'test_before_calibration'

blackandredplayerinfuture opened this issue · comments

commented

CUDA_VISIBLE_DEVICES=3 python main_imagenet.py --data_path /disk2/imagenet/ --arch resnet18 --n_bits_w 2 --channel_wise --n_bits_a 4 --act_quant --test_before_calibration | tee w2a4_test.log
CUDA_VISIBLE_DEVICES=3 python main_imagenet.py --data_path /disk2/imagenet/ --arch resnet18 --n_bits_w 2 --channel_wise --n_bits_a 4 --act_quant | tee w2a4.log

the outcome of w2a4 and w2a32 after reconstruction are different when I remove the hyperparameter 'test_before_calibration', but this one wouldn't modify the seed. I'm wondering why and looking forward to your reply.