some trouble in train 1H

[CMYCMY1]

I've commented <self.layer4 = hourglass_block(128, 128)>、<self.layer3= hourglass_block(128, 128)>、<self.layer2 = hourglass_block(128, 128)> and <result4, out, feature4 = self.layer4(out)>、<result3, out, feature3 = self.layer3(out)>、<result2, out, feature2 = self.layer2(out)> , also I modify the <return [result1, result2, result3, result4], [feature1, feature2, feature3, feature4]> to <return [result1], [feature1]>, and I changed "index=[3]" to "index=[0]",

but there was a problem with the evaluation，The error is displayed as follows “'int' object has no attribute 'data'” .
I would appreciate it if the author could tell me how to solve this problem.

[koyeongmin]

I cannot find the reason. I checked some points' ".data" attribute, but there is no int object. If you can share more detailed error messages (line number, ... ), it will be more helpful. Thank you!

[CMYCMY1]

Thank you for your reply！More error details are shown in the figure：

[koyeongmin]

For calculating the attention loss, the deeper network's feature acts as a teacher. However, if you set only one hourglass network to use, there is no teacher network, so "attention_loss" becomes zero, int type (there are no changes from line 253). If you remove the attention loss parts, it will work.

[CMYCMY1]

It worked.Thank you very much!