-
80-NL315-14 A
MAY CONTAIN U.S. AND INTERNATIONAL EXPORT CONTROLLED INFORMATION
|
Snapdragon Neural Processing Engine SDK
Reference Guide
|
This tutorial describes the steps needed to create a UDO package for DSP runtime 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 SNPE. This tutorial also describes the offline cache generation steps for DSP V68.
The SNPE SDK provides the resources for this example under
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.
The artifacts necessary to run the Inception-V3 network for CPU, GPU, and DSP runtime will be generated in this tutorial. The steps required to compile and execute the Inception-V3 network for DSP runtime alone are outlined here. Information on running the Inception-V3 network for CPU and GPU runtime is available at Inception-V3 UDO Tutorial.
The following tutorial assumes that general SNPE setup has been followed to support SDK environment, TensorFlow environment, and desired platform dependencies. Additionally, we need an extracted QNN-SDK (no need of QNN-SDK setup) for generating the skeleton code and building the libraries. For QNN-SDK details, refer to the QNN documentation at $QNN_SDK_ROOT/docs/index.html page, where QNN_SDK_ROOT is the location of the QNN-SDK installation. Set the $QNN_SDK_ROOT to the unzipped QNN-SDK location. 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.
Here are the steps to develop and run a UDO
2.) Framework Model Conversion to a DLC
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 SNPE command-line executable snpe-net-run. Optionally, the user can perform steps 1-4 automatically using the provided setup script.
Generating the SoftmaxUdoPackage requires the snpe-udo-package-generator tool and the provided UDO plugin: Softmax_Quant.json. The plugin is located under $SNPE_ROOT/examples/NativeCpp/UdoExample/Softmax/config. More information about creating a UDO plugin can be found here.
Generate the SoftmaxUdoPackage using the following:
export SNPE_UDO_ROOT=$SNPE_ROOT/share/SnpeUdo snpe-udo-package-generator -p $SNPE_ROOT/examples/NativeCpp/UdoExample/Softmax/config/Softmax_Quant.json -o $SNPE_ROOT/models/inception_v3/
Similarly for DSP V68 example, Config is available at the location
This command creates the Softmax based package at $SNPE_ROOT/models/inception_v3/SoftmaxUdoPackage.
For more information on the snpe-udo-package-generator tool visit here.
Information for converting a model to a DLC is available at Inception V3 UDO Model Conversion.
This will generate a DLC named inception_v3_udo.dlc containing the Softmax as UDO at $SNPE_ROOT/models/inception_v3/dlc.
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 SNPE is provided by the snpe-udo-package-generator.
The UDO implementations for this tutorial are provided under $SNPE_ROOT/examples/NativeCpp/UdoExample/Softmax/src.
DSP Implementations for V65 and V66
A registration library and an implementation library are required to run inference on a network with UDO layers on SNPE 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
The provided example implementation is present at the location
Copy the provided implementations to the package:
cp -f $SNPE_ROOT/examples/NativeCpp/UdoExample/Softmax/src/DSP/Softmax.cpp $SNPE_ROOT/models/inception_v3/SoftmaxUdoPackage/jni/src/DSP/
Optionally, the user can provide their own implementations in the package.
DSP Implementations for V68 or later
Similar to all other SNPE runtimes, a registration library and an implementation library are required to run inference on a network with UDO layers on SNPE DSP. The registration library will run on CPU, and specifies the DSP implementation library of the UDO.
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
The provided example implementation is present at the location
Copy the provided implementations to the package:
cp -f $SNPE_ROOT/examples/NativeCpp/UdoExample/Softmax/src/DSP_v68/SoftmaxImplLibDsp.cpp $SNPE_ROOT/models/inception_v3/SoftmaxUdoPackage/jni/src/DSP_V68/
Optionally, the user can provide their own implementations in the package.
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.
In order to build the implementation libraries for DSP V68 or later runtimes, Hexagon-SDK 4.0+ needs to be installed and set up. For Hexagon-SDK details, follow the setup instructions on $HEXAGON_SDK4_ROOT/docs/readme.html page, where HEXAGON_SDK_ROOT is the location of your Hexagon-SDK installation. Also, we need an extracted QNN-SDK (no need of QNN-SDK setup) for building the libraries. For QNN-SDK details, refer to the QNN documentation at $QNN_SDK_ROOT/docs/index.html page, where QNN_SDK_ROOT is the location of the QNN-SDK installation. Set the $QNN_SDK_ROOT to the unzipped QNN-SDK location. Information for compiling a UDO for DSP V68 or later is available at Compiling a UDO for DSP_V68 or later.
Compile for offline cache generation in case of DSP V68:
cd SoftmaxUdoPackage make dsp_x86 X86_CXX=<path_to_x86_64_clang>
The expected artifact after compiling for offline cache generation is
The SNPE 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/inception_v3/scripts/setup_inceptionv3.py [-h] -a ASSETS_DIR [-d] [-r RUNTIME] [-u] [-l [HTP_SOC]]
Prepares the inception_v3 assets for tutorial examples.
required arguments:
-a ASSETS_DIR, --assets_dir ASSETS_DIR
directory containing the inception_v3 assets
optional arguments:
-d, --download Download inception_v3 assets to inception_v3 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 inception_v3. 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 waipio, default
value is sm8550
The --udo extension is compatible with options normally used by the setup_inceptionv3.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 SoftmaxUdo Package 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 -l or --htp_soc option will generate and compile the package for the HTP architecture of the SoC provided.
The command to use the setup script for UDO is:
python3 $SNPE_ROOT/models/inception_v3/scripts/setup_inceptionv3.py -a ~/tmpdir -d -u -r <runtime_of_choice>
In case of DSP V68:
python3 $SNPE_ROOT/models/inception_v3/scripts/setup_inceptionv3.py -a ~/tmpdir -d -u -r <runtime_of_choice> -l
This will populate the artifacts in Step 4.
Note: Setup script compiles for arm64-v8a platform architecture. To compile for different target set PLATFORM when using make. See step 4 for more.
Execution using snpe-net-run
Executing Inception-V3 for UDO is largely the same as use of snpe-net-run without UDO.
The SNPE SDK provides Linux and Android binaries of snpe-net-run under
For UDO, snpe-net-run consumes the registration library through the --udo_package_path option. LD_LIBRARY_PATH must also be updated to include the runtime-specific artifacts generated from package compilation.
Android Target Execution
The tutorial for execution on Android targets will use the arm64-v8a architecture.
# architecture: arm64-v8a - compiler: clang - STL: libc++ export SNPE_TARGET_ARCH=aarch64-android-clang8.0 export SNPE_TARGET_STL=libc++_shared.so
Then, push SNPE binaries and libraries to the target device:
adb shell "mkdir -p /data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/bin"
adb shell "mkdir -p /data/local/tmp/snpeexample/$SNPE_TARGET_ARCH/lib"
adb push $SNPE_ROOT/lib/$SNPE_TARGET_ARCH/$SNPE_TARGET_STL \
/data/local/tmp/snpeexample/$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/$SNPE_TARGET_ARCH/bin
Next, update environment variables on the target device to include the SNPE libraries and binaries:
adb shell export SNPE_TARGET_ARCH=aarch64-android-clang8.0 export LD_LIBRARY_PATH=$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/models/inception_v3 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
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.
Note: In the below command one should use input dlc generated at Model DLC Conversion. Also, provide the path of the registration lib generated after compiling x86 Host under the argument "udo_package_path". More information about compiling x86 can be found here.
To quantize the DLC for use on DSP:
cd $SNPE_ROOT/models/inception_v3/ 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 quantizing the DLC with offline cache generation to use on DSP V68 :
Copy the generated registration library libUdoSoftmaxUdoPackageReg.so and implementation library libUdoSoftmaxUdoPackageImplCpu.so after compiling x86 to SoftmaxUdoPackage/libs/x86-64_linux_clang. More information about compiling x86 can be found here.
cd $SNPE_ROOT/models/inception_v3/ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:SoftmaxUdoPackage/libs/x86-64_linux_clang 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_htp
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
Before executing on the DSP, push the SNPE libraries for DSP to device:
adb shell "mkdir -p /data/local/tmp/snpeexample/dsp/lib" adb push $SNPE_ROOT/lib/dsp/*.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 SNPE SDK).
cd $SNPE_ROOT/models/inception_v3/ adb shell "mkdir -p /data/local/tmp/inception_v3_udo/dsp" adb push SoftmaxUdoPackage/libs/dsp_v68/*.so /data/local/tmp/inception_v3_udo/dsp adb push SoftmaxUdoPackage/libs/arm64-v8a/libUdoSoftmaxUdoPackageReg.so /data/local/tmp/inception_v3_udo/dsp # Pushes reg lib
Then set required environment variables and run snpe-net-run on device:
adb shell cd /data/local/tmp/inception_v3_udo/ export LD_LIBRARY_PATH=/data/local/tmp/inception_v3_udo/dsp/:$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_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.
Note: In the below command one should use input dlc generated at Model DLC Conversion. Also provide the path of the registration lib generated after compiling x86 Host under the argument "udo_package_path". More information about compiling x86 can be found here.
The command to quantize the DLC for AIP is:
cd $SNPE_ROOT/models/inception_v3/ 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 SNPE libraries for DSP to device with these commands:
adb shell "mkdir -p /data/local/tmp/snpeexample/dsp/lib" adb push $SNPE_ROOT/lib/dsp/*.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 SNPE SDK).
cd $SNPE_ROOT/models/inception_v3/ adb shell "mkdir -p /data/local/tmp/inception_v3_udo/dsp" adb push SoftmaxUdoPackage/libs/dsp_v68/*.so /data/local/tmp/inception_v3_udo/dsp adb push SoftmaxUdoPackage/libs/arm64-v8a/libUdoSoftmaxUdoPackageReg.so /data/local/tmp/inception_v3_udo/dsp # Pushes reg lib
Then set required environment variables and run snpe-net-run on device:
adb shell cd /data/local/tmp/inception_v3_udo/ export LD_LIBRARY_PATH=/data/local/tmp/inception_v3_udo/dsp/:$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 SNPE 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/models/inception_v3/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/models/inception_v3/SoftmaxUdoPackage/libs/dsp/*.so app/src/main/jniLibs/arm64-v8a/
If not already done, running setup_inceptionv3.sh will add the Inception-V3 model enabled with UDO to the project.
bash ./setup_inceptionv3.sh
Now the Java API can be registered. Edit the file $SNPE_ROOT/examples/android/image-classifiers/app/src/main/java/com/qualcomm/qti/snpe/imageclassifiers/tasks/LoadNetworkTask.java
To contain this line
@Override
protected NeuralNetwork doInBackground(File... params) {
NeuralNetwork network = null;
try {
SNPE.addOpPackage(mApplication,"libUdoSoftmaxUdoPackageReg.so"); // Add this line to register package
final SNPE.NeuralNetworkBuilder builder = new SNPE.NeuralNetworkBuilder(mApplication)
...
Now the APK can be built and exercised
./gradlew assembleDebug
80-NL315-14 A
MAY CONTAIN U.S. AND INTERNATIONAL EXPORT CONTROLLED INFORMATION