如何在 libtorch 中堆叠形状为 (n, k) 的张量和形状为 (k) 的张量?
How to stack a tensor of shape (n, k) with tensors of shape (k) in libtorch?
torch::stack
接受 c10::TensorList
并且在给出相同形状的张量时工作得很好。但是,当您尝试发送先前 torch::stack
ed Tensor 的输出时,它会失败并出现内存访问冲突。
更具体地说,假设我们有 3 个形状为 4 的张量,例如:
torch::Tensor x1 = torch::randn({4});
torch::Tensor x2 = torch::randn({4});
torch::Tensor x3 = torch::randn({4});
torch::Tensor y = torch::randn({4});
第一轮堆叠很简单:
torch::Tensor stacked_xs = torch::stack({x1,x2,x3});
但是,正在努力做到:
torch::Tensor stacked_result = torch::stack({y, stacked_xs});
会失败。
我希望获得与 Python 中的 np.vstack
相同的行为,这是允许的并且有效。
我该怎么办?
您可以使用 torch::unsqueeze
向 y
添加维度。然后与 cat
连接(不是 stack
,与 numpy 不同,但结果将是你要求的):
torch::Tensor x1 = torch::randn({4});
torch::Tensor x2 = torch::randn({4});
torch::Tensor x3 = torch::randn({4});
torch::Tensor y = torch::randn({4});
torch::Tensor stacked_xs = torch::stack({x1,x2,x3});
torch::Tensor stacked_result = torch::cat({y.unsqueeze(0), stacked_xs});
也可以根据您的喜好展平您的第一个堆栈,然后对其进行整形:
torch::Tensor stacked_xs = torch::stack({x1,x2,x3});
torch::Tensor stacked_result = torch::cat({y, stacked_xs.view({-1}}).view({4,4});
torch::stack
接受 c10::TensorList
并且在给出相同形状的张量时工作得很好。但是,当您尝试发送先前 torch::stack
ed Tensor 的输出时,它会失败并出现内存访问冲突。
更具体地说,假设我们有 3 个形状为 4 的张量,例如:
torch::Tensor x1 = torch::randn({4});
torch::Tensor x2 = torch::randn({4});
torch::Tensor x3 = torch::randn({4});
torch::Tensor y = torch::randn({4});
第一轮堆叠很简单:
torch::Tensor stacked_xs = torch::stack({x1,x2,x3});
但是,正在努力做到:
torch::Tensor stacked_result = torch::stack({y, stacked_xs});
会失败。
我希望获得与 Python 中的 np.vstack
相同的行为,这是允许的并且有效。
我该怎么办?
您可以使用 torch::unsqueeze
向 y
添加维度。然后与 cat
连接(不是 stack
,与 numpy 不同,但结果将是你要求的):
torch::Tensor x1 = torch::randn({4});
torch::Tensor x2 = torch::randn({4});
torch::Tensor x3 = torch::randn({4});
torch::Tensor y = torch::randn({4});
torch::Tensor stacked_xs = torch::stack({x1,x2,x3});
torch::Tensor stacked_result = torch::cat({y.unsqueeze(0), stacked_xs});
也可以根据您的喜好展平您的第一个堆栈,然后对其进行整形:
torch::Tensor stacked_xs = torch::stack({x1,x2,x3});
torch::Tensor stacked_result = torch::cat({y, stacked_xs.view({-1}}).view({4,4});