CovaMNet
CovaMNet copied to clipboard
WenbinLee
The Pytorch code of "Distribution Consistency based Covariance Metric Networks for Few-shot Learning", AAAI 2019.
您好，想问一下，在训练阶段，就已经对测试集进行测试了对吗？ 还有训练阶段的 # Fix the parameters of Batch Normalization after 10000 episodes (1 epoch) if epoch_item < 1: model.train() else: model.eval() 这几行代码是什么意思呢？epoch_item是不是从for epoch_item in range(opt.epochs):这里获取的
准确率问题
您好，我在本地测试了代码的结果，发现在miniImageNet数据集上准确率相当，但在stand_dog和Cub_bird数据集上测试出来的准确率相较于论文中要差3%-4%，是否是超参对结果有影响呢，还是我多重复跑几次可能会有更好的结果？ 麻烦您了
Do you have the implementation code for prototypical network，I want reproduce the results in the three datasets(Stanford Dog,Stanford Car and CUB)that showed in your paper.Perhaps I would cite your article.
