EfficientNet-PyTorch icon indicating copy to clipboard operation
EfficientNet-PyTorch copied to clipboard

Published 20 hours ago • verified publisher icon lukemelas

Got the Top-1 accu of only 70.7% when training efficientnet-b3 with Imagenet

Open YvetteLaw opened this issue 4 years ago • 3 comments

I train efficientnet-b3 with ImageNet dataset by the script in ./examples/imagenet/main.py with the following command python main.py /path/to/imagenet -b 128 --image_size 300 -a 'efficient-b3' . The GPU of my machine is Tesla V100 and I trained with 8P. After the default 90 epochs, I got the following result: Acc@1 70.702 Acc@5 90.050. The top-1 accuracy of 70.7% is not as good as 80.8% claimed. Is there anything wrong with my command? Or what factors result in this result？

YvetteLaw avatar Aug 26 '21 07:08 YvetteLaw

I eval the provided efficientnet-b4, and got only 77.516 top1 on imagenet val set.

RuiFeiHe avatar Sep 12 '21 08:09 RuiFeiHe

I eval the provided efficientnet-b4, and got only 77.516 top1 on imagenet val set.

I got only 74.99% top1 with efficientnet-b4.

JGyoung33 avatar Mar 13 '22 01:03 JGyoung33

@YvetteLaw can you please share the dataset structure?

hamzakhalil798 avatar Nov 15 '22 11:11 hamzakhalil798