About：AttributeError: 'Conv2d' object has no attribute 'weight' about self-attention-gan HOT 8 OPEN

Got a similar issue. The reason is that, as shown in line 59 of spectral.py, weight attribute of whatever module you used (in your case Conv2d) is deleted. Instead weight_u weight_v and weight_bar are added.

from self-attention-gan.

解决了 其实就是删除了生成器和鉴别器的初始化，采用pytorch默认初始化方式，原因是SN层那里是复合网络结构，编译器无法拆分到底层找到conv进行初始化。。。所以要加SN层的话要么把netD.apply(weights_init)和netG.apply(weights_init)删了，要么重写SN结构把它和conv2d单独提出来写。。

from self-attention-gan.

Thank you for your reply!Your idea is great. Have a good life !

from self-attention-gan.

Thank you for your reply!Your idea is great. Have a good life !

I encountered the same problem as you. Have you solved this problem? Can you share your solution. thank you.

from self-attention-gan.

楼主怎么解决的啊？ 我自己加SN层也出现了这个问题

from self-attention-gan.

解决了 其实就是删除了生成器和鉴别器的初始化，采用pytorch默认初始化方式，原因是SN层那里是复合网络结构，编译器无法拆分到底层找到conv进行初始化。。。所以要加SN层的话要么把netD.apply(weights_init)和netG.apply(weights_init)删了，要么重写SN结构把它和conv2d单独提出来写。。

התפלק לך של סינים

מעשייך מסבירים למה היטלר הרג יהודים.

from self-attention-gan.

你好！感谢您对生成对抗网络研究的贡献并分享您的代码！我来自**。现在是**新年。祝你**新年快乐！我对你的论文很感兴趣，当我尝试在我的新网络中添加频谱归一化时，程序给出以下错误： Traceback（最近一次调用最后一次）： 文件“SR.py”，第 45 行，在 train(opt, Gs, Zs, reals, NoiseAmp) 文件“E:\SinGAN-masterplus\SinGAN\training.py”，第 34 行，训练中 D_curr,G_curr = init_models(opt) 文件“E:\SinGAN-masterplus\SinGAN\training.py” py”，第 310 行，init_models netG.apply(models.weights_init) 文件“E:\abcd\lib\site-packages\torch\nn\modules\module.py”，第 293 行， 文件“E:\abcd\lib\site-packages\torch\nn\modules\module.py”，第 293 行，在应用 module.apply(fn) 文件“E:\abcd\lib\site-packages\torch\ nn\modules\module.py”，第 294 行，在应用 fn(self) 文件“E:\SinGAN-masterplus\SinGAN\models.py”，第 215 行，在 weights_init m.weight.data.normal_(0.0, 0.02 ) 文件“E:\abcd\lib\site-packages\torch\nn\modules\module.py”，第 591 行，getattr 类型（self）。name , name)) AttributeError: 'Conv2d' 对象没有属性 'weight'

查了很多资料都解决不了，所以想请教一下，祝您生活愉快，期待您的回复！

请问问题解决了吗？

from self-attention-gan.

The solution is actually to delete the initialization of the generator and the initializer, using pytorch as the default initialization method, the reason is that the SN layer is a complex network structure, the compiler can't remove 分 to the end of the layer, and the conv is initialized... Or 把netD.apply(weights_init)和netG.apply(weights_init)删了，or 重写SN structure put it together and conv2d separately.

Split you of Chinese

Your actions explain why Hitler killed Jews.

That's a little too much.

from self-attention-gan.