shapes (1780,444) and (2,10) not aligned: 444 (dim 1) != 2 (dim 0)

这个错误通常是由于矩阵乘法时矩阵的维度不匹配引起的。在这个错误中，矩阵 A 的形状为 (1780, 444)，矩阵 B 的形状为 (2, 10)。由于矩阵乘法的规则是，第一个矩阵的列数必须等于第二个矩阵的行数，因此在这种情况下，无法将这两个矩阵相乘。

要解决这个问题，你需要检查你的代码，找出哪里出了问题。你可能会发现有一个错误的矩阵尺寸或者你没有正确地转置矩阵。可以通过调试或者打印相关的矩阵来查找错误。

相关问题

为什么affine_forward怎么修改都会出现shapes () and ) not aligned: (dim 1) != (dim 0)

这个错误通常是由于输入的x和w的形状不兼容引起的。在affine_forward函数中，x和w的形状必须满足矩阵乘法的规则，即x的第二个维度必须等于w的第一个维度，否则就会出现shapes not aligned的错误。因此需要确保x和w的形状是兼容的，才能进行矩阵乘法运算。在修改代码时，需要注意确保x和w的形状是兼容的，也可以使用reshape函数来调整它们的形状。

ValueError: shapes (50,2) and (1,2) not aligned: 2 (dim 1) != 1 (dim 0)

This error occurs when trying to perform an operation that requires two arrays to have the same shape or compatible shapes, but their shapes are not compatible.

In this specific case, the error message indicates that you are trying to perform an operation between two arrays with shapes (50,2) and (1,2), respectively. The error occurs because the second array has only one row, while the first one has 50 rows, and the operation cannot be performed because the dimensions are not compatible.

To resolve this error, you need to ensure that the shapes of the arrays you are working with are compatible for the operation you want to perform. You can reshape the arrays or use broadcasting to make sure their shapes match.