Comments (4)
This is coming indirectly from the protobuf library that CoreML uses to define the model format.
Have added changes to patch the protobuf headers in the version of protobuf we're using to avoid the issue. More details in the PR.
Will be in the next release in a few weeks. Unfortunately that's the soonest we can fix it.
Short-term alternative would be to build the onnxruntime-c pod locally with those changes. On a mac, if you checkout the onnxruntime repo you can run this script to do that
python3 tools/ci_build/github/apple/build_apple_framework.py --build_dir build/iOS_framework_full tools/ci_build/github/apple/default_full_ios_framework_build_settings.json
from onnxruntime.
Sorry - one correction. That script will build an xcframework. To build the cocoapods locally you'd need to run
python3 tools/ci_build/github/apple/build_and_assemble_apple_pods.py --variant Full --build-settings-file tools/ci_build/github/apple/default_full_apple_framework_build_settings.json
usage: build_and_assemble_apple_pods.py [-h] [--build-dir BUILD_DIR] [--staging-dir STAGING_DIR] [--pod-version POD_VERSION] [--variant {Full,Mobile,Training}] [--test]
[--include-ops-by-config INCLUDE_OPS_BY_CONFIG] --build-settings-file BUILD_SETTINGS_FILE [-b BUILD_APPLE_FRAMEWORK_EXTRA_ARGS]
Builds an iOS framework and uses it to assemble iOS pod package files.
optional arguments:
-h, --help show this help message and exit
--build-dir BUILD_DIR
The build directory. This will contain the iOS framework build output. (default: /Users/me/src/github/ort/build/apple_framework)
--staging-dir STAGING_DIR
The staging directory. This will contain the iOS pod package files. The pod package files do not have dependencies on files in the build directory. (default:
/Users/me/src/github/ort/build/apple_pod_staging)
--pod-version POD_VERSION
The version string of the pod. The same version is used for all pods. (default: 1.19.0-local)
--variant {Full,Mobile,Training}
Pod package variant. (default: Mobile)
--test Run tests on the framework and pod package files. (default: False)
iOS framework build arguments:
See the corresponding arguments in build_apple_framework.py for details.
--include-ops-by-config INCLUDE_OPS_BY_CONFIG
--build-settings-file BUILD_SETTINGS_FILE
The positional argument of build_apple_framework.py. (default: None)
-b BUILD_APPLE_FRAMEWORK_EXTRA_ARGS, --build-apple-framework-arg BUILD_APPLE_FRAMEWORK_EXTRA_ARGS
Pass an argument through to build_apple_framework.py. This may be specified multiple times. (default: [])
from onnxruntime.
thanks @skottmckay for a quick response
from onnxruntime.
This issue has been automatically marked as stale due to inactivity and will be closed in 30 days if no further activity occurs. If further support is needed, please provide an update and/or more details.
from onnxruntime.
Related Issues (20)
- [Training] Support for RKNPU Execution Provider on RK3562 Platform and On-Device Training Capabilities HOT 1
- Support Numpy v2.0 HOT 9
- Segmentation fault during inference HOT 2
- Can't find definition of OrtTensorRTProviderOptionsV2 in latest release
- [Mobile] Segmentation fault after repeated inference HOT 5
- [Bug] W16A16 quantization, qdq_error is empty, but W8A8 is normal HOT 1
- [Feature Request] support FP8 calibraion method and quantization HOT 2
- DML cannot use device_id = 1 , run_with_iobinding failed. HOT 1
- [Mobile] CreatMemoryInfo Failure in Android when try to create Ort::Value HOT 6
- [Build] ERROR: *.whl is not a valid wheel filename & ImportError: DLL load failed while importing onnxruntime_pybind11_state HOT 6
- [Performance] Running YOLOv8-seg.onnx with Dynamic Batch Size on GPU HOT 1
- [Web] `Error: [WebGPU] Kernel "[Conv] /text_encoder/encoder/layers.0/feed_forward/conv_2/Conv" failed. Error: FILTER_IN_CHANNEL should be equal to DATA_CHANNEL` HOT 1
- [Bug] fp8 quantization, weight_error is empty, but qdq_err is normal
- cannot resolve operator 'Cast' with opsets: ai.onnx v17 [Web]
- [Performance] Call a error when running on windows 7.detail:System.TypeInitializationException at Microsoft.ML.OnnxRuntime.SessionOptions..ctor() HOT 3
- [Feature Request] Support for Florence-2 model family HOT 1
- [Web] [Webnn] Can't seem to use the WebNN. Getting "WEBNN execution provider is not supported in this build." HOT 2
- Symbolic Shape infer fails on onnx file without much logs
- How to convert quantized ONNX model from Tensor-Oriented format to Operator-Oriented format?
- Quantized ONNX Model Still Has Float32 Input/Output Tensors HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from onnxruntime.