Closed bensch98 closed 1 year ago
Hi!
Pre-computing the spectral basis is also necessary for inference. It doesn't necessarily need to be cached/fetched (it could be computed on the fly right before evaluating the network), caching can be disabled by setting op_cache_dir=None
in the get_operator()
/get_all_operators()
functions. But the basis still needs to be computed either way.
If the precomputation cost is a problem for you, there are a few possible workarounds:
method='implicit_dense'
in the diffusion layer. This switches to an $~O(N^3)$ dense solver, but it avoids the need to precompute a spectral basis.k_eig
). The default is 128
, but for many applications you can go down to ~32
without much loss of performance.
I'm currently looking where I can speed up my whole inference pipeline. Is the computation of the operators at the end of the dataset.py necessary for pure inference or is it just useful for caching during training?