From 3bfa19cd4ecf3ba71f5364e14fc5e88aee713c21 Mon Sep 17 00:00:00 2001 From: Karol Blaszczak Date: Mon, 20 Jan 2025 16:39:56 +0100 Subject: [PATCH] [DOCS] Remove "experimental" note for torch.export port (#28558) port: https://github.com/openvinotoolkit/openvino/pull/28492 by M. Vafin Signed-off-by: Maxim Vafin Co-authored-by: Maxim Vafin --- .../model-preparation/convert-model-pytorch.rst | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/docs/articles_en/openvino-workflow/model-preparation/convert-model-pytorch.rst b/docs/articles_en/openvino-workflow/model-preparation/convert-model-pytorch.rst index fc2637aba9139e..fa1b6b733bb548 100644 --- a/docs/articles_en/openvino-workflow/model-preparation/convert-model-pytorch.rst +++ b/docs/articles_en/openvino-workflow/model-preparation/convert-model-pytorch.rst @@ -179,7 +179,7 @@ It is recommended to address model outputs by the index rather then the name. Support for torch.export ######################## -`torch.export `__ is the current way to get a graph +`torch.export `__ is the current way to get a graph representation of a model (since PyTorch 2.1). It produces ``ExportedProgram`` which includes the graph representation in the FX format. To see why it has an advantage over the TorchScript representation, refer to `PyTorch documentation `__. @@ -198,11 +198,6 @@ Here is an example of how to convert a model obtained with ``torch.export``: exported_model = export(model, (torch.randn(1, 3, 224, 224),)) ov_model = convert_model(exported_model) -.. note:: - - This is an experimental feature. Use it only if you know that you need to. PyTorch version 2.2 - is recommended. Dynamic shapes are not supported yet. - Converting a PyTorch Model from Disk ####################################