Tensor 常用点备忘录

原创已于 2022-03-03 14:25:17 修改 · 783 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#pytorc #基础

于 2022-03-03 14:24:13 首次发布

PyTorch 专栏收录该内容

33 篇文章

订阅专栏

该教程介绍了Pytorch中如何进行矩阵乘法和元素级乘法。使用`@`运算符、`matmul()`函数以及`mul()`函数分别实现了矩阵的乘法，而`*`运算符和`mul()`函数用于执行元素级乘法。同时，提到了在位操作可能带来的内存节省但可能导致梯度计算问题，因此不推荐频繁使用。

1 来自 Pytorch 官网 Tutorial

矩阵乘法和 element-wise 乘法

# This computes the matrix multiplication between two tensors. y1, y2, y3 will have the same value
y1 = tensor @ tensor.T
y2 = tensor.matmul(tensor.T)

y3 = torch.rand_like(tensor)
torch.matmul(tensor, tensor.T, out=y3)


# This computes the element-wise product. z1, z2, z3 will have the same value
z1 = tensor * tensor
z2 = tensor.mul(tensor)

z3 = torch.rand_like(tensor)
torch.mul(tensor, tensor, out=z3)

note: In-place operations save some memory, but can be problematic when computing derivatives because of an immediate loss of history. Hence, their use is discouraged.