Difficulties calculating mean square error between 2 tensors

I’m trying to build a loss function which will calculate the mean squared error of 2 tenors of the same size. In other words I need a function that calcualtes the difference of every 2 cells (with the same row and column) cell on matrix A and matrix B, squares it and calculate the mean of the differences.

As far as I understand nn.MSELoss should do exactly that.

When I pass the 2 tensors to nn.MSELoss I’m getting the following error message:

RuntimeError: Boolean value of Tensor with more than one value is ambiguous

Here’s my code


The tensors are floats of same shape.

stack_3.shape, stack_7.shape
(torch.Size([6131, 784]), torch.Size([6131, 784]))

You would have to create an object for the loss function and use it afterwards:

criterion = nn.MSELoss()
loss = criterion(stack_3[0, :], stack_7[0, :])
1 Like