Wu Yuhang

> Thanks for sharing the results. Sorry that you get weird results... I reimplemented GDAS FRC based on my memory with the sacrifice of being compatible with the NATS-Bench/NAS-Bench-201 codebase,...

> {'normal': [(('skip_connect', 1, 0.15519889), ('dil_sepc_5x5', 0, 0.1416643)), (('skip_connect', 1, 0.15950418), ('max_pool_3x3', 1, 0.1456287)), (('skip_connect', 1, 0.15625753), ('max_pool_3x3', 1, 0.1543942)), (('max_pool_3x3', 1, 0.15630342), ('skip_connect', 1, 0.15141682))], 'normal_concat': [2, 3, 4,...

I have met this problem too, and don't know why it happens :(

Under settings and versions in my question. I followed your reply, and added Back ward name to CONV. As the result, I solved this problem. Thanks for helping. Details are...

I have the same issue, I use a single 3090, and I can't reproduce the accuracy of 94% neither. The BEST acc I can get is 88% in 25 epoch.

求相关群链接

> Hi, did you manage to implement the fine tune results with these codes, I found there is a huge gap between the paper and this codebase's. I only change...