Framework providing pythonic APIs, algorithms and utilities to be used with Modulus core to physics inform model training as well as higher level abstraction for domain experts
The order of args for Conv1dFCLayer layer changed during Sym-Core integration PR here: https://github.com/NVIDIA/modulus-sym/pull/62. This caused the values for weight_norm and activation_par to be inverted for Conv1dFCLayer. This PR fixes that issue by making the args explicit.
This also fixes the FNO predictions as ConvFullyConnectedArch model was used for decoder.
ktangsali
commented
6 months ago
Modulus Pull Request
Description
The order of args for
Conv1dFCLayerlayer changed during Sym-Core integration PR here: https://github.com/NVIDIA/modulus-sym/pull/62. This caused the values forweight_normandactivation_parto be inverted forConv1dFCLayer. This PR fixes that issue by making the args explicit.This also fixes the FNO predictions as
ConvFullyConnectedArchmodel was used for decoder.Checklist
Dependencies