Make `torch_nets.models.ANN` more flexible by adopting a list of `Linear` layers

m2lines / convection-parameterization-in-CAM

Deployment of the convection parameterization scheme (previously from within SAM) deployed into the CAM model

MIT License

3 stars 2 forks source link

Make `torch_nets.models.ANN` more flexible by adopting a list of `Linear` layers #51

Closed tztsai closed 8 months ago

tztsai commented 10 months ago

Currently the Linear layers of ANN is hand-coded as linear1, linear2, etc. It may be more flexible to use a list of Linear layers, so that the number of layers can vary and the forward method can also be simplified using a for loop.