Koan-Sin Tan

aarch64-bare-metal-qemu. aarch64 bare metal test on qemu

classdump-dyld. a classdump-dyld fork works on macOS m1

sensors_cmdline. Read thermal/temperature sensors, voltage meters, and current meters on M1 and iPhone

iOS-device-tree-dump. Dump non-encrypted iOS device tree extracted from im4p

coreml_to_ane_hwx. a quick and dirty little program to convert Apple CoreML model to ANE hwx file

TestANE. Test Apple Neural Engine

keras_cv_stable_diffusion_to_tflite. Scripts for converting Keras CV Stable Diffusion to tflite

test-ioreport. A little program to show how to dump all the IOKit IOReport information

sensors. Read values from thermal sensors, voltage meters, and current meters on iPhone/iPad

SimpleInceptionV3-ObjC. A simple image classification test using Core ML and Inception V3 model in Objective-C

tensorflow. Computation using data flow graphs for scalable machine learning

glDelegateBench. quick and dirty inference time benchmark for TFLite gles delegate

X20-96-board. Collection of X20 96 Board Resources

glDelegateBenchmark. quick and dirty benchmark for TFLite gles delegate on iOS

some_super_resolution_tflite_models. Some super resolutions models converted to TFLite

edgetpu-native. edgetpu-native from https://coral.googlesource.com/edgetpu-native

edge_tpu_python_scripts. some scripts I used to test Google's Edge TPU

coreml_modelc_profling. per op profiling in using Core ML MLComputePlan

sysctl-swift. Use sysctl_by_name() to get some iOS device information

deeplabv3_tflite_for_nnapi_delegate. DeepLab V3 TFLite models that be fully delegated to NNAPI

m1_smc_senors. Retrieve some SMC temperature sensors names (in 4CC) and values.

ProfilingMobilenetV4. Profiling MobilenetV4 CoreML model

coremlbenchmark. Simple CoreML Benchmark

mcc. get/set information of Apple MemCacheController

jetson-nano-tf-trt. test tf-trt on Jetson Nano

coreml_models_for_mlperf. Converting models used by MLPerf Mobile working group to Core ML format

node-python-lua-on-7688.

coreml-mobilenet-models. Convert Keras MobileNet models into Core ML ones

lk-x20-96-board. Little Kernel for X20 96Board

minimal_asr_cli. a minimal CLI Objective-C example to test Apple's Speech.framework

swift-coreml-diffusers. Swift app demonstrating Core ML Stable Diffusion

linkit-7688-duo. An Introduction to LinkIt Smart 7688 Duo for Guys Familiar with System Software

libtensorflow-pharo-bindings. TensorFlow library bindings for Pharo

label_image_for_Pharo_TensorFlow_CAPI_binding. label_image for Pharo TensorFlow CAPI binding

benchmarks. Benchmark code

android-utah-teapot. Automatically exported from code.google.com/p/android-utah-teapot

tf-examples. TensorFlow examples

android-vnc-viewer. Automatically exported from code.google.com/p/android-vnc-viewer

TestSimpleCoreMLCommandLine. Run a simple Core ML classification model without using coremlc generated wrapper

CameraxTFLite. my exercise to use Android CameraX and TFLite codegen in Kotlin

linux. Linux kernel source tree

profiling_models_in_remote_aar. Profiling .mlmodelc models, compiled MLProgram, in remote AAR (Apple Archive)

arm-trusted-firmware. ARM Trusted Firmware

kernel-3.18-X20-96-board.

super-resolution. Tensorflow 2.x based implementation of EDSR, WDSR and SRGAN for single image super-resolution

sme. Assembly

SimpleInceptionV3. A simple image classification test using Core ML and Inception V3 model

MiDaS. Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, arXiv:1907.01341"