margelo / margelo/react-native-fast-tflite

iOS does not build on x86 Simulators

Open
#35 7 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
TypeScript
Stars
1.2k
Forks
92
Avg merge
13h 9m
Merged PRs (30d)
2

Description

On iOS, we currently build TensorFlowLiteC from source. This builds a fat iOS binary: https://github.com/mrousavy/react-native-fast-tflite/blob/5b8d61270e777dd5b66bbe06004e5109bac8f874/scripts/build-tensorflow-ios.sh#L16-L17

..for some reason users have reported that this does not work when running the app on an iOS Simulator on a Intel x86 Mac.

I don't have such Mac anymore, but I am not sure what's going wrong - maybe there is a way to also build for x86?

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by inspecting scripts/build-tensorflow-ios.sh, especially the fat-binary build at lines 16-17, and investigate how the iOS Simulator architectures are selected. Reproduce the reported failure on an Intel x86 Mac or equivalent environment, then verify that the resulting TensorFlowLiteC binary builds and runs on an x86 iOS Simulator.

Written by the indexing model from the issue text.

Assessment

Tech stack
ios, react-native, tensorflow
Domain
build-system, machine-learning, mobile
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
42/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.