johsnows

V3是否有在imagenet预训练过？没有预训练的效果很差

1

Average Precision Per-class: aeroplane: 0.5286851217064079 bicycle: 0.5684498038841389 bird: 0.2951959818198857 boat: 0.3374119115412078 bottle: 0.11274539710602145 bus: 0.5840837968782298 car: 0.5631029936677479 cat: 0.5605063414099851 chair: 0.24291365433556902 cow: 0.2908948526148929 diningtable: 0.4292561103683377 dog: 0.47845551032801703 horse: 0.6137629939581943 motorbike:...

from yacs.config import CfgNode as CN

in layer4, if dilation =2 and padding =2, will raise this error shape torch.Size([4, 2048, 35, 35]) torch.Size([4, 2048, 33, 33]) Traceback (most recent call last): File "prune.py", line 265,...

subnet重训练代码

1

project里似乎只有supernet的训练代码，子网的重训练代码请问是否能提供？

i didn't found the CNN on your link？ can u provided more detailed link？ thank u~

grad*reward?is this rigorous? i used this code to apply to svhn dataset, and got very low accuracy, and sometimes the accuracy will accuracy will increase and then decrease, so i...

which genotype is best？

5

after search on the train_search.py, we get many genotype, no restrict skipconnetct genotype and genotypes with number of skip-connect:7,6,5,4,3,2,1,0, which one is best? which one is recommended to evaluate?