83be3759bc
ORTModule requires two PyTorch CPP extensions that are currently JIT compiled. The runtime compilation can cause issues in some environments without all build requirements or in environments with multiple instances of ORTModule running in parallel This PR creates a custom command to compile such extensions that must be manually executed before ORTModule is executed for the first time. When users try to use ORTModule before the extensions are compiled, an error with instructions are raised PyTorch CPP Extensions for ORTModule can be compiled by running: python -m onnxruntime.training.ortmodule.torch_cpp_extensions.install Full build environment is needed for this |
||
|---|---|---|
| .. | ||
| SwiftMnist | ||
| SwiftMnist.xcodeproj | ||
| ReadMe.md | ||
MNIST Sample - Number recognition
This sample uses the MNIST model from the Model Zoo: https://github.com/onnx/models/tree/master/vision/classification/mnist
Requirements
- MacOS Catalina
- Xcode 11
- Compiled libonnxruntime.dll / lib
Build
Command line:
$ xcodebuild -project SwiftMnist.xcodeproj
From Xcode, open SwiftMnist.xcodeproj and run with Command-R.
How to use it
Just draw a number on the surface, when you lift your finger from the mouse or the trackpad, the guess will be displayed.
Note that when drawing numbers requiring multiple drawing strokes, the model will be run at the end of each stroke with probably wrong predictions (but it's amusing to see and avoids needing to press a 'run model' button).
How it works
(Add once it is added)
Preprocessing the data
MNIST's input is a {1,1,28,28} shaped float tensor, which is basically a 28x28 floating point grayscale image (0.0 = background, 1.0 = foreground).
Postprocessing the output
MNIST's output is a simple {1,10} float tensor that holds the likelihood weights per number. The number with the highest value is the model's best guess.
The MNIST structure uses std::max_element to do this and stores it in result_: