search

tum-pbs / PhiFlow

A differentiable PDE solving framework for machine learning
MIT License
1.43k stars 193 forks source link

INNs #78

Closed kbali1297 closed 2 years ago

kbali1297 commented 2 years ago

Currently implemented INNs for pytorch. User can concatenate multiple coupling layers to compose an INN. User can set backward = True and compute input feature map with the existing network from the output feature map. Current Drawback : input and output shape for each coupling layer is identical (bijectivity is important for inversion).

kbali1297 commented 2 years ago

Closed request accidently while renaming the branch. Please refer to the latest pull request #79