* Ignore all streaming output of invalid utf-8 string
* Update bpe_streaming.hpp
* add the phi-3 tokenizer test
* add a streaming test for phi-3 model
* fix the utf-8 validation
* fix the utf-8 validation 2
* fix the utf-8 validation 3
* fix the utf-8 validation 4
* Add support for YOLO v8 Pose post-processing.
The output has additional values in the 'mask' data for the keypoints.
- Update the post processing steps to support extracting and scaling the keypoints.
- Simplify the existing step to split out the boxes and scores by using a basic Split operator if there is no confidence score for a bounding box to apply to the class scores.
- Confidence score for a bounding box is YOLO versions prior to 8.
- Update existing tests
TODO: Add unit tests for new Steps. They have been manually validated with the real model for now.
* Changes to support pre-decoded input.
Needs cleanup.
* Support an overall max number of detections as well as per-class detections.
* Expand Identity to support multiple inputs
Fix issue with incorrect score being selected by NMS (was max and not score for selected clas)
Fix TopK usage so result ordering is consistent when it is not used
Add unit tests.
* Update docs and some cleanups
* Use Union
* initial draft
* second
* third
* polishing
* fix the M_PI name in LINUX platform
* fix bessel function issue
* add a unit test case
* fix the unit test name
* Add a nuget test app
* remove unused file
* Compatible with onnxruntime-gpu package (#410)
* be compatible without onnxruntime-gpu version
* some fixing
* turn it as a .net demo project
---------
Co-authored-by: Sayan Shaw <52221015+sayanshaw24@users.noreply.github.com>
* object detection
* Unit test
add e2e fastestdet model test
---------
Co-authored-by: Changming Sun <chasun@microsoft.com>
Co-authored-by: Scott McKay <skottmckay@gmail.com>
* evaluate the audio decoder library
* MP3 Decoder
* rename it to test_audio_codec
* add the audio decoder to whisper model
* whisper end-to-end draft
* fix the mp3 decoder
* Running with ONNX models
* Add more audio format supports
* refine the end-to-end script
* Update operators/audio/audio_decoder.hpp
Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
* Update operators/audio/audio_decoder.hpp
Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
* Update operators/audio/audio_decoder.hpp
Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
* some fixings of comments and more test cases.
* changes for review comments.
* Update audio_decoder.hpp
* Update audio_decoder.hpp
* code refinement
* Update operators/audio/audio_decoder.hpp
Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
---------
Co-authored-by: Sayan Shaw <52221015+sayanshaw24@users.noreply.github.com>
Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
* add a stft-norm custom op for log-mel spectrum.
* undo the debug change
* Support ONNX standard STFT op signature.
* Add a unit test onnx STFT compatible mode.
* add whisper pre-/post- processing example
* Update dlib.cmake
* undo test code changes
* Update setup.cfg
* update the end2end example with STFT op
* - Fix Split(18) requiring num_outputs.
- Calculate `sizes` in Resize instead of using the simpler `scales`
- ORT implementation does not round correctly when applying scales
- Update center crop to use float so we are more accurate in choosing the crop area.
- Fix minor issue with Debug step by only adding values that are altered to the renaming graph inputs.
- Update unit tests expected output due to the change in Resize using sizes instead of scales.
- Crop e2e example input so before/after image covers same area.
* Simplify.
CenteredCrop doesn't need to use float as it's dividing by 2 (so using float + floor gives the same result).
Remove Resize impl using scales - we most likely will never go back to it.
Address PR comments
Update doc
* Move the pre/post processing scripts into the python module.
Update usage/examples.
* Use better version parsing.
* Update tests, docs,
* Address PR comments.
Remove global Settings and pass onnx opset around directly where needed. Make PrePostProcessor the owner of the checker context.
* Separate ops in operators/cv2 that do and do not require codecs so they're easier to include/exclude from a build.
Remove jpeg2000 from opencv file formats. It costs 1MB and is (afaict) not a common format.
Add ability to enable/disable cv2 ops to gen_selectedops.py.
* Remove super resolution pre/post process ops that are no longer needed.
* Replace super resolution e2e tutorial
Co-authored-by: Wenbing Li <10278425+wenbingl@users.noreply.github.com>
* update the main doc and add a developer doc
* add it back
* fix some typo
* Update README.md
Co-authored-by: Nat Kershaw (MSFT) <nakersha@microsoft.com>
Co-authored-by: Nat Kershaw (MSFT) <nakersha@microsoft.com>
* an android test app for extensions AAR package
* add the pipeline
* fxing the Android CI pipeline
* fix the build issus on macOS
* more fixings
* more fixings
* switch to jdk 11
* gradlew path issue
* update the command lines
* split the test task
* better name
* more C++ code fixing and polish for release
* fixing for android build
* build flags for android release
* add missing exporting function
* imint
* first versoin
* more C++ code fixing and polish for release (#275)
* more C++ code fixing and polish for release
* fixing for android build
* build flags for android release
* add missing exporting function
* support build_id on Python package building (#281)
* support buildid in package building
* undo the change on build.sh
* build.sh issue on macos
* Add `$schema` to `cgmanifest.json` (#284)
Co-authored-by: Jamie Magee <jamie.magee@microsoft.com>
* test package with a simple java app
* demo app
* some fixing for windows platform
* refine the example app
* fix the missing symobls issue for Linux build
* fix the package package build issue
* typo
* a missing change
* fix PythonOp
* fix Android test issue
* one more Android change
* replace build flags in ci pipeline
* android AAR package build
* refine the code for android package
Co-authored-by: Jamie Magee <jamie.magee@gmail.com>
Co-authored-by: Jamie Magee <jamie.magee@microsoft.com>
* Implemented a new version of Kernel and the CustomOp to support
output that matches the HuggingFace model's input without the need
for intermediate python logic.
* Implemented a e2e tutorial for exporting and inferencing using the
HuggingFace's QuestionAnsering model.
Known Issue: Python side doesn't have an implementation of Bert Decoder
and so the augmented model is only half-complete. At the time of
inferencing the HuggingFace tokenizer is used to decode the result back
to string.
* initial checkins for onnxcompose
* update ci pipeline for the test.
* add the missing quotes
* Switch to looseVersion for torch version.
* testif
* padding_length
* skip the gpt2
* add onnxruntime 1.9 test package.
* fix a memory bug on pyop.