I am using Snapdragon Neural Processing Engine (SNPE) 1.19.2 and i am trying to build the android app example with android studio. I also run the setup_inception_v3.py script, and i have theinception_v3.zip in res/raw folder. When i build the project I get a success message. During runtime, when i try to build the network, with the build() method:
final SNPE.NeuralNetworkBuilder builder = new SNPE.NeuralNetworkBuilder(mApplication) .setDebugEnabled(false) .setRuntimeOrder(mTargetRuntime) .setModel(mModel.file) .setCpuFallbackEnabled(true) .setUseUserSuppliedBuffers(mTensorFormat != SupportedTensorFormat.FLOAT); final long start = SystemClock.elapsedRealtime(); network = builder.build();
I get the following error:
E/LoadNetworkTask: Unable to create network! Cause: error_code=307; error_message=Model record is missing in dlc. Missing mandatory record model; error_component=Dl Container; line_no=497; thread_id=547841111120
java.lang.IllegalStateException: Unable to create network! Cause: error_code=307; error_message=Model record is missing in dlc. Missing mandatory record model; error_component=Dl Container; line_no=497; thread_id=547841111120
at com.qualcomm.qti.snpe.internal.NativeNetwork.nativeInitFromFile(Native Method)
at com.qualcomm.qti.snpe.internal.NativeNetwork.<init>(NativeNetwork.java:104)
at com.qualcomm.qti.snpe.SNPE$NeuralNetworkBuilder.build(SNPE.java:272)
at com.example.luca.myapplication2.tasks.LoadNetworkTask.doInBackground(LoadNetworkTask.java:58)
at com.example.luca.myapplication2.tasks.LoadNetworkTask.doInBackground(LoadNetworkTask.java:18)
at android.os.AsyncTask$2.call(AsyncTask.java:305)
at java.util.concurrent.FutureTask.run(FutureTask.java:237)
at android.os.AsyncTask$SerialExecutor$1.run(AsyncTask.java:243)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1133)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:607)
at java.lang.Thread.run(Thread.java:761)
I try with ubuntu 14.04,16.04 and 18.04 and i get the same problem.
How to fix this problem? Thanks.
In the last, have you resolve the probelm, it occurs to me the same
Hi. I am having the same problem - were you ever able to resolve the problem?
Hi
After running the setup_inception_v3.py script you have to follow few more steps to prepare the APP by copying the runtime and the model.
Bellow are the instructions to follow after executing “setup_inception_v3.py”,
$ cd $SNPE_ROOT/examples/android/image-classifiers
$ cp ../../../android/snpe-release.aar ./app/libs # copies the NPE runtime library
$ bash ./setup_inceptionv3.sh # packages the Inception_v3 example (DLC, labels, inputs) as an Android resource file
Follow the SNPE setup guide from QDN https://developer.qualcomm.com/software/qualcomm-neural-processing-sdk/getting-started.
I have not tried –use_gpu or –use_dsp options because i know those won’t work without KGSL and FastRPC support. I am not sure about making GPU runtime working but for aDSP, I think we can port FastRPC. I would like to know if some is already working on GPU support.
Hi Cciedump,
We worked on GPU runtime, can you let us know what kind of support you are expecting for GPU support.