From efb8a34767b128bb691fd63252bc306b42397015 Mon Sep 17 00:00:00 2001 From: Chaopeng Shen Date: Tue, 17 Dec 2024 02:42:01 -0500 Subject: [PATCH] Update frameworks.md Find it a little confusing to have this point to another page. I made it point to github here directly. --- docs/codes/frameworks.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/docs/codes/frameworks.md b/docs/codes/frameworks.md index 868a3ec..45d4d60 100644 --- a/docs/codes/frameworks.md +++ b/docs/codes/frameworks.md @@ -5,9 +5,11 @@ [Code Release][dmg_code] -`𝛿MG` is a domain-agnostic, PyTorch-based framework for developing trainable differentiable models that merge neural networks with process-based equations. +[`𝛿MG`](https://github.com/mhpi/generic_deltaModel) is a domain-agnostic, PyTorch-based framework for developing trainable differentiable models that merge neural networks with process-based equations. 𝛿MG is not a partcularly model. Rather, it is a generic framework that support many models across various domains (some are from HydroDL2.0) in a uniform way, while integrating ecosystem tools. Although the packages contains some basic examples for learners' convenience, the deployment models are supposed to exit in separate repositories and couple to the 𝛿MG framework. -The `hydroDL2` repository for hydrology models couples with the 𝛿MG framework to enable MHPI-specific hydrologic modeling capabilities. The combination serves both as a benchmark capability for published results (including those that used hydroDL) and an exploratory platform for future hydrology research in MHPI. +For example, the [`hydroDL2`](https://github.com/mhpi/hydroDL2) repository for hydrology models couples with the 𝛿MG framework to enable MHPI-specific hydrologic modeling capabilities. The combination serves both as a benchmark capability for published results (including those that used hydroDL) and an exploratory platform for future hydrology research in MHPI. + +We include an optional [GUI](https://mhpi-spatial.s3.us-east-2.amazonaws.com/mhpi-release/config_builder_gui/Config+Builder+GUI.zip) ([source code](https://github.com/mhpi/GUI-Config-builder)) for constructing/editing 𝛿MG YAML configuration files with a user-friendly interface: Closely synergizes with deep learning tools and the scale advantage of PyTorch. Maintained by the [MHPI group](http://water.engr.psu.edu/shen/) advised by Dr. Chaopeng Shen. @@ -24,4 +26,4 @@ In 𝛿MG, we define a differentiable model with the class *DeltaModel* that can The *DeltaModel* object can be trained and forwarded just as any other PyTorch model (nn.Module). - [dmg_code]: ../dmg/code.md + [dmg_code]: https://github.com/mhpi/generic_deltaModel