You can add the losses inplace as long as no errors are raised, but would accumulate the computation graphs. This post explains it in more detail.
The losses wouldn’t be equal, since you are scaling loss2 by len(x) in each iteration.
You can add the losses inplace as long as no errors are raised, but would accumulate the computation graphs. This post explains it in more detail.
The losses wouldn’t be equal, since you are scaling loss2 by len(x) in each iteration.