PYTORCH_MODEL

	This is part of the pytorch module
	It is only available if you configure PLUMED with ./configure –enable-modules=pytorch . Furthermore, this feature is still being developed so take care when using it and report any problems on the mailing list.

Load a PyTorch model compiled with TorchScript.

This can be a function defined in Python or a more complex model, such as a neural network optimized on a set of data. In both cases the derivatives of the outputs with respect to the inputs are computed using the automatic differentiation (autograd) feature of Pytorch.

By default it is assumed that the model is saved as: model.ptc, unless otherwise indicated by the FILE keyword. The function automatically checks for the number of output dimensions and creates a component for each of them. The outputs are called node-i with i between 0 and N-1 for N outputs.

Note that this function is active only if LibTorch is correctly linked against PLUMED. Please check the instructions in the PYTORCH (Machine Learning Collective Variables) page.

Examples

Load a model called torch_model.ptc that takes as input two dihedral angles and returns two outputs.

Click on the labels of the actions for more information on what each action computes

#SETTINGS AUXFILE=regtest/pytorch/rt-pytorch_model_2d/torch_model.ptc
phi: TORSION 
ATOMS
the four atoms involved in the torsional angle 
=5,7,9,15 The TORSION action with label phi calculates a single scalar value
psi: TORSION 
ATOMS
the four atoms involved in the torsional angle 
=7,9,15,17 The TORSION action with label psi calculates a single scalar value
model: PYTORCH_MODEL 
FILE
Filename of the PyTorch compiled model 
=torch_model.ptc 
ARG
the input for this action is the scalar output from one or more other actions. 
=phi,psi The PYTORCH_MODEL action with label model calculates the following quantities:

 Quantity   
 Description  
model.node-0
Model outputs  This is the 0th of these quantities
model.node-1
Model outputs  This is the 1th of these quantities


PRINT 
FILE
the name of the file on which to output these quantities 
=COLVAR 
ARG
the input for this action is the scalar output from one or more other actions. 
=model.node-0,model.node-1 The PRINT action with label 

Glossary of keywords and components

Description of components

By default the value of the calculated quantity can be referenced elsewhere in the input file by using the label of the action. Alternatively this Action can be used to calculate the following quantities by employing the keywords listed below. These quantities can be referenced elsewhere in the input by using this Action's label followed by a dot and the name of the quantity required from the list below.

Quantity	Description
node	Model outputs

Options

NUMERICAL_DERIVATIVES	( default=off ) calculate the derivatives for these quantities numerically
ARG	the input for this action is the scalar output from one or more other actions. The particular scalars that you will use are referenced using the label of the action. If the label appears on its own then it is assumed that the Action calculates a single scalar value. The value of this scalar is thus used as the input to this new action. If * or *.* appears the scalars calculated by all the proceeding actions in the input file are taken. Some actions have multi-component outputs and each component of the output has a specific label. For example a DISTANCE action labelled dist may have three components x, y and z. To take just the x component you should use dist.x, if you wish to take all three components then use dist.*.More information on the referencing of Actions can be found in the section of the manual on the PLUMED Getting Started. Scalar values can also be referenced using POSIX regular expressions as detailed in the section on Regular Expressions. To use this feature you you must compile PLUMED with the appropriate flag.. You can use multiple instances of this keyword i.e. ARG1, ARG2, ARG3...
FILE	Filename of the PyTorch compiled model