了解GPU上的Pytorch内存分配

我有以下代码片段在Pytorch中进行复杂乘法 Variation 3 def complex_mult(x, y): a, b = x[:, :, :, :, :, 0], x[:, :, :, :, :, 1] c, d = y[:, :, :, :, :, 0], y[:, :, :, :, :, 1] out = torch.stack([a*c - b*d, a*d + b*c], dim=-1) return out As I was investigating why I a...