DeepEMD

DeepEMD copied to clipboard

All the results are lower than paper with the default settings and feature pyramid 5,2,1

1

I have tried FCN pyramid structure 5,2,1 in the paper, but the accuracy on miniImagenenet is still 65.5%. Besides, acc on tiered imagenet is 70.6%(2% lower), 72.8%(2% lower) on CIFAR-FS,...

Germany321

Can't achieve the accuracy in the papar

5

I pretrained the model and then used deep emd with the default setting, but the 5-way-1-shot accuracy was just 65.5%, which was 1% lower than the paper.

Germany321

About the acc on miniImageNet

2

Hi，I use the parameters you gave to train on miniimagenet，the model is DeepEMD-FCN. But the acc_test=60.5072. Did you use another training strategy, or did you pre-train on ImageNet？Looking forward to...

marson666

dataset structure？

1

-0: 1 2..... -1: 1 2....

Williamlizl

The memory of QPTH-solver(5way-1shot) is about 22GB

1


SethDeng

Fail to reproduce accuracy for miniimagenet

1

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%....

viviGeng

Dear author, thanks for opening source your project. I am just wondering if you can publish the training script for CUB and CIFAR datasets that can potentially achieve the results...

RongKaiWeskerMA

Code for Visualization of Fig 6 & 7 in the paper

2

Hi @icoz69 , Thanks for your great work!! I am impressed by your visualization **Fig 6 & 7** in the [paper](https://arxiv.org/pdf/2003.06777.pdf) to explain matching patches of images. Do you have...

haithanhp

opencv solver for 5-shot evaluation

4

Hi, I saw the default setting (both the eval.py and the evaluation command-line script in the ReadMe file) is using opencv solver. However, for 5-shot evaluation, the structured FC weights...

Tsingularity

Unable to REPEAT previous results.

1

Although setting the same random seed, the accuracy results of two experiments with the same setting are different. Code: os.environ['PYTHONHASHSEED'] = str(seed) random.seed(seed) np.random.seed(seed) torch.manual_seed(seed) torch.cuda.manual_seed(seed) torch.cuda.manual_seed_all(seed) torch.backends.cudnn.benchmark = False...

lovelyczli