Fail to reproduce accuracy for miniimagenet

icoz69 / DeepEMD

Code for paper "DeepEMD: Few-Shot Image Classification with Differentiable Earth Mover's Distance and Structured Classifiers", CVPR2020

MIT License

577 stars 82 forks source link

Fail to reproduce accuracy for miniimagenet #42

Open viviGeng opened 3 years ago

viviGeng commented 3 years ago

Hi. I tried to reproduce results for MiniImageNet in DeepEMD FCN following your instruction, but failed to get the accuracy listed in your paper. The evaluation accuracy is only 55%.

Here is my training scripts:

$ python train_pretrain.py -shot 1 -way 5 -dataset miniimagenet -gpu 
$ python train_meta.py -deepemd fcn -shot 1 -way 5 -solver opencv -dataset miniimagenet -gpu 0
$ python eval.py -shot 1 -way 5 -dataset miniimagenet -gpu

Could you give me some tips? Looking forward to your reply.

icoz69 commented 3 years ago

hi the command looks correct. Are you using the raw codes and datasets to reproduce?