[FIXED] NaN in tflite model

Issue

i created a model with Keras and have

model = tf.keras.models.Sequential([ 
    tf.keras.layers.Conv2D(16,(3,3), activation = 'relu', input_shape=(size,size,3)),
    tf.keras.layers.MaxPooling2D(2,2),

    tf.keras.layers.Conv2D(32,(3,3), activation = 'relu'),
    tf.keras.layers.MaxPooling2D(2,2),

    tf.keras.layers.Conv2D(64,(3,3), activation = 'relu'),
    tf.keras.layers.MaxPooling2D(2,2),

    tf.keras.layers.Conv2D(128,(3,3), activation = 'relu'),
    tf.keras.layers.MaxPooling2D(2,2),

    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(512, activation = 'relu'),
    tf.keras.layers.Dense(512, activation = 'relu'),
    tf.keras.layers.Dense(2, activation='softmax',name='predictions')
  ])

  model.compile(optimizer='adam',
                loss='categorical_crossentropy',
                metrics=['accuracy']) 

my predict in Python:

print(model.predict(x))

return:

[[1. 0.]]

and convert model to tflite:

# Convert the model.
converter = tf.lite.TFLiteConverter.from_keras_model(model)
tflite_model = converter.convert()

# Save the model.
with open('model.tflite', 'wb') as f:
  f.write(tflite_model)

And when I implement this in kotlin to app:

val resizeBitmap: Bitmap = Bitmap.createScaledBitmap(bitmap, 300, 300, true)
        val model = com.example.iscanner.ml.Model.newInstance(context)
        val theBuffer = TensorImage.fromBitmap(resizeBitmap)
        val byteBuffer = theBuffer.buffer
        val inputFeature0 = TensorBuffer.createFixedSize(intArrayOf(1, 150, 150, 3), DataType.FLOAT32)
        inputFeature0.loadBuffer(byteBuffer)
        val outputs = model.process(inputFeature0)
        val outputFeature0 = outputs.outputFeature0AsTensorBuffer
        val tab = outputFeature0.floatArray
        model.close()
        Log.d("Tab_test[0]", " "+ tab[0])
        Log.d("Tab_test[1]", " "+ tab[1])

Have this:

D/Tab_test[0]:  NaN
D/Tab_test[1]:  NaN

Anyone know where the problem could be? And how do I fix it?

It implements a different network and the type is DataType.UINT8 and here is DataType.FLOAT32 Could it be because of this?

Solution

its help, everything works correctly

val resizeBitmap: Bitmap = Bitmap.createScaledBitmap(bitmap, 150, 150, true)
        val model = com.example.iscanner.ml.Model.newInstance(context)

        val bytebuffer = ByteBuffer.allocateDirect(4*150*150*3)
        bytebuffer.order(ByteOrder.nativeOrder())
        val intValues  = IntArray(150*150)
        bitmap.getPixels(intValues,0,resizeBitmap.width,0,0,resizeBitmap.width,resizeBitmap.height)
        var pixel = 0
        for( i in 0 .. 149){
            for(j in 0..149){
                val tmpVal = intValues[pixel++]
                bytebuffer.putFloat(((tmpVal shr 16) and  0xFF)*(1.0f/1))
                bytebuffer.putFloat(((tmpVal shr 8) and  0xFF)*(1.0f/1))
                bytebuffer.putFloat((tmpVal and  0xFF)*(1.0f/1))
            }
        }
        val inputFeature0 = TensorBuffer.createFixedSize(intArrayOf(1, 150, 150, 3), DataType.FLOAT32)
        inputFeature0.loadBuffer(bytebuffer)
        val outputs = model.process(inputFeature0)
        val outputFeature0 = outputs.outputFeature0AsTensorBuffer
        val tab = outputFeature0.floatArray
        model.close()

Answered By - macekmacek