saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-28 20:11:22 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add the custom op project information (#6334)

Browse source
This commit is contained in:
Wenbing Li 2021-01-20 15:23:24 -08:00 committed by GitHub
parent 453431f7bb
commit 69af0440b1
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 3 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/AddingCustomOp.md
View file

@ -15,6 +15,8 @@ Currently, the only supported Execution Providers (EPs) for custom ops registere
Note that when a model being inferred on gpu, onnxruntime will insert MemcpyToHost op before a cpu custom op and append MemcpyFromHost after to make sure tensor(s) are accessible throughout calling, meaning there are no extra efforts required from custom op developer for the case.
To facilitate the custom operator development, sharing and release, please check the [onnxruntime custom operator library](https://github.com/microsoft/ort-customops) project for the more information.
### 2. Using RegisterCustomRegistry API
* Implement your kernel and schema (if required) using the OpKernel and OpSchema APIs (headers are in the include folder).
* Create a CustomRegistry object and register your kernel and schema with this registry.

2
docs/PyOp.md
View file

@ -1,6 +1,6 @@
# Python Operator
**Deprecation Note: This feature is deprecated and no longer supported.**
**Deprecation Note: This feature is deprecated and no longer supported, please refer to [onnxruntime_customops](https://github.com/microsoft/ort-customops) project for this function.**
The Python Operator provides the capability to easily invoke any custom Python code within a single node of an ONNX graph using ONNX Runtime. This can be useful for quicker experimentation when a model requires operators that are not officially supported in ONNX and ONNX Runtime, particularly if there is already a Python implementation for the required functionality. This should be used with discretion in production scenarios, and all security or other risks should be considered beforehand.