Closed HydrogenSulfate closed 1 year ago
I got the same question as yours, do you have any ideas now? Thx
I got the same question as yours, do you have any ideas now? Thx
We've tries several times for reproducing with paddlepaddle, but got many result up to Top1=83.58%, still has 0.27% diff to official Top1=83.85%.
We find this may be a slightly overfitting, so we add a Mixup
to moderate, and finally achieve to 83.84%, please check the model and config below:
efficientnet_v2.py
EfficientNetV2_S.yaml
The reson might be framework differences between tf and paddlepaddle/pytorch. As we all know, many paper in tensorflow always hard to reproduce same metric by other DL frameworks and always got slightly lower metric.
for example: the max value of
dropout_rate
andram
is 0.2 and 10 ineffnetv2_configs.py
, but 0.3 and 15 in paper, anddropout_rate
seems not progressively changed in 4 traning stages