one of the variables needed for gradient computation has been modified by an inplace operation: [tor

报错：
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [256, 3, 32, 32]] is at version 768; expected version 512 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

问题原因：

利用a变量进行一次网络运算后，使用修改后的a变量又进行一次网络运算，而网络在后向传播时，发现第一次网络运算的梯度溯源失败，a变量被修改了。

解决方案：
增加一个z变量，用copy函数浅拷贝一份原数据，在原数据的基础上进行改动。让梯度计算时能够溯源。

			z=copy.copy(imgs[:, net_idx, ...])
            with torch.no_grad():
                for img_id, imgg in enumerate(z):
                    z[img_id]=(cutout(imgg))