From 15c10e74fe9d143c89131832540caf5f875e9827 Mon Sep 17 00:00:00 2001 From: Ilya Churaev Date: Thu, 29 Oct 2020 06:22:25 +0300 Subject: [PATCH] Added information about unsupported subgraphs for set affinity (#2872) --- docs/IE_DG/supported_plugins/HETERO.md | 2 ++ docs/nGraph_DG/nGraph_Python_API.md | 2 ++ 2 files changed, 4 insertions(+) diff --git a/docs/IE_DG/supported_plugins/HETERO.md b/docs/IE_DG/supported_plugins/HETERO.md index b395736983f..e417907b0a7 100644 --- a/docs/IE_DG/supported_plugins/HETERO.md +++ b/docs/IE_DG/supported_plugins/HETERO.md @@ -32,6 +32,8 @@ Another way to annotate a network is to set affinity manually using ngraph The fallback policy does not work if even one layer has an initialized affinity. The sequence should be calling of automating affinity settings and then fix manually. +> **NOTE**: If you set affinity manually, be careful at the current moment Inference Engine plugins don't support constant (`Constant`->`Result`) and empty (`Parameter`->`Result`) networks. Please avoid such subgraphs when you set affinity manually. + @snippet openvino/docs/snippets/HETERO1.cpp part1 If you rely on the default affinity distribution, you can avoid calling InferenceEngine::Core::QueryNetwork and just call InferenceEngine::Core::LoadNetwork instead: diff --git a/docs/nGraph_DG/nGraph_Python_API.md b/docs/nGraph_DG/nGraph_Python_API.md index f28253f41fb..3b778747c06 100644 --- a/docs/nGraph_DG/nGraph_Python_API.md +++ b/docs/nGraph_DG/nGraph_Python_API.md @@ -188,6 +188,8 @@ for node in function.get_ordered_ops(): Attributes are properties of nodes in the computational graph, which will be stored when the model is serialized to a file. However, there can be additional properties of nodes, which are only important during the execution of a graph. An example of such a property is `affinity`, which determines which operation will be executed on which hardware in a heterogeneous environment. You can get and set runtime information by using the `get_rt_info` method of a node. +> **NOTE**: If you set affinity manually, be careful at the current moment Inference Engine plugins don't support constant (`Constant`->`Result`) and empty (`Parameter`->`Result`) networks. Please avoid such subgraphs when you set affinity manually. + ```python rt_info = node.get_rt_info() rt_info["affinity"] = "test_affinity"