if use_fork is false, this should be ignored

alasdairtran / fourierflow

[ICLR 2023] Factorized Fourier Neural Operators

https://arxiv.org/abs/2111.13802

MIT License

144 stars 19 forks source link

if use_fork is false, this should be ignored #3

Open hsliuustc opened 2 years ago

hsliuustc commented 2 years ago

https://github.com/alasdairtran/fourierflow/blob/97e6cfb0848e44d3a7bc1d063b1ab86bc4c603ee/fourierflow/modules/fourier_2d_factorized_parallel.py#L218

alasdairtran commented 2 years ago

Yeah you're right! I had a go at running the experiment with avg_outs set to False, and it makes no difference to the loss (which makes sense since it's just a linear scaling factor, which the projection layer can easily learn). I'll probably remove this scaling altogether in the next iteration of experiments.