wenbinlee / covamnet Goto Github PK

您好，请问“将z中的m个局部相似度值进行线性加权，得到查询图像与类别之间的全局相似度Z”，请问这个权重是如何计算的呢？

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

Hello, when I tested, I encountered the following problem。

Traceback (most recent call last):
File "D:/yy/2019.3-/code/CovaMNet-master/CovaMNet_Test_5way1shot.py", line 293, in
test_accuracy, h = mean_confidence_interval(accuracies)
File "D:/yy/2019.3-/code/CovaMNet-master/CovaMNet_Test_5way1shot.py", line 246, in mean_confidence_interval
m, se = np.mean(a), scipy.stats.sem(a)
File "D:\Program\Anaconda3\envs\env_name\lib\site-packages\numpy\core\fromnumeric.py", line 3118, in mean
out=out, **kwargs)
File "D:\Program\Anaconda3\envs\env_name\lib\site-packages\numpy\core_methods.py", line 85, in _mean
ret = ret.dtype.type(ret / rcount)
AttributeError: 'torch.dtype' object has no attribute 'type'

I tried to make some changes, replacing np.mean(a) with torch.mean(torch.stack(a)), but there are still other problems.

I will be great appreciate that if you can tell me how to solve this problem.

HI,
I am working on my custom logo detection dataset.Can you guide me on how to train and test(detection) my model.Mainly im not able to understand the detection part.Kindly provide more details,also mention on how to use 5 shot algorithm

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.