pytorch/ios/TestApp
David Reiss b7e044f0e5 Re-apply PyTorch pthreadpool changes
Summary:
This re-applies D21232894 (b9d3869df3) and D22162524, plus updates jni_deps in a few places
to avoid breaking host JNI tests.

Test Plan: `buck test @//fbandroid/mode/server //fbandroid/instrumentation_tests/com/facebook/caffe2:host-test`

Reviewed By: xcheng16

Differential Revision: D22199952

fbshipit-source-id: df13eef39c01738637ae8cf7f581d6ccc88d37d5
2020-06-23 19:26:21 -07:00
..
benchmark Re-apply PyTorch pthreadpool changes 2020-06-23 19:26:21 -07:00
custom_build Add CI scripts for Custom Build (#32316) 2020-01-16 14:46:16 -08:00
fastlane Suppress XCode build warnings (#31000) 2019-12-10 11:37:52 -08:00
TestApp [pytorch] remove boilerplate setQEngine() from PyTorch mobile predictors (#34556) 2020-03-11 00:55:14 -07:00
TestApp.xcodeproj Fix iOS CI (#30327) 2019-12-03 11:24:21 -08:00
TestAppTests [iOS] Add nonVarTypeModeGuard to fix the unit test (#39743) 2020-06-09 20:05:32 -07:00
.clang-format add benchmark code to iOS TestApp (#28405) 2019-10-22 12:52:30 -07:00
.gitignore Suppress XCode build warnings (#31000) 2019-12-10 11:37:52 -08:00
bootstrap.sh Check device connection before running xcodebuild (#28996) 2019-11-02 14:38:08 -07:00
Gemfile
Gemfile.lock Update Gemfile (#32147) 2020-01-14 14:52:50 -08:00
Podfile
README.md [pytorch][mobile] change mobile build scripts to build PyTorch by default (#34203) 2020-03-05 23:40:47 -08:00

TestApp

The TestApp is being used for different purposes as described below

Cocoapods

To quickly test our framework in Cocoapods, simply run

pod install

This will pull the latest version of LibTorch from Cocoapods. To run the app, you need to have your model copied to the project as well as a config.json file, which can be found in the benchmark folder.

Circle CI and Fastlane

The TestApp is currently being used as a dummy app by Circle CI for nightly jobs. The challenge comes when testing the arm64 build as we don't have a way to code-sign our TestApp. This is where Fastlane came to rescue. Fastlane is a trendy automation tool for building and managing iOS applications. It also works seamlessly with Circle CI. We are going to leverage the import_certificate action, which can install developer certificates on CI machines. See Fastfile for more details.

For simulator build, we run unit tests as the last step of our CI workflow. Those unit tests can also be run manually via the fastlane scan command.

Benchmark

The benchmark folder contains two scripts that help you setup the benchmark project. The setup.rb does the heavy-lifting jobs of setting up the XCode project, whereas the trace_model.py is a Python script that you can tweak to generate your model for benchmarking. Simply follow the steps below to setup the project

  1. In the PyTorch root directory, run IOS_ARCH=arm64 ./scripts/build_ios.sh to generate the custom build from Master branch
  2. Navigate to the benchmark folder, run python trace_model.py to generate your model.
  3. In the same directory, open config.json. Those are the input parameters you can tweak.
  4. Again, in the same directory, run ruby setup.rb to setup the XCode project.
  5. Open the TestApp.xcodeproj, you're ready to go.

The benchmark code is written in C++, you can use UI_LOG to visualize the log. See benchmark.mm for more details.

bootstrap.sh

For those who want to do perf testing but don't want to touch XCode, bootstrap.sh is the right tool for you. It'll automatically build and install the app on your device. That being said, it does require you to have

  1. A valid iOS dev certificate installed on your local machine.
  2. A valid provisioning profile for code signing
  3. A valid team identifier

To run the script, simply type the command below and make sure your phone is connected via USB.

./bootstrap

Open the app on your device, the benchmark result will be displayed on the screen.

Note This requires ios-deploy to be installed. Please have a look at ios-deploy. To quickly install it, use npm -g i ios-deploy