search

NVIDIA / modulus-launch

Repo of optimized training recipes for accelerating PyTorch workflows of AI driven surrogates for physical systems
Apache License 2.0
54 stars 27 forks source link

🐛[BUG]: Issues In vortex_shedding_mgn example #83

Open lucapegolotti opened 1 year ago

lucapegolotti commented 1 year ago

Version

0.1.0

On which installation method(s) does this occur?

No response

Describe the issue

I noticed a couple of potential issues in inference.py in the vortex_shedding_mgn example:

  1. line 87: variables are denormalized before entering the model.
  2. line 101: i is incremented, but it is already the index of the loop iteration.

Minimum reproducible example

No response

Relevant log output

No response

Environment details

No response

cfd1 commented 1 year ago

There is also an issue with loading the checkpoint

Screenshot from 2023-09-23 11-13-53

this needs to be fixed for when no scaler is passed