Question

我要向量化以下代码：

def style_noise(self, y, style):
    n = torch.randn(y.shape)
    for i in range(n.shape[0]):
        n[i] = (n[i] - n.mean(dim=(1, 2, 3))[i]) * style.std(dim=(1, 2, 3))[i] / n.std(dim=(1, 2, 3))[i] + style.mean(dim=(1, 2, 3))[i]
    noise = Variable(n, requires_grad=False).to(y.device)
    return noise

我没有找到一种很好的方法。

y和style是4d张量，例如style.shape = y.shape = [64, 3, 128, 128]。

我想返回噪声张量noise.shape = [64, 3, 128, 128]。

如果问题不清楚，请在评论中让我知道。

Answer 1

您的用例正是.mean和.std方法带有keepdim参数的原因。您可以利用此功能来使broadcasting semantics为您向量化事物：

def style_noise(self, y, style):
    n = torch.randn(y.shape)
    n_mean = n.mean(dim=(1, 2, 3), keepdim=True)
    n_std = n.std(dim=(1, 2, 3), keepdim=True)
    style_mean = style.mean(dim=(1, 2, 3), keepdim=True)
    style_std = style.std(dim=(1, 2, 3), keepdim=True)
    n = (n - n_mean) * style_std / n_std + style_mean
    noise = Variable(n, requires_grad=False).to(y.device)
    return noise

Answer 2

要计算整个张量的均值和标准差，请不要设置任何参数

m = t.mean(); print(m) # if you don't set the dim for the whole tensor
s = t.std(); print(s) # if you don't set the dim for the whole tensor

然后，如果您的形状是2,2,2，则创建张量以广播减法和除法。

ss = torch.empty(2,2,2).fill_(s)
print(ss)

mm = torch.empty(2,2,2).fill_(m)
print(mm)

当您未设置keepdim时，dim目前无法正常工作。

m = t.mean(); print(m) # for the whole tensor
s = t.std(); print(s) # for the whole tensor

m = t.mean(dim=0); print(m) # 0 means columns mean
s = t.std(dim=0); print(s) # 0 means columns mean

m = t.mean(dim=1); print(m) # 1 means rows mean
s = t.std(dim=1); print(s) # 1 means rows mean

s = t.mean(keepdim=True);print(s) # will not work
m = t.std(keepdim=True);print(m) # will not work

如果将一个dim设置为元组，则它将返回平均值，而不是全部。

如何将总和向量化？张量[i，：，：，：] +张量[i]

2 个答案: