load_state_dict

This function should only be used to load models saved in python.
For it to work correctly you need to use <code>torch.save</code> with the flag:
<code>_use_new_zipfile_serialization=True</code> and also remove all <code>nn.Parameter</code>
classes from the tensors in the dict.

Provides functionality to define and train neural networks similar to
'PyTorch' by Paszke et al (2019) <doi:10.48550/arXiv.1912.01703> but written entirely in R
using the 'libtorch' library. Also supports low-level tensor operations and
'GPU' acceleration.

Daniel Falbel

torch

Tensors and Neural Networks with 'GPU' Acceleration

Javier Luraschi

Dmitriy Selivanov

Athos Damiani

Christophe Regouby

Krzysztof Joachimiak

Hamada S. Badr

Sebastian Fischer

Maximilian Pichler

 RStudio

load_state_dict function

<dl><dt>path</dt>
<dd>to the state dict file</dd>
<dt>...</dt>
<dd>additional arguments that are currently not used.</dd>
<dt>legacy_stream</dt>
<dd>if <code>TRUE</code> then the state dict is loaded using a
a legacy way of handling streams.</dd></dl>

Arguments

Load a state dict file — load_state_dict

<dl>

<dt>path</dt>
<dd>to the state dict file</dd>


<dt>...</dt>
<dd>additional arguments that are currently not used.</dd>


<dt>legacy_stream</dt>
<dd>if <code>TRUE</code> then the state dict is loaded using a
a legacy way of handling streams.</dd>

</dl>

Load a state dict file

load_state_dict: Load a state dict file

Description

Usage

Value

Arguments

Details