Fail to use custom model in tensorflow lite object detection android app

Question

I trained model using Google AutoMl then produce tensorflow lite model to detect plastic bottle etc. I would like to use in the tensorflowlite object detection android example but failed

this the github that i refer : https://github.com/tensorflow/examples/tree/master/lite/examples/object_detection/android

i replaced the tflite file and the txt file with my own project, the installation on android studio its work well but the apps its crashed and didnt work

public class DetectorActivity extends CameraActivity implements OnImageAvailableListener {
  private static final Logger LOGGER = new Logger();

  // Configuration values for the prepackaged SSD model.
  private static final int TF_OD_API_INPUT_SIZE = 300;
  private static final boolean TF_OD_API_IS_QUANTIZED = true;
  private static final String TF_OD_API_MODEL_FILE = "swai.tflite";
  private static final String TF_OD_API_LABELS_FILE = "file:///android_asset/swai.txt";
  private static final DetectorMode MODE = DetectorMode.TF_OD_API;
  // Minimum detection confidence to track a detection.
  private static final float MINIMUM_CONFIDENCE_TF_OD_API = 0.5f;
  private static final boolean MAINTAIN_ASPECT = false;
  private static final Size DESIRED_PREVIEW_SIZE = new Size(640, 480);
  private static final boolean SAVE_PREVIEW_BITMAP = false;
  private static final float TEXT_SIZE_DIP = 10;
  OverlayView trackingOverlay;

this the eror that i found when deploying in the virtual devices

09-17 13:32:09.283 1599-1856/? D/gralloc_ranchu: gralloc_alloc: Creating ashmem region of size 462848
09-17 13:32:09.325 9980-10000/org.tensorflow.lite.examples.detection E/AndroidRuntime: FATAL EXCEPTION: inference
    Process: org.tensorflow.lite.examples.detection, PID: 9980
    java.lang.IllegalArgumentException: Cannot convert between a TensorFlowLite buffer with 786432 bytes and a ByteBuffer with 270000 bytes.
        at org.tensorflow.lite.Tensor.throwIfShapeIsIncompatible(Tensor.java:272)
        at org.tensorflow.lite.Tensor.throwIfDataIsIncompatible(Tensor.java:249)
        at org.tensorflow.lite.Tensor.setTo(Tensor.java:110)
        at org.tensorflow.lite.NativeInterpreterWrapper.run(NativeInterpreterWrapper.java:151)
        at org.tensorflow.lite.Interpreter.runForMultipleInputsOutputs(Interpreter.java:275)
        at org.tensorflow.lite.examples.detection.tflite.TFLiteObjectDetectionAPIModel.recognizeImage(TFLiteObjectDetectionAPIModel.java:193)
        at org.tensorflow.lite.examples.detection.DetectorActivity$2.run(DetectorActivity.java:181)
        at android.os.Handler.handleCallback(Handler.java:873)
        at android.os.Handler.dispatchMessage(Handler.java:99)
        at android.os.Looper.loop(Looper.java:193)
        at android.os.HandlerThread.run(HandlerThread.java:65)

I think there is no settings to implement this model work, Any Sugesstion please? Thanks!

Hi Ali, could you please add the error logcat in the question? That would make it easier for us to figure out what the error could be. — BennyHawk
@BennyHawk Thanks for reply, i already add the error logcat.. — Ali Hafidz
What was the input shape for your model which you trained with AutoML? — Shubham Panchal

Ali Hafidz Ali Hafidz · Accepted Answer · 2019-09-18T07:08:20

case close, solved with changing the TF_OD_API_INPUT_SIZE from 300 to 512. 786432 is represent 512x512x3 but my input is only 270000 (300x3003).

Fail to use custom model in tensorflow lite object detection android app

1 Answers