Unverified Commit ad7cad50 authored by Gao, Xiang's avatar Gao, Xiang Committed by GitHub
Browse files

Add warning to training setup (#469)

parent 01b0fb17
...@@ -15,6 +15,19 @@ specified in `inputtrain.ipt`_ ...@@ -15,6 +15,19 @@ specified in `inputtrain.ipt`_
.. note:: .. note::
TorchANI provide tools to run NeuroChem training config file `inputtrain.ipt`. TorchANI provide tools to run NeuroChem training config file `inputtrain.ipt`.
See: :ref:`neurochem-training`. See: :ref:`neurochem-training`.
.. warning::
The training setup used in this file is configured to reproduce the original research
at `Less is more: Sampling chemical space with active learning`_ as much as possible.
That research was done on a different platform called NeuroChem which has many default
options and technical details different from PyTorch. Some decisions made here
(such as, using NeuroChem's initialization instead of PyTorch's default initialization)
is not because it gives better result, but solely based on reproducing the original
research. This file should not be interpreted as a suggestions to the readers on how
they should setup their models.
.. _`Less is more: Sampling chemical space with active learning`:
https://aip.scitation.org/doi/full/10.1063/1.5023802
""" """
############################################################################### ###############################################################################
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment