After I used this command to save tf model for tflite converting python save_model.py --weights ./data/yolov4.weights --output ./checkpoints/yolov4-416 --input_size 416 --model yolov4 --framework tflite
And this command converts yolov4 quantize float16 python convert_tflite.py --weights ./checkpoints/yolov4-416 --output ./checkpoints/yolov4-416-fp16.tflite --quantize_mode float16
I put that model in assets folder, I modify the path in java files fpr the model and when I launch the app I got these errors
E/QT: [QT]file does not exist
E/MiuiMultiWindowUtils: initFreeFormResolutionArgs failed, device is eos
E/ion: ioctl c0044901 failed with code -1: Invalid argument
E/AndroidRuntime: FATAL EXCEPTION: main
Process: org.tensorflow.lite.examples.detection, PID: 29232
java.lang.RuntimeException: Unable to start activity ComponentInfo{org.tensorflow.lite.examples.detection/org.tensorflow.lite.examples.detection.MainActivity}: java.lang.RuntimeException: java.lang.IllegalArgumentException: Internal error: Cannot create interpreter: Op builtin_code out of range: 127. Are you using old TFLite binary with newer model?
Registration failed.
Caused by: java.lang.RuntimeException: java.lang.IllegalArgumentException: Internal error: Cannot create interpreter: Op builtin_code out of range: 127. Are you using old TFLite binary with newer model?
Registration failed.
Caused by: java.lang.IllegalArgumentException: Internal error: Cannot create interpreter: Op builtin_code out of range: 127. Are you using old TFLite binary with newer model?
Registration failed.
Do you know what is the issue with the converted model and how to fix it? Thank in advance!
Hello. I downloaded yolov4.weights from the official https://github.com/AlexeyAB/darknet
After I used this command to save tf model for tflite converting python save_model.py --weights ./data/yolov4.weights --output ./checkpoints/yolov4-416 --input_size 416 --model yolov4 --framework tflite
And this command converts yolov4 quantize float16 python convert_tflite.py --weights ./checkpoints/yolov4-416 --output ./checkpoints/yolov4-416-fp16.tflite --quantize_mode float16
I put that model in assets folder, I modify the path in java files fpr the model and when I launch the app I got these errors
E/QT: [QT]file does not exist E/MiuiMultiWindowUtils: initFreeFormResolutionArgs failed, device is eos E/ion: ioctl c0044901 failed with code -1: Invalid argument E/AndroidRuntime: FATAL EXCEPTION: main Process: org.tensorflow.lite.examples.detection, PID: 29232 java.lang.RuntimeException: Unable to start activity ComponentInfo{org.tensorflow.lite.examples.detection/org.tensorflow.lite.examples.detection.MainActivity}: java.lang.RuntimeException: java.lang.IllegalArgumentException: Internal error: Cannot create interpreter: Op builtin_code out of range: 127. Are you using old TFLite binary with newer model? Registration failed. Caused by: java.lang.RuntimeException: java.lang.IllegalArgumentException: Internal error: Cannot create interpreter: Op builtin_code out of range: 127. Are you using old TFLite binary with newer model? Registration failed. Caused by: java.lang.IllegalArgumentException: Internal error: Cannot create interpreter: Op builtin_code out of range: 127. Are you using old TFLite binary with newer model? Registration failed.
Do you know what is the issue with the converted model and how to fix it? Thank in advance!