Giters

huawei-noah / Efficient-AI-Backbones

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Evaluation Mode doesn't work.

Leanna97 opened this issue · comments

commented

Thanks for your great work. I train my 'vig_ti_224_gelu' model and the accuracy reaches 78.22%. These results are from the summary.csv generated during training. When I try to resume the saved checkpoint using '--resume', it works well. However, when I tried to evaluate the saved model using '--evaluate', the results become 1.04% and the loss is nan. Could anyone help me to solve this problem?

summary.csv:
image

'--evaluate':
image

commented

Thanks for your great work. I train my 'vig_ti_224_gelu' model and the accuracy reaches 78.22%. These results are from the summary.csv generated during training. When I try to resume the saved checkpoint using '--resume', it works well. However, when I tried to evaluate the saved model using '--evaluate', the results become 1.04% and the loss is nan. Could anyone help me to solve this problem?

summary.csv: image

'--evaluate': image

Hi, Have you found a solution? I have the same problem。

commented

I think it's the version issue. Please refer to #219 (comment)