UDO Tutorial

Overview

This tutorial describes the steps needed to create a UDO package and execute the Inception V3 model using the package. The Softmax operation has been chosen in this tutorial to demonstrate the implementation of a UDO with Qualcomm® Neural Processing SDK.

The Qualcomm® Neural Processing SDK provides the resources for this example under

  • $SNPE_ROOT/examples/SNPE/NativeCpp/UdoExample/Softmax

Information on UDO in general is available at UDO Overview.

Information on running the Inception V3 network without UDO is available at Inception V3 Tutorial.

Prerequisites

The following tutorial assumes that general Qualcomm (R) Neural Processing SDK setup has been followed to support SDK environment, TensorFlow environment, and desired platform dependencies. Please ensure that your hexagon sdk is named in the format “hexagon-sdk-<version name>” and ensure that the hexagon sdk has the path for the tools directory in format of “hexagon-sdk-<version name>/tools/HEXAGON_Tools/<tools name>/”

Additionally, we need an extracted Qualcomm® AI Direct SDK (no need of Qualcomm® AI Direct SDK setup) for generating the skeleton code and building the libraries. For Qualcomm® AI Direct SDK details, refer to the Qualcomm® AI Direct SDK documentation at $QNN_SDK_ROOT/docs/QNN/index.html page, where QNN_SDK_ROOT is the location of the Qualcomm® AI Direct SDK installation. Set the $QNN_SDK_ROOT to the unzipped Qualcomm® AI Direct SDK location. This has to be performed after running the envsetup.sh script mentioned in SNPE Setup. The steps listed in this tutorial use the Tensorflow model in the form of inception_v3_2016_08_28_frozen.pb. For details on acquiring the Inception V3 model visit Tutorials Setup.

Introduction

Here are the steps to develop and run a UDO

  1. Package Generation

  2. Framework Model Conversion to a DLC

  3. Package Implementation

  4. Package Compilation

  5. Model Execution

Steps 1-4 are run offline on the x86 host and are necessary for execution in step 5. Step 5 provides information on execution using the Qualcomm® Neural Processing SDK command-line executable snpe-net-run. Optionally, the user can perform steps 1-4 automatically using the provided setup script.

Make sure to run following commands for setting up the tensorflow paths and hexagon path

export TENSORFLOW_HOME=<path to tensorflow framework version 2.3.0>
export TENSORFLOW_ROOT=$TENSORFLOW_HOME/focal/py3
export PYTHONPATH=$TENSORFLOW_ROOT/distribute:$TENSORFLOW_ROOT/dependencies/python:$PYTHONPATH

# hexagon sdk and tools version depend on dsp aarch, below version is for v68 aarch
export HEXAGON_SDK_ROOT=<path to Hexagon SDK 4.2.0>
export HEXAGON_TOOLS_ROOT=$HEXAGON_SDK_ROOT/tools/HEXAGON_Tools/8.4.09

Step 1: Package Generation

Generating the SoftmaxUdoPackage requires the snpe-udo-package-generator tool and the provided UDO plugin: Softmax_Htp.json. The plugin is located under $SNPE_ROOT/examples/SNPE/NativeCpp/UdoExample/Softmax/config. More information about creating a UDO plugin can be found here.

Generate the SoftmaxUdoPackage using the following:

export SNPE_UDO_ROOT=$SNPE_ROOT/share/SNPE/SnpeUdo
export QNN_SDK_ROOT=<path to Qualcomm® AI Direct SDK>
snpe-udo-package-generator -p $SNPE_ROOT/examples/SNPE/NativeCpp/UdoExample/Softmax/config/Softmax_Htp.json -o $SNPE_ROOT/examples/Models/InceptionV3/

This command creates the Softmax based package at $SNPE_ROOT/examples/Models/InceptionV3/SoftmaxUdoPackage. For more information on the snpe-udo-package-generator tool visit here.

Step 2: Framework model Conversion to a DLC

Converting the Tensorflow Inception V3 model to DLC requires the snpe-tensorflow-to-dlc tool. The snpe-tensorflow-to-dlc tool consumes the same Softmax_Htp.json used in package generation via the –udo command line option. In this step, <INCEPTION_V3_PATH> refers to the path to the inception_v3 pb file. For example, after running the setup_inceptionv3_snpe.py script <INCEPTION_V3_PATH> is $SNPE_ROOT/examples/Models/InceptionV3/tensorflow.

Convert Inception V3 with the following:

snpe-tensorflow-to-dlc --input_network <INCEPTION_V3_PATH>/inception_v3_2016_08_28_frozen.pb --input_dim 'input' 1,299,299,3 --out_node InceptionV3/Predictions/Reshape_1 --output_path $SNPE_ROOT/examples/Models/InceptionV3/dlc/inception_v3_udo.dlc --udo $SNPE_ROOT/examples/SNPE/NativeCpp/UdoExample/Softmax/config/Softmax_Htp.json

This will generate a DLC named inception_v3_udo.dlc containing the Softmax as UDO at $SNPE_ROOT/examples/Models/InceptionV3/dlc.

Step 3: Package Implementations

The generated package creates the skeleton of the operation implementation, which must be filled by the user to create a functional UDO. The rest of the code scaffolding for compatibility with Qualcomm® Neural Processing SDK is provided by the snpe-udo-package-generator. The UDO implementations for this tutorial are provided under $SNPE_ROOT/examples/SNPE/NativeCpp/UdoExample/Softmax/src.

CPU Implementations (Android and x86)

The file in the package that needs to be implemented for CPU is

  • SoftmaxUdoPackage/jni/src/CPU/src/ops/Softmax.cpp

The provided example implementation is present at the location

  • $SNPE_ROOT/examples/SNPE/NativeCpp/UdoExample/Softmax/src/CPU/Softmax.cpp

Copy the provided implementation to the package:

cp -f $SNPE_ROOT/examples/SNPE/NativeCpp/UdoExample/Softmax/src/CPU/Softmax.cpp $SNPE_ROOT/examples/Models/InceptionV3/SoftmaxUdoPackage/jni/src/CPU/src/ops/

Optionally, the user can provide their own implementations in the package.

GPU Implementations (Android)

The file in the package that needs to be implemented for GPU is

  • SoftmaxUdoPackage/jni/src/GPU/src/ops/Softmax.cpp

The provided example implementation is present at the location

  • $SNPE_ROOT/examples/SNPE/NativeCpp/UdoExample/Softmax/src/GPU/Softmax.cpp

Copy the provided implementation to the package:

cp -f $SNPE_ROOT/examples/SNPE/NativeCpp/UdoExample/Softmax/src/GPU/Softmax.cpp $SNPE_ROOT/examples/Models/InceptionV3/SoftmaxUdoPackage/jni/src/GPU/src/ops/

Optionally, the user can provide their own implementations in the package.

DSP Implementations for V65 and V66

Similar to all other Qualcomm® Neural Processing SDK runtimes, a registration library and an implementation library are required to run inference of a network with UDO layers on Qualcomm® Neural Processing SDK DSP. The registration library will run on CPU, and specifies the DSP implementation library of the UDO. Refer Implementing a UDO for DSP V65 and V66 for more information on implementing UDO for DSP V65 and V66 runtimes.

The file in the package that need to be implemented for DSP V65 and V66 are

  • SoftmaxUdoPackage/jni/src/DSP/Softmax.cpp

The provided example implementation is present at the location

  • $SNPE_ROOT/examples/SNPE/NativeCpp/UdoExample/Softmax/src/DSP/Softmax.cpp

Copy the provided implementations to the package:

cp -f $SNPE_ROOT/examples/SNPE/NativeCpp/UdoExample/Softmax/src/DSP/Softmax.cpp $SNPE_ROOT/examples/Models/InceptionV3/SoftmaxUdoPackage/jni/src/DSP/src/ops

Optionally, the user can provide their own implementations in the package.

DSP Implementations for V68 and later

Refer Implementing a UDO for DSP V68 or later for more information on implementing UDO for DSP V68 or later runtimes. The directory paths and locations in this example are specific to DSP V68. For later runtimes, please replace DSP_V68 with the corresponding DSP architecture (for example, DSP_V69) in the paths.

The file in the package that needs to be implemented for DSP V68 and later is

  • SoftmaxUdoPackage/jni/src/DSP_V68/src/ops/Softmax.cpp

The provided example implementation is present at the location

  • $SNPE_ROOT/examples/SNPE/NativeCpp/UdoExample/Softmax/src/HTP/Softmax.cpp

Copy the provided implementations to the package:

cp -f $SNPE_ROOT/examples/SNPE/NativeCpp/UdoExample/Softmax/src/HTP/Softmax.cpp $SNPE_ROOT/examples/Models/InceptionV3/SoftmaxUdoPackage/jni/src/DSP_V68/src/ops

Optionally, the user can provide their own implementations in the package.

Step 4: Package Compilation

x86 Host Compilation

Compiling on x86 host uses the make build system. Compile the CPU implementations with the following:

cd $SNPE_ROOT/examples/Models/InceptionV3/SoftmaxUdoPackage
make cpu_x86

The expected artifacts after compiling for CPU on x86 host are

  • SoftmaxUdoPackage/libs/x86-64_linux_clang/libUdoSoftmaxUdoPackageImplCpu.so

  • SoftmaxUdoPackage/libs/x86-64_linux_clang/libUdoSoftmaxUdoPackageReg.so

Android CPU Runtime Compilation

Compilation for the CPU runtime on Android uses Android NDK. The ANDROID_NDK_ROOT environment variable must be set to the directory containing ndk-build in order to compile the package.

export ANDROID_NDK_ROOT=<path_to_android_ndk>

It is suggested to add ANDROID_NDK_ROOT to the PATH environment variable to access ndk-build.

export PATH=$ANDROID_NDK_ROOT:$PATH

Once the ANDROID_NDK_ROOT is part of PATH, compile the package for Android CPU target:

cd $SNPE_ROOT/examples/Models/InceptionV3/SoftmaxUdoPackage
make cpu_android

The expected artifacts after compiling for Android CPU are

  • SoftmaxUdoPackage/libs/arm64-v8a/libUdoSoftmaxUdoPackageImplCpu.so

  • SoftmaxUdoPackage/libs/arm64-v8a/libUdoSoftmaxUdoPackageReg.so

  • SoftmaxUdoPackage/libs/arm64-v8a/libc++_shared.so

Hexagon DSP Runtime Compilation

Compilation for the DSP runtime makes use of the make system. In order to build the implementation libraries for DSP V65 and V66 runtimes, Hexagon-SDK needs to be installed and set up. For details, follow the setup instructions on $HEXAGON_SDK_ROOT/docs/readme.html page, where HEXAGON_SDK_ROOT is the location of your Hexagon-SDK installation. Information for compiling a UDO for DSP is available at Compiling UDO for DSP.

Setup Script

The Qualcomm® Neural Processing SDK provides an option to automatically perform steps of DLC conversion, package generation, package implementation, and package compilation for UDO as outlined in steps 1-4 above. The option is an extension of the Inception V3 setup script. To enable Inception V3 setup for UDO, run the script with the –udo or -u option.

usage: $SNPE_ROOT/models/examples/Models/InceptionV3/scripts/setup_inceptionv3_snpe.py [-h] -a ASSETS_DIR [-d] [-r RUNTIME] [-u] [-l [HTP_SOC]]

Prepares the InceptionV3 assets for tutorial examples.

required arguments:
  -a ASSETS_DIR, --assets_dir ASSETS_DIR
                        directory containing the InceptionV3 assets

optional arguments:
  -d, --download        Download InceptionV3 assets to InceptionV3 example
                        directory
  -r RUNTIME, --runtime RUNTIME
                        Choose a runtime to set up tutorial for. Choices: cpu,
                        gpu, dsp, aip, all. 'all' option is only supported
                        with --udo flag
  -u, --udo             Generate and compile a user-defined operation package
                        to be used with InceptionV3. Softmax is simulated as
                        a UDO for this script.
  -l [HTP_SOC], --htp_soc [HTP_SOC]
                        Specify SOC target for generating HTP Offline Cache.
                        For example: "--htp_soc sm8450" for Snapdragon 8 Gen 1,
                        default value is sm8750.

The –udo extension is compatible with options normally used by the setup_inceptionv3_snpe.py script. When the –udo option is enabled, the -r or –runtime option controls the runtime for the package implementation and compilation. Additionally, the –udo option supports use of an ‘all’ runtime option to create and compile the SoftmaxUdoPackage for the CPU, GPU, and DSP/AIP runtimes. Selecting the ‘aip’ or ‘dsp’ runtime options additionally compiles x86 libraries in order to quantize the model. Selecting the ‘cpu’ runtime option compiles for both x86 and Android targets. Compilation for Android target will be skipped if ANDROID_NDK_ROOT is not set. If no runtime option is provided, the package is compiled for the CPU runtime.

The command to use the setup script for UDO is:

python3 $SNPE_ROOT/examples/Models/InceptionV3/scripts/setup_inceptionv3_snpe.py -a ~/tmpdir -d -u -r <runtime_of_choice>

For instance, to create and compile a package containing the libraries for all runtimes run:

python3 $SNPE_ROOT/examples/Models/InceptionV3/scripts/setup_inceptionv3_snpe.py -a ~/tmpdir -d -u -r all

For DSP_V68 or later, use the -l optional argument of the setup script to specify the htp soc. Or follow the steps here.

This will populate the artifacts in Step 4.

Model Execution

Execution using snpe-net-run

Executing Inception V3 with UDO is largely the same as use of snpe-net-run without UDO.

The Qualcomm® Neural Processing SDK provides Linux and Android binaries of snpe-net-run under

  • $SNPE_ROOT/bin/x86_64-linux-clang

  • $SNPE_ROOT/bin/aarch64-android

  • $SNPE_ROOT/bin/aarch64-oe-linux-gcc8.2

  • $SNPE_ROOT/bin/aarch64-oe-linux-gcc9.3

  • $SNPE_ROOT/bin/aarch64-ubuntu-gcc9.4

  • $SNPE_ROOT/bin/aarch64-oe-linux-gcc11.2

For UDO, snpe-net-run consumes the registration library through the –udo_package_path option. LD_LIBRARY_PATH must also be updated to include the runtime-specific artifacts generated from package compilation.

x86 Host Execution

To execute the network on x86 host, run:

cd $SNPE_ROOT/examples/Models/InceptionV3
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$SNPE_ROOT/examples/Models/InceptionV3/SoftmaxUdoPackage/libs/x86-64_linux_clang/
snpe-net-run --container dlc/inception_v3_udo.dlc --input_list data/cropped/raw_list.txt --udo_package_path SoftmaxUdoPackage/libs/x86-64_linux_clang/libUdoSoftmaxUdoPackageReg.so

Android Target Execution

The tutorial for execution on Android targets will use the arm64-v8a architecture. This portion of the tutorial is generic to all runtimes (CPU, GPU, DSP). Set SNPE_TARGET_DSPARCH to the DSP architecture of the target Android device.

# architecture: arm64-v8a - compiler: clang - STL: libc++
export SNPE_TARGET_ARCH=aarch64-android
export SNPE_TARGET_DSPARCH=hexagon-v68

Then, push Qualcomm® Neural Processing SDK binaries and libraries to the target device:

adb shell "mkdir -p /data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/bin"
adb shell "mkdir -p /data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/lib"

adb push $SNPE_ROOT/lib/$SNPE_TARGET_ARCH/*.so \
      /data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/lib
adb push $SNPE_ROOT/bin/$SNPE_TARGET_ARCH/snpe-net-run \
      /data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/bin

Next, update environment variables on the target device to include the Qualcomm® Neural Processing SDK libraries and binaries:

adb shell
export SNPE_TARGET_ARCH=aarch64-android
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/lib
export PATH=$PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/bin

Lastly, push the Inception V3 UDO model and input data to the device:

cd $SNPE_ROOT/examples/Models/InceptionV3
mkdir data/rawfiles && cp data/cropped/*.raw data/rawfiles/
adb shell "mkdir -p /data/local/tmp/inception_v3_udo"
adb push data/rawfiles /data/local/tmp/inception_v3_udo/cropped
adb push data/target_raw_list.txt /data/local/tmp/inception_v3_udo
adb push dlc/inception_v3_udo.dlc /data/local/tmp/inception_v3_udo
rm -rf data/rawfiles

Android CPU Execution

Once the model and data have been placed on the device, place the UDO libraries on the device:

cd $SNPE_ROOT/examples/Models/InceptionV3
adb shell "mkdir -p /data/local/tmp/inception_v3_udo/cpu"
adb push SoftmaxUdoPackage/libs/arm64-v8a/libUdoSoftmaxUdoPackageImplCpu.so /data/local/tmp/inception_v3_udo/cpu
adb push SoftmaxUdoPackage/libs/arm64-v8a/libUdoSoftmaxUdoPackageReg.so /data/local/tmp/inception_v3_udo/cpu
adb push SoftmaxUdoPackage/libs/arm64-v8a/libc++_shared.so /data/local/tmp/inception_v3_udo/cpu

Now set required environment variables and run snpe-net-run on device:

adb shell
cd /data/local/tmp/inception_v3_udo/
export SNPE_TARGET_ARCH=aarch64-android
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/lib
export PATH=$PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/bin
export LD_LIBRARY_PATH=/data/local/tmp/inception_v3_udo/cpu/:$LD_LIBRARY_PATH
snpe-net-run --container inception_v3_udo.dlc --input_list target_raw_list.txt --udo_package_path cpu/libUdoSoftmaxUdoPackageReg.so

Android GPU Execution

The procedure for execution using the GPU runtime is largely similar to execution procedure for CPU. First, use the following to place the UDO libraries on device:

cd $SNPE_ROOT/examples/Models/InceptionV3
adb shell "mkdir -p /data/local/tmp/inception_v3_udo/gpu"
adb push SoftmaxUdoPackage/libs/arm64-v8a/libUdoSoftmaxUdoPackageImplGpu.so /data/local/tmp/inception_v3_udo/gpu
adb push SoftmaxUdoPackage/libs/arm64-v8a/libUdoSoftmaxUdoPackageReg.so /data/local/tmp/inception_v3_udo/gpu
adb push SoftmaxUdoPackage/libs/arm64-v8a/libc++_shared.so /data/local/tmp/inception_v3_udo/gpu

Now set required environment variables and run snpe-net-run to device:

adb shell
cd /data/local/tmp/inception_v3_udo/
export SNPE_TARGET_ARCH=aarch64-android
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/lib
export PATH=$PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/bin
export LD_LIBRARY_PATH=/data/local/tmp/inception_v3_udo/gpu/:$LD_LIBRARY_PATH
snpe-net-run --container inception_v3_udo.dlc --input_list target_raw_list.txt --udo_package_path gpu/libUdoSoftmaxUdoPackageReg.so --use_gpu

Hexagon DSP Execution

The procedure for execution on device for DSP is largely the same as CPU and GPU. However, the DSP runtime requires quantized network parameters. While DSP allows unquantized DLCs, it is generally recommended to quantize DLCs for improved performance. The tutorial will use a quantized DLC as an illustrative example. Quantizing the DLC requires the snpe-dlc-quantize tool.

To quantize the DLC for use on DSP:

cd $SNPE_ROOT/examples/Models/InceptionV3/
snpe-dlc-quantize --input_dlc dlc/inception_v3_udo.dlc --input_list data/cropped/raw_list.txt --udo_package_path SoftmaxUdoPackage/libs/x86-64_linux_clang/libUdoSoftmaxUdoPackageReg.so --output_dlc dlc/inception_v3_udo_quantized.dlc

For more information on snpe-dlc-quantize visit quantization. For information on UDO-specific quantization visit Quantizing a DLC with UDO. For information on DSP/AIP runtime visit DSP Runtime or AIP Runtime.

Now push the quantized model to device:

adb push dlc/inception_v3_udo_quantized.dlc /data/local/tmp/inception_v3_udo

Note: Please refer to UDO DSP tutorial for Quantized DLC for executing on the DSP runtime using quantized dlc.

Before executing on the DSP, push the Qualcomm® Neural Processing SDK libraries for DSP to device:

adb shell "mkdir -p /data/local/tmp/snpeexample/dsp/lib"
adb push $SNPE_ROOT/lib/$SNPE_TARGET_DSPARCH/unsigned/*.so /data/local/tmp/snpeexample/dsp/lib

Now push DSP-specific UDO libraries to device. Depending on DSP architecture specified in the config, dsp_v68 directory can be dsp_v60 or dsp (with older Qualcomm® Neural Processing SDK).

cd $SNPE_ROOT/examples/Models/InceptionV3
adb shell "mkdir -p /data/local/tmp/inception_v3_udo/dsp"
adb push SoftmaxUdoPackage/libs/dsp_v68/*.so /data/local/tmp/inception_v3_udo/dsp
adb push SoftmaxUdoPackage/libs/arm64-v8a/libUdoSoftmaxUdoPackageReg.so /data/local/tmp/inception_v3_udo/dsp # Pushes reg lib
adb push SoftmaxUdoPackage/libs/arm64-v8a/libc++_shared.so /data/local/tmp/inception_v3_udo/dsp
adb push SoftmaxUdoPackage/libs/arm64-v8a/libUdoSoftmaxUdoPackageImplDsp_AltPrep.so /data/local/tmp/inception_v3_udo/dsp #If online prepare is used

Then set required environment variables and run snpe-net-run on device:

adb shell
cd /data/local/tmp/inception_v3_udo/
export SNPE_TARGET_ARCH=aarch64-android
export LD_LIBRARY_PATH=/data/local/tmp/inception_v3_udo/dsp:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/lib
export PATH=$PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/bin
export ADSP_LIBRARY_PATH="/data/local/tmp/inception_v3_udo/dsp/;/data/local/tmp/snpeexample/dsp/lib;/system/lib/rfsa/adsp;/system/vendor/lib/rfsa/adsp;/dsp"
snpe-net-run --container inception_v3_udo_quantized.dlc --input_list target_raw_list.txt --udo_package_path dsp/libUdoSoftmaxUdoPackageReg.so --use_dsp

AIP Execution

Because UDOs are not supported on the HTA hardware, executing on the AIP runtime defaults to the DSP UDO implementations. HTA hardware runs exclusively on quantized models and therefore as with the DSP runtime, a quantized model will be used. The command to quantize the DLC for AIP is:

cd $SNPE_ROOT/examples/Models/InceptionV3/
snpe-dlc-quantize --input_dlc dlc/inception_v3_udo.dlc --input_list data/cropped/raw_list.txt --udo_package_path SoftmaxUdoPackage/libs/x86-64_linux_clang/libUdoSoftmaxUdoPackageReg.so --output_dlc dlc/inception_v3_udo_quantized.dlc --enable_hta

Now push the quantized model to device:

adb push dlc/inception_v3_udo_quantized.dlc /data/local/tmp/inception_v3_udo

Before executing using the AIP runtime, push the Qualcomm® Neural Processing SDK libraries for DSP to device with these commands:

adb shell "mkdir -p /data/local/tmp/snpeexample/dsp/lib"
adb push $SNPE_ROOT/lib/$SNPE_TARGET_DSPARCH/unsigned/*.so /data/local/tmp/snpeexample/dsp/lib

Now push DSP-specific UDO libraries to device. Depending on DSP architecture specified in the config, dsp_v68 directory can be dsp_v60 or dsp (with older Qualcomm® Neural Processing SDK).

cd $SNPE_ROOT/examples/Models/InceptionV3
adb shell "mkdir -p /data/local/tmp/inception_v3_udo/dsp"
adb push SoftmaxUdoPackage/libs/dsp_v68/*.so /data/local/tmp/inception_v3_udo/dsp
adb push SoftmaxUdoPackage/libs/arm64-v8a/libUdoSoftmaxUdoPackageReg.so /data/local/tmp/inception_v3_udo/dsp # Pushes reg lib
adb push SoftmaxUdoPackage/libs/arm64-v8a/libc++_shared.so /data/local/tmp/inception_v3_udo/dsp

Then set required environment variables and run snpe-net-run on device:

adb shell
cd /data/local/tmp/inception_v3_udo/
export SNPE_TARGET_ARCH=aarch64-android
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/lib
export PATH=$PATH:/data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/bin
export LD_LIBRARY_PATH=/data/local/tmp/inception_v3_udo/dsp/:$LD_LIBRARY_PATH
export ADSP_LIBRARY_PATH="/data/local/tmp/inception_v3_udo/dsp/;/data/local/tmp/snpeexample/dsp/lib;/system/lib/rfsa/adsp;/system/vendor/lib/rfsa/adsp;/dsp"
snpe-net-run --container inception_v3_udo_quantized.dlc --input_list target_raw_list.txt --udo_package_path dsp/libUdoSoftmaxUdoPackageReg.so --use_aip

Integration with Android APK

This portion of the tutorial outlines how to integrate Qualcomm® Neural Processing SDK UDO libraries and Java API for package registration into an Android application. Generally, for native shared libraries to be discoverable by the application they must be placed in the project under

<project>/app/src/main/jniLibs/<platform_abi>

Once the libraries are accessible by the application, the registration library can be registered using the provided Java API. This process will be replicated with the example Image Classifiers application. The following assumes that the rest of the example application setup has been followed. The tutorial will issue instructions for platforms with arm64-v8a ABI.

First, create the neccessary directories to contain the UDO libraries. The following steps will populate all runtime implementation libraries.

mkdir app/src/main/jniLibs/
cp -a $SNPE_ROOT/examples/Models/InceptionV3/SoftmaxUdoPackage/libs/arm64-v8a/ app/src/main/jniLibs/

If DSP is to be used as the runtime, copy the implementation library with the following:

cp $SNPE_ROOT/examples/Models/InceptionV3/SoftmaxUdoPackage/libs/dsp_v68/*.so app/src/main/jniLibs/arm64-v8a/

If not already done, running setup_inceptionv3.sh will add the Inception V3 model enabled with UDO and image data to the project.

bash ./setup_inceptionv3.sh

Now the Java API can be registered. Include the Qualcomm® Neural Processing SDK AAR which includes necessary native binaries

export SNPE_AAR=snpe-release.aar
cp $SNPE_ROOT/lib/android/${SNPE_AAR} app/libs/${SNPE_AAR}

Now the APK can be built and exercised

# exporting gradle user_home is optional but suggested if USER_HOME storage is low
export GRADLE_USER_HOME=<local path for caching gradle files>
export ANDROID_SDK_ROOT=<path to android-sdk-9>
./gradlew assembleDebug

For more information, visit Android Sample App.