Caused by: java.lang.IllegalArgumentException: Cannot convert between a TensorFlowLite tensor with type UINT8 and a Java object of type [[F (which is compatible with the TensorFlowLite type FLOAT32).

[vishal-patel17]

Hello, I am facing this issue when trying to run the code:

var imageBytes = (await rootBundle.load(image.path)).buffer;
    img.Image oriImage = img.decodeJpg(imageBytes.asUint8List());
    img.Image resizedImage = img.copyResize(oriImage, height: 112, width: 112);
    var recognitions = await Tflite.runModelOnBinary(
      binary: imageToByteListFloat32(resizedImage, 112, 127.5, 127.5),
      numResults: 6,
      threshold: 0.05,
    );
  }

  Uint8List imageToByteListFloat32(
      img.Image image, int inputSize, double mean, double std) {
    var convertedBytes = Float32List(1 * inputSize * inputSize * 3);
    var buffer = Float32List.view(convertedBytes.buffer);
    int pixelIndex = 0;
    for (var i = 0; i < inputSize; i++) {
      for (var j = 0; j < inputSize; j++) {
        var pixel = image.getPixel(j, i);
        buffer[pixelIndex++] = (img.getRed(pixel) - mean) / std;
        buffer[pixelIndex++] = (img.getGreen(pixel) - mean) / std;
        buffer[pixelIndex++] = (img.getBlue(pixel) - mean) / std;
      }
    }
    return convertedBytes.buffer.asUint8List();
}

I am using model, generated using AutoML in firebase.

Error is as follows:
Caused by: java.lang.IllegalArgumentException: Cannot convert between a TensorFlowLite tensor with type UINT8 and a Java object of type [[F (which is compatible with the TensorFlowLite type FLOAT32).

[vishal-patel17]

Also facing the same issue upon using:
Tflite.runModelOnImage(path: image.path);

[shaqian]

Hi Vishal,

Can you check if the error happens when feeding input tensor or output tensor?

You can set a breakpoint at the following line. If you are able to get here, the error is because the output tensor is of type uint8 but labelProb is float32.
https://github.com/shaqian/flutter_tflite/blob/master/android/src/main/java/sq/flutter/tflite/TflitePlugin.java#L452

The definition of labelProb:
https://github.com/shaqian/flutter_tflite/blob/master/android/src/main/java/sq/flutter/tflite/TflitePlugin.java#L55

Output of image classification is usually float number between 0 and 1. You may need to check how the model is trained.

Thanks,
Qian

[shaqian]

I'm archiving this thread. Feel free to reopen if you have further questions.

Thanks,
Qian

[PepeExpress]

Im facing same issue both when using Tflite.runModelOnImage(path: image.path); and await Tflite.runModelOnBinary(binary:binary);

I attach an image with model properties of the tflite model I'm using.

[zoraiz-WOL]

use this code to train you custom model

import os

import numpy as np

import tensorflow as tf
assert tf.version.startswith('2')

from tflite_model_maker import model_spec
from tflite_model_maker import image_classifier
from tflite_model_maker.config import ExportFormat
from tflite_model_maker.config import QuantizationConfig
from tflite_model_maker.image_classifier import DataLoader

import matplotlib.pyplot as plt

#to unzip a rar
!unzip path-of-zip-file -d path-to-save-extract-file

data = DataLoader.from_folder('path-of-custom-folder')
train_data, rest_data = data.split(0.8)
validation_data, test_data = rest_data.split(0.5)
model = image_classifier.create(train_data, validation_data=validation_data)
loss, accuracy = model.evaluate(test_data)
config = QuantizationConfig.for_float16()
model.export(export_dir='path-to-save-model', quantization_config=config,export_format=ExportFormat.TFLITE)
model.export(export_dir='path-to-save-label', quantization_config=config,export_format=ExportFormat.LABEL)

[2shrestha22]

Anyone having this issue should export model with float16 quantization.

config = QuantizationConfig.for_float16()
model.export(export_dir='.', tflite_filename='model_fp16.tflite', quantization_config=config)

[elkhalifte]

inside your code change the output from float to byte and finally get the float value from byte data.
before:

float[][] labelProb = new float[1][labels.size()];
 for (int i = 0; i < labels.size(); ++i) { 
float confidence = labelProb[0][i]; 
} 

after:

byte[][] labelProb = new byte[1][labels.size()];
 for (int i = 0; i < labels.size(); ++i) {
 float confidence = (float)labelProb[0][i];
 }

i might send a pull request for this.

[umang752]

I am getting this error,

Cannot copy to a TensorFlowLite tensor (input_1) with 602112 bytes from a Java Buffer with 150528 bytes.

`import os

import numpy as np

import tensorflow as tf

from tflite_model_maker import model_spec
from tflite_model_maker import image_classifier
from tflite_model_maker.config import ExportFormat
from tflite_model_maker.config import QuantizationConfig
from tflite_model_maker.image_classifier import DataLoader

EXPORT_DIR = '/home/ailabs/work/TFLite/Model/'
CAR_POTO_DIR = '/home/ailabs/work/TFLite/car_photos/'
EPOCHS = 1

data = DataLoader.from_folder(CAR_POTO_DIR)

train_data, rest_data = data.split(0.8)
validation_data, test_data = rest_data.split(0.5)

model = image_classifier.create(train_data, epochs=EPOCHS, validation_data=validation_data)

loss, accuracy = model.evaluate(test_data)

config = QuantizationConfig.for_float16()

model.export(export_dir=EXPORT_DIR,tflite_filename='coco_ssd_mobilenet_v1_1.0_quant.tflite',quantization_config=config,export_format=ExportFormat.TFLITE)
model.export(export_dir=EXPORT_DIR,tflite_filename='coco_ssd_mobilenet_v1_1.0_labels.txt',export_format=ExportFormat.LABEL)
`