在Android上部署TensorFlowLite报错（The model is not a valid Flatbuffer buffer）

Question

经过了一两天的折腾，我终于可以运行TensorFlowLite这个项目了，但是运行时，APP又闪退了，而且报了这个错误：

The model is not a valid Flatbuffer buffer

我使用的是这个教程：

https://www.jianshu.com/p/50f5c7d32575

完整报错信息如下所示：

I/tensorflow: CameraConnectionFragment: Desired size: 640x480, min size: 480x480
    CameraConnectionFragment: Valid preview sizes: [640x480, 1280x720, 1280x960]
    CameraConnectionFragment: Rejected preview sizes: [352x288, 320x240, 176x144]
    CameraConnectionFragment: Exact size match found.
W/Gralloc4: allocator 3.x is not supported
I/OpenGLRenderer: Davey! duration=729ms; Flags=0, IntendedVsync=19184231315234, Vsync=19184631315218, OldestInputEvent=9223372036854775807, NewestInputEvent=0, HandleInputStart=19184633402720, AnimationStart=19184633419620, PerformTraversalsStart=19184633445520, DrawStart=19184635850020, SyncQueued=19184636460520, SyncStart=19184636978920, IssueDrawCommandsStart=19184637139320, SwapBuffers=19184638083420, FrameCompleted=19184961823020, DequeueBufferDuration=32864300, QueueBufferDuration=887800, GpuCompleted=8245932998015870825, 
D/AndroidRuntime: Shutting down VM
E/AndroidRuntime: FATAL EXCEPTION: main
    Process: org.tensorflow.lite.examples.detection, PID: 15312
    java.lang.AssertionError: Error occurred when initializing ObjectDetector: The model is not a valid Flatbuffer buffer
        at org.tensorflow.lite.task.vision.detector.ObjectDetector.initJniWithByteBuffer(Native Method)
        at org.tensorflow.lite.task.vision.detector.ObjectDetector.access$100(ObjectDetector.java:86)
        at org.tensorflow.lite.task.vision.detector.ObjectDetector$3.createHandle(ObjectDetector.java:211)
        at org.tensorflow.lite.task.core.TaskJniUtils.createHandleFromLibrary(TaskJniUtils.java:91)
        at org.tensorflow.lite.task.vision.detector.ObjectDetector.createFromBufferAndOptions(ObjectDetector.java:207)
        at org.tensorflow.lite.examples.detection.tflite.TFLiteObjectDetectionAPIModel.<init>(TFLiteObjectDetectionAPIModel.java:87)
        at org.tensorflow.lite.examples.detection.tflite.TFLiteObjectDetectionAPIModel.create(TFLiteObjectDetectionAPIModel.java:81)
        at org.tensorflow.lite.examples.detection.DetectorActivity.onPreviewSizeChosen(DetectorActivity.java:99)
        at org.tensorflow.lite.examples.detection.CameraActivity.onPreviewFrame(CameraActivity.java:200)
        at android.hardware.Camera$EventHandler.handleMessage(Camera.java:1227)
        at android.os.Handler.dispatchMessage(Handler.java:106)
        at android.os.Looper.loop(Looper.java:223)
        at android.app.ActivityThread.main(ActivityThread.java:7656)
        at java.lang.reflect.Method.invoke(Native Method)
        at com.android.internal.os.RuntimeInit$MethodAndArgsCaller.run(RuntimeInit.java:592)
        at com.android.internal.os.ZygoteInit.main(ZygoteInit.java:947)
I/Process: Sending signal. PID: 15312 SIG: 9

报错图片：

Logcat报错图片：

我使用的模型文件是自动下载的.tflite文件：

不知道这个问题应该怎么解决，希望有解决这个问题的同学可以和我分享一下解决方案，谢谢啦。

Answer 1

兄弟，没玩过这个额，你看看下是不是这个原因啊：

ByteBuffer is not a valid flatbuffer model - 简书 在Android手机上使用tensorflow训练出来的猫狗识别模型时，遇到如题目的问题 一加载模型，就报错，查了很多原因，通过上面的V3和下面的V2的对比，发现只能用V2的... https://www.jianshu.com/p/e03f081a135b