# Test TensorFlow Lite using label image

Source: [https://docs.qualcomm.com/doc/80-88500-3/topic/68_Test_TFLite_using_label_image.html](https://docs.qualcomm.com/doc/80-88500-3/topic/68_Test_TFLite_using_label_image.html)

1. Run  `adb shell mkdir /data/tf `.
2. - For Linux Ubuntu,

Get the model and the label file `use wget`
        [https://storage.googleapis.com/download.tensorflow.org/models/tflite/mobilenet_v1_224_android_quant_2017_11_08.zip](https://storage.googleapis.com/download.tensorflow.org/models/tflite/mobilenet_v1_224_android_quant_2017_11_08.zip)
    - For Linux Embedded:
Note: The model is executed on CPU, as the accelerator support is
              removed.
3. Run unzip mobilenet\_v1\_224\_android\_quant\_2017\_11\_08.zip
4. Run `adb push mobilenet_quant_v1_224.tflite /data/tf/ `.
5. Run `adb push labels.txt /data/tf/`.
6. Run get the sample image `use wget`: [https://github.com/tensorflow/tensorflow/raw/master/tensorflow/lite/examples/label_image/testdata/grace_hopper.bmp](https://github.com/tensorflow/tensorflow/raw/master/tensorflow/lite/examples/label_image/testdata/grace_hopper.bmp).
7. Run `adb push grace_hopper.bmp /data/tf/ `
8. Run `adb shell`
9. Go to `/data/tf/: run cd /data/tf/`
10. Run the command `label_image -a 1 -m mobilenet_quant_v1_224.tflite -c 10 -l
          labels.txt`.

- **[Set hardware acceleration, multiple models, and their priorities in label image](https://docs.qualcomm.com/doc/80-88500-3/topic/69_Set_hardware_acceleration__multiple_models__and_their_priorities_in_label_image.html)**

**Parent Topic:** [Configure AI/ML modules](https://docs.qualcomm.com/doc/80-88500-3/topic/66_Configure_AI_ML_modules.html)

Last Published: Sep 26, 2023

[Previous Topic
Configure AI/ML modules](https://docs.qualcomm.com/bundle/publicresource/80-88500-3/topics/66_Configure_AI_ML_modules.md) [Next Topic
Set hardware acceleration, multiple models, and their priorities in label image](https://docs.qualcomm.com/bundle/publicresource/80-88500-3/topics/69_Set_hardware_acceleration__multiple_models__and_their_priorities_in_label_image.md)