-
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 run UDO with weights and execute the Alexnet model using the package. The Convolution operation has been chosen in this tutorial to demonstrate the implementation of a UDO with weights.
The SNPE SDK provides the resources for this example under
Information on UDO in general is available at UDO Overview.
Information on running the Alexnet network without UDO is available at Alexnet Tutorial.
Information on creating a UDO package and executing the model using the package is available at UDO Tutorial.
The following tutorial assumes that general SNPE setup has been followed to support SDK environment, Caffe 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. For details on acquiring the Alexnet 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.
Generating the Conv2DPackage requires the snpe-udo-package-generator tool and the provided UDO plugin: Conv2D.json / Conv2DQuant.json depending on your runtime requirement. The Conv2D.json and Conv2DQuant.json gives you skeleton code for CPU(float) and DSP(uint8) implementations respectively. The plugins is located under $SNPE_ROOT/examples/NativeCpp/UdoExample/Conv2D/config. More information about creating a UDO plugin can be found here.
Generate the Conv2DPackage UDO package using the following:
export SNPE_UDO_ROOT=$SNPE_ROOT/share/SnpeUdo mkdir $SNPE_ROOT/models/alexnet/ConvUdoCpu snpe-udo-package-generator -p $SNPE_ROOT/examples/NativeCpp/UdoExample/Conv2D/config/Conv2D.json -o $SNPE_ROOT/models/alexnet/ConvUdoCpu
or for DSP
export SNPE_UDO_ROOT=$SNPE_ROOT/share/SnpeUdo mkdir $SNPE_ROOT/models/alexnet/ConvUdoDsp snpe-udo-package-generator -p $SNPE_ROOT/examples/NativeCpp/UdoExample/Conv2D/config/Conv2DQuant.json -o $SNPE_ROOT/models/alexnet/ConvUdoDsp
This command creates the Convolution based package at $SNPE_ROOT/models/alexnet/ConvUdoCpu/Conv2DPackage or $SNPE_ROOT/models/alexnet/ConvUdoDsp/Conv2DPackage.
For more information on the snpe-udo-package-generator tool visit here.
Converting the Caffe Alexnet model to DLC requires the snpe-caffe-to-dlc tool. The snpe-caffe-to-dlc tool consumes the same Conv2D.json used in package generation via the --udo command line option. If you follow Tutorials Setup, an alexnet with batch dimension 1 will be in $SNPE_ROOT/models/alexnet/caffe.
Then we can convert Alexnet with the following:
snpe-caffe-to-dlc --input_network $SNPE_ROOT/models/alexnet/caffe/deploy_batch_1.prototxt --caffe_bin $SNPE_ROOT/models/alexnet/caffe/bvlc_alexnet.caffemodel --output_path $SNPE_ROOT/models/alexnet/dlc/alexnet_udo.dlc --udo $SNPE_ROOT/examples/NativeCpp/UdoExample/Conv2D/config/Conv2D.json
This will generate a DLC named alexnet_udo.dlc containing the Convolution as UDO at $SNPE_ROOT/models/alexnet/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/Conv2D/src.
Note: Implementing validation is user-specific and not a strict requirement for using a UDO in SNPE.
CPU Implementations (Android and x86)
The file in the package that needs to be implemented for CPU is
The provided example implementation is present at the location
Copy the provided implementation to the package:
cp -f $SNPE_ROOT/examples/NativeCpp/UdoExample/Conv2D/src/CPU/Convolution.cpp $SNPE_ROOT/models/alexnet/ConvUdoCpu/Conv2DPackage/jni/src/CPU/
DSP Implementations (Android) for V65 and V66
Please note that only C files are supported for UDO on DSP V65 and V66 runtimes. Refer Implementing a UDO for DSP V65 and V66 for more information on implementing UDO for DSP V65 and V66 runtimes. The example here executes float implementation on DSP runtime. Please refer to UDO DSP for Quantized DLC tutorial for executing quantized implementation on DSP runtime.
The files in the package that need to be implemented for DSP are
The provided example implementations are present at the locations
Copy the provided implementations to the package:
cp -f $SNPE_ROOT/examples/NativeCpp/UdoExample/Conv2D/src/DSP/Conv2DInt8Impl/ConvolutionImplLibDsp.c $SNPE_ROOT/models/alexnet/ConvUdoDsp/Conv2DPackage/jni/src/DSP/ cp -f $SNPE_ROOT/examples/NativeCpp/UdoExample/Conv2D/src/DSP/Conv2DInt8Impl/ConvolutionImplLibDsp.h $SNPE_ROOT/models/alexnet/ConvUdoDsp/Conv2DPackage/include/
Optionally, the user can provide their own implementations in the package.
DSP Implementations for V68 and later
Please note that only C++ files are supported for UDO on DSP V68 and later runtimes. 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 runtimes later than DSP V68, 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
Optionally, the user can provide their own implementations in the package.
x86 Host Compilation
Compiling on x86 host uses the make build system. Compile the CPU implementations with the following:
cd $SNPE_ROOT/models/alexnet/ConvUdoCpu/Conv2DPackage make cpu_x86
The expected artifacts after compiling for CPU on x86 host are
Android CPU Runtime Compilation
Compilation for the CPU runtime on Android uses Android NDK. The ANDROID_NDK_ROOT environment variable must be set to the directory containing ndk-build in order to compile the package.
export ANDROID_NDK_ROOT=<path_to_android_ndk>
It is suggested to add ANDROID_NDK_ROOT to the PATH environment variable to access ndk-build.
export PATH=$ANDROID_NDK_ROOT:$PATH
Target architecture must also be specified when compiling the package.
export UDO_APP_ABI=<target_architecture>
This tutorial uses arm64-v8a architectures - it is recommended but not required to use arm64-v8a as the target architecture for the remainder of the tutorial. If no target architecture is supplied both arm64-v8a and armeabi-v7a are targeted.
Once the ANDROID_NDK_ROOT is part of PATH, compile the package for Android CPU target:
cd $SNPE_ROOT/models/alexnet/ConvUdoCpu/Conv2DPackage make cpu_android PLATFORM=$UDO_APP_ABI
The expected artifacts after compiling for Android CPU are
Hexagon DSP Runtime Compilation
Compilation for the DSP runtime makes use of the make system. In order to build the DSP implementation libraries, 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.
Execution using snpe-net-run
Executing AlexNet with 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.
x86 Host Execution
To execute the network on x86 host, run:
cd $SNPE_ROOT/models/alexnet export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$SNPE_ROOT/models/alexnet/ConvUdoCpu/Conv2DPackage/libs/x86-64_linux_clang/ snpe-net-run --container dlc/alexnet_udo.dlc --input_list data/cropped/raw_list.txt --udo_package_path ConvUdoCpu/Conv2DPackage/libs/x86-64_linux_clang/libUdoConv2DPackageReg.so
Android Target Execution
The tutorial for execution on Android targets will use the arm64-v8a architecture. This portion of the tutorial is generic to all runtimes (CPU, DSP).
# architecture: arm64-v8a - compiler: clang - STL: libc++ export SNPE_TARGET_ARCH=aarch64-android-clang8.0 export SNPE_TARGET_STL=libc++_shared.so
Then, push SNPE binaries and libraries to the target device:
adb shell "mkdir -p /data/local/tmp/snpeexample/$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 Alexnet UDO model and input data to the device:
cd $SNPE_ROOT/models/alexnet mkdir data/rawfiles && cp data/cropped/*.raw data/rawfiles/ adb shell "mkdir -p /data/local/tmp/alexnet_udo" adb push data/rawfiles /data/local/tmp/alexnet_udo/cropped adb push data/target_raw_list.txt /data/local/tmp/alexnet_udo adb push dlc/alexnet_udo.dlc /data/local/tmp/alexnet_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 $SNPE_ROOT/models/alexnet/ConvUdoCpu adb shell "mkdir -p /data/local/tmp/alexnet_udo/cpu" adb push Conv2DPackage/libs/arm64-v8a/libUdoConv2DUdoPackageImplCpu.so /data/local/tmp/alexnet_udo/cpu adb push Conv2DPackage/libs/arm64-v8a/libUdoConv2DUdoPackageReg.so /data/local/tmp/alexnet_udo/cpu adb push Conv2DPackage/libs/arm64-v8a/libc++_shared.so /data/local/tmp/alexnet_udo/cpu
Now set required environment variables and run snpe-net-run on device:
adb shell cd /data/local/tmp/alexnet_udo/ export LD_LIBRARY_PATH=/data/local/tmp/alexnet_udo/cpu/:$LD_LIBRARY_PATH snpe-net-run --container alexnet_udo.dlc --input_list target_raw_list.txt --udo_package_path cpu/libUdoConv2DPackageReg.so
Hexagon DSP Execution
The procedure for execution on device for DSP is largely the same as CPU. 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/models/alexnet/ snpe-dlc-quantize --input_dlc dlc/alexnet_udo.dlc --input_list data/cropped/raw_list.txt --udo_package_path ConvUdoCpu/Conv2DPackage/libs/x86-64_linux_clang/libUdoConv2DPackageReg.so --output_dlc dlc/alexnet_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 runtime visit DSP Runtime.
Now push the quantized model to device:
adb push dlc/alexnet_udo_quantized.dlc /data/local/tmp/alexnet_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 $SNPE_ROOT/models/alexnet/ConvUdoDsp adb shell "mkdir -p /data/local/tmp/alexnet_udo/dsp" adb push Conv2DPackage/libs/dsp_v68/*.so /data/local/tmp/alexnet_udo/dsp adb push Conv2DPackage/libs/arm64-v8a/libUdoConv2DPackageReg.so /data/local/tmp/alexnet_udo/dsp # Pushes reg lib
Then set required environment variables and run snpe-net-run on device. Note that Conv2DInt8Impl should be used for quantized DLCs:
adb shell cd /data/local/tmp/alexnet_udo/ export LD_LIBRARY_PATH=/data/local/tmp/alexnet_udo/dsp/:$LD_LIBRARY_PATH export ADSP_LIBRARY_PATH="/data/local/tmp/alexnet_udo/dsp/;/data/local/tmp/snpeexample/dsp/lib;/system/lib/rfsa/adsp;/system/vendor/lib/rfsa/adsp;/dsp" snpe-net-run --container alexnet_udo_quantized.dlc --input_list target_raw_list.txt --udo_package_path dsp/libUdoConv2DPackageReg.so --use_dsp
To verify classification results, run the following on your host cpu machine.
cd $SNPE_ROOT/models/alexnet/
adb pull /data/local/tmp/alexnet_udo/output .
python3 $SNPE_ROOT/models/alexnet/scripts/show_alexnet_classifications.py -i data/cropped/raw_list.txt \
-o output/ \
-l data/ilsvrc_2012_labels.txt
The output should look like the following, showing classification results for all the images.
Classification results
<input_files_dir>/trash_bin.raw 0.949348 412 ashcan, trash can, garbage can,
wastebin, ash bin, ash-bin, ashbin,
dustbin, trash barrel, trash bin
<input_files_dir>/plastic_cup.raw 0.749104 647 measuring cup
<input_files_dir>/chairs.raw 0.365685 831 studio couch, day bed
<input_files_dir>/notice_sign.raw 0.722708 458 brass, memorial tablet, plaque
80-NL315-14 A
MAY CONTAIN U.S. AND INTERNATIONAL EXPORT CONTROLLED INFORMATION