Open csinva opened 1 month ago
Me, too. But the examples/mnist.py can work correctly.
Worked okay when I just lowered the learning rate / switched the optimizer...
That one happens somewhat randomly when reconstructing the splines on the new grid (performing update_grid
)... Possibly some numerical failure in the Least Square optimization. I also encountered that in some cases. To workaround that, consider pre-normalize input into [-1, 1]
, and avoid calling update_grid
.
Getting this error when running
test_simple_math.py
. Any idea how to resolve it?(pytorch is up-to-date, version '2.3.0+cu121', python 3.11)