Finally I have Onnxruntime recipe
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 30/100
- Issue type
- Feature
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- android, cmake, numpy, opencv, python
- Domain
- build-system, machine-learning, mobile-dev
Research direction
Start by reviewing the custom recipe in daslearning-org/vision-ai at onnx/p4a_local_recipes/onnxruntime, including its CMake and wheel build steps, then read the constraints documented in issue #3203. Done means the Android recipe is reviewed for python-for-android and its build requirements and limitations are clearly addressed.
Written by the indexing model from the issue text.
Description
Background
- Onnxruntime is an an open-source, high-performance inference engine that accelerates machine learning models in the Open Neural Network Exchange (ONNX) format.
- Building it for
androidwas a huge challenge. I have followed some patterns fromtermux-packages& after many days of hit-n-try, I was able to build it.
Custom recipe link
- Here is my open-source project on
onnxruntime& here is the recipe link which builds thecmakepart first & then it build the wheel. - You can try my app from releases.
Constraints
- I am currently building on
numpy 1.26.5due to #3203 issue as I also needopencvin my project. - Another one is, currently it is built using
ndk 25band that problem is also written in the above mentioned issue.
My thoughts
I'm not a build expert on cmake, wheel etc. I tried my best to make it work and I am sure that the developers can make it more robust.
Please feel free to let me know your thoughts. Thank you
- Dominant language
- Python
- Stars
- 8.9k
- Forks
- 2k
- Avg merge
- 12h 20m
- Merged PRs (30d)
- 9
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from kivy/python-for-android
-
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
kivy/python-for-android#3335 · 1 comment · 3 reactions ·
-
Documentation easy
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
kivy/python-for-android#3326 · 1 comment ·
-
Documentation easy Priority: Low
Difficulty 1/5 Under an hour Newbie friendliness 88/100
kivy/python-for-android#3299 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 48/100
kivy/python-for-android#3382 ·
-
Difficulty 3/5 1-2 days Newbie friendliness 45/100
kivy/python-for-android#3381 ·
All issues in kivy/python-for-android
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
anthropics/skills#1811 · 1 comment ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
speaches-ai/speaches#678 ·
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
datalayer/mcp-compose#42 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
conda-forge/spacy-feedstock#177 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
UKGovernmentBEIS/inspect_evals#2523 ·