bug1:
one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [128, 15]], which is output 0 of TBackward, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).
跟着莫凡老师学习GAN网络,写好代码却一直在报错,同时我也使用了retain_graph=True, 按理来说不应该报错了,看了很多解释说是版本问题,好像是inplace 设置问题,但是我不太懂。
找到莫凡老师在github的源代码,发现可以运行,然后对比了一下,找到了一些原因,我修改了一下我的代码
图1, 初始代码
图2,修改之后的代码