Ran Gu

hello, you can transform the attention weight in the middle step from tensor to numpy, and then save to Image (.png, .jpg).

Hi rp775, Yes, you need to save the attention weight as an image. As you see in the validation.py and 'network.py', we have provided the commands obtaining the attention weight,...

Hi everyone, as I previously said. If you want to get the attention weight for test data to see the attention weight map, you just need to replace 'output =...

yes, there are mistakes, thanks for your feedback. I will correct it later.

The dropout mistake does not affect the experimental results. HeyWhale8 ***@***.***> 于2021年11月18日周四 下午5:36写道： > If you use this code in your paper experiment, I'm afraid your > experimental results can't...

In the paper, the result is an average of three times test as I mentioned in the paper. HeyWhale8 ***@***.***> 于2021年11月18日周四 下午11:39写道： > Can you run your pre-trained model on...

Thanks for your issue. Yes, it is better to use nearest-neighbor interpolation for label resize.

关于t-test，你可以保存下来每个测试样本的测试结果，然后再用python的三方库就可以进行计算，比如scipy.states就提供有t-test的函数，具体可以参见：https://blog.csdn.net/charie411/article/details/100009024

你好，你这里展示的是底层代码，看起来像是数据加载过程中没有读到数据，请检查读取数据的地址是否正确

Hi userhr2333, thanks for your interest in our project. You are right, there is a mistake in cscada_net.py, and we have corrected it in our new version in cscada_net.py.