Блог

Главная - Вопросы по программированию - Проблемы делегирования GPU в tensorflow-lite в Android studio

Проблемы делегирования GPU в tensorflow-lite в Android studio

#java #android-studio #tensorflow #opencl #tensorflow-lite

Вопрос:

Я получаю ошибку, когда запускаю свое приложение в Android studio. Я слежу за обучающими видеороликами ElectroCode по созданию приложения для распознавания языка жестов на YouTube.

Это мой журнал ошибок:

 E/AndroidRuntime: FATAL EXCEPTION: Thread-4
    Process: com.example.imagepro, PID: 7161
    java.lang.IllegalArgumentException: Internal error: Failed to run on the given Interpreter: Next operations are not supported by GPU delegate:
    CUSTOM TFLite_Detection_PostProcess: Operation is not supported.
    First 98 operations will run on the GPU, and the remaining 1 on the CPU.
    OpenCL library not loaded - dlopen failed: library "libOpenCL-pixel.so" not found
    Falling back to OpenGL
    TfLiteGpuDelegate Invoke: ToTensorConverter: input data size does not match expected size.
    Node number 99 (TfLiteGpuDelegateV2) failed to invoke.

        at org.tensorflow.lite.NativeInterpreterWrapper.run(Native Method)
        at org.tensorflow.lite.NativeInterpreterWrapper.run(NativeInterpreterWrapper.java:163)
        at org.tensorflow.lite.Interpreter.runForMultipleInputsOutputs(Interpreter.java:360)
        at com.example.imagepro.objectDetectorClass.recognizeImage(objectDetectorClass.java:159)
        at com.example.imagepro.CameraActivity.onCameraFrame(CameraActivity.java:130)
        at org.opencv.android.CameraBridgeViewBase.deliverAndDrawFrame(CameraBridgeViewBase.java:392)
        at org.opencv.android.JavaCameraView$CameraWorker.run(JavaCameraView.java:373)
        at java.lang.Thread.run(Thread.java:929)
D/CameraBridge: call checkCurrentState
Метки: