Commit graph

27 commits

Author SHA1 Message Date
Ashwini Khade
8fa65aba0e
enable training tests for csharp bindings (#15513)
### Description
Simple fix to enable training tests in csharp through build.py script.
2023-04-17 09:57:23 -07:00
Dmitri Smirnov
ce3b4eabd3
Implement Optional Metadata support and C# test support (#15314)
### Description
Implement Optional Type metadata support in the library.
Implement optional support in C# API along with metadata.
Implement Sequence, Map, Optional test data support
and test execution.

Prune tests and provide more details for failing tests in C# code.

Note, this PR does not enable running onnx test models in C++.

### Motivation and Context
Opset18 optional type support.
2023-04-11 09:41:59 -07:00
Dmitri Smirnov
d034b432ec
Add support for handling sbyte (Int8) data in C# inference tests (#14807)
### Description
Add sbyte specific test case support.

### Motivation and Context
C# Test Data loading code and comparators are missing sbyte (Int8)
specializations.
This fails a test
2023-02-23 17:05:28 -08:00
Yi Zhang
1ea360148f
restore opset18 test (#14677)
### Description
Reenable disabled opset18 tests


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2023-02-20 18:19:10 +08:00
Scott McKay
c252a7f992
Remove exclusions for ONNX model tests that now pass. (#14337)
### Description
<!-- Describe your changes. -->
Remove exclusions for ONNX model tests that now pass due to kernels
being implemented.
Update ONNX update doc to point to correct location for tests.

### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
Run as many tests as possible.

Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
2023-01-24 08:04:27 +10:00
liqun Fu
05915d8393
support Pad(18) (#14219) 2023-01-23 12:14:35 -08:00
JiCheng
4f309f05ca
[CPU] Resize of Opset 18 (#13890)
### Description

To Implement Resize 18.
This PR depends on https://github.com/microsoft/onnxruntime/pull/13765.

### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2023-01-14 08:57:23 +10:00
Scott McKay
ea12b674c0
Disable the failing opset 18 model tests that are breaking the packaging pipeline (#14259)
### Description
<!-- Describe your changes. -->
Skip tests for opset18 models that we haven't implemented kernels for
yet.

Slice was checked in today so those failures should go away.

Resize: #13890 (all resize failures are fixed by this PR as confirmed in
output
[here](https://dev.azure.com/aiinfra/530acbc4-21bc-487d-8cd8-348ff451d2ff/_apis/build/builds/264725/logs/729))
Col2Im: #12311
ScatterND and ScatterElement: #14224
Pad (should also fix CenterCropPad failures): #14219 Bitwise ops: #14197
Optional: Unknown if we're intending to support this in 1.14

Not sure about SoftPlus as that is failing due to `Could not find an
implementation for Exp(1)`. ORT supports Exp from opset 6 and on, and it
seems incorrect for the test model created for opset 18 to be using a
version of Exp that is so old. Would have expected it to use the latest
- Exp(13). @liqunfu is this something that requires a fix to the ONNX
model?


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
Fix pipeline
2023-01-13 09:55:52 +10:00
Ashwini Khade
65201e47bf
Enable nuget packages for on device training (#13637)
### Description
This PR enables building nuget packages locally for on device training
using --build_nuget arg.
This PR also enables the C# bindings by default in the managed package.
If a user triggers any training apis when the native binary is not built
for training, an exception with message "Training is disabled in the
current build. Please build ONNXRuntime from source with the build flags
enable_training and enable_training_on_device. " is thrown.

Build command for creating nuget packes for on device training:
build.bat --enable_training --enable_training_on_device --build_nuget 

2 Nuget packages are built
1. Microsoft.ML.OnnxRuntime.Managed
2. Microsoft.ML.OnnxRuntime.Training OR
Microsoft.ML.OnnxRuntime.Training.Gpu



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
2022-12-05 14:54:09 -08:00
Yi Zhang
777c474f61
skip quantized model C# tests on GPU (#13782)
### Description
Skip quantized model C# tests on GPU too.

### Motivation and Context
It looks the current test result isn't reasonable.
https://github.com/onnx/models/issues/581

Once we update the image, the quantized model [test data will be
generated with
VNNI](ba629906dd),
the CI would be broken.
2022-12-01 12:33:20 +08:00
Changming Sun
3e9e5e9d6d
Patch Protobuf and ONNX's cmake files and enforce BinSkim check (#13694)
Patch Protobuf and ONNX's cmake files and enforce BinSkim check.

This PR has overlap with #13523 . I would prefer to get this one merged
first so that we can finished the BinSkim work, and I try to make this
PR as small as possible.
2022-11-18 10:09:47 -08:00
Dmitri Smirnov
0e2087acff
Add extension method to compensate for Contains() absence (#13466)
### Description
The targeted framework does not contain `Contains(string, orginal)`. 
Add extension method to compensate in following the suggestion
[here](https://learn.microsoft.com/en-us/dotnet/api/system.string.contains?view=net-7.0).


### Motivation and Context
Packaging pipeline fails.
2022-10-27 10:00:47 -07:00
Yi Zhang
143725604e
Skip some models failed in Windows CPU C# tests (#13395)
### Description
For models from model zoo, in C# tests of Windows CPU CI
skip models whose name contains int8 or qdq.
skip some models (VGG16, VGG19) in x86 workflow

### Motivation and Context
These models always failed in Windows CPU C# tests 

(https://dev.azure.com/onnxruntime/onnxruntime/_build/results?buildId=789442&view=results)


### verified

https://dev.azure.com/onnxruntime/onnxruntime/_build/results?buildId=789861&view=results
C# tests passed
2022-10-22 13:54:24 +08:00
Yi Zhang
bb16ee712e
skip 2 models in C# test (#13384)
### Description
<!-- Describe your changes. -->



### Motivation and Context

these 2 models are also skipped in gtest

fc12abf6b1/onnxruntime/test/providers/cpu/model_tests.cc (L119-L122)
2022-10-21 09:01:34 +08:00
Yi Zhang
3c08f24efc
uset SearchOption for dotframework (#13321)
### Description
As Title


### Motivation and Context
dotcore has EnumerationOptions but dotnetframewok hasn't

**netframework-4.6.1**

https://learn.microsoft.com/en-us/dotnet/api/system.io.directory.enumeratedirectories?view=netframework-4.6.1#system-io-directory-enumeratedirectories(system-string-system-string-system-io-searchoption)

**net-5.0**

https://learn.microsoft.com/en-us/dotnet/api/system.io.directory.enumeratedirectories?view=net-5.0

It breaks C#.net framework step in Packaging Pipeline

Testing workflow

https://dev.azure.com/aiinfra/Lotus/_build/results?buildId=238516&view=results
2022-10-14 10:22:05 -07:00
Yi Zhang
0d672e9112
Enable C# test load models with more complex directories. (#13251)
### Description
Currently, C# test only load models with the directory structure as
`{modelroot}->{opsetXX}->{modelname}->{.onnx}`
In this PR, C# test can load models from
`{modelroot}->{model-source}->{opsetXX}->{modelname}->{.onnx}`

### Motivation and Context
There're multiple sources of testing models.
1. model zoo (Not in official image)
2. 1st party models
3.  models with contrib-ops
4.  others.

It'd better to insert a mid-directory for new sources.

**This PR is compatible with current models.**
From
https://dev.azure.com/onnxruntime/onnxruntime/_build/results?buildId=776643&view=logs&j=6df8fe70-7b8f-505a-8ef0-8bf93da2bac7&t=e7d9f128-b630-5ee6-a99e-2fca70d04619&l=79
the test result is same as master build `Passed: 583, Skipped: 14,
Total: 597`

**model zoo models (mounted in ..\models\zoo) could be loaded**
And from this test workflow, it can load both existing models and models
from model zoo.

https://dev.azure.com/onnxruntime/onnxruntime/_build/results?buildId=777018&view=logs&j=6df8fe70-7b8f-505a-8ef0-8bf93da2bac7&t=e7d9f128-b630-5ee6-a99e-2fca70d04619
Skipping failed models will be in other PRs
2022-10-12 13:53:58 +08:00
ashbhandare
27dde0b51f
Csharp bindings for on-device training APIs (#12404) 2022-09-02 13:13:48 -07:00
Chun-Wei Chen
6246662b1d
[Dup] Fix SAME_UPPER/SAME_LOWER (auto_pad attribute) in ConvTranspose (#12537)
* Fix SAME_UPPER/SAME_LOWER (auto_pad attribute) in ConvTranspose

* Bump ONNX 1.10.2 globally

* load ONNX_VERSION from VERSION_NUMBER

* /

* revert deprecate warning in ORT 1.12

* add a comment about why removing cntk_simple_seg

* correct the implem in DML as well
2022-08-22 15:35:34 -07:00
Wei-Sheng Chin
0ee0b8cf18
Disable sequence-type tests since C# infra doesn't support well (#12037) 2022-06-30 09:49:03 -07:00
Edward Chen
466b2d9f3d
[C# Tests] Add support for double tensor output in TestPreTrainedModels. (#12008)
Add support for double tensor output in TestPreTrainedModels.
2022-06-27 18:49:19 -07:00
Vincent Wang
3b6cee8059
[CUDA] Optimize Conv and ConvGrad for Training (#10999)
* Optimize Conv and ConvGrad for Training

* add provider option to control

* fix typo
2022-03-29 07:31:36 +08:00
Chun-Wei Chen
bac9c0eb50
skip optional related models from opset16 (#10840) (#10878) 2022-03-16 08:49:42 -07:00
Scott McKay
c1c9fa18bf
C#: Avoid inefficient DenseTensor ctor in ToTensor extensions (#10240)
* Update extension helpers to avoid inefficient construction of DenseTensor.
Add tests for extension helpers.
2022-01-19 07:43:44 +10:00
Hariharan Seshadri
0552a47ec2
Enable CUDA provider option configuration for C# (#10188) 2022-01-06 11:03:14 -08:00
Ye Wang
2803a9465d
Add example of registering custom cuda op as shared lib (#10025) 2022-01-05 09:22:15 -08:00
Scott McKay
eb2612b588
Remove netcoreapp2.1 target as it is EOL and out of support. Attempting to use it with VS now causes unit test run failures. (#9603) 2021-10-29 11:11:22 +10:00
Scott McKay
b5a652c578
Add Xamarin support (#9436)
Add Xamarin support to the ORT nuget packages.
  - Update C# code to support Xamarin builds for iOS and Android
  - refactor some things to split out common code
  - include iOS and Android ORT native shared library in native nuget package
2021-10-27 20:07:07 +10:00