search

google-coral / pycoral

Python API for ML inferencing and transfer-learning on Coral devices
https://coral.ai
Apache License 2.0
351 stars 145 forks source link

Coral Mini Pycoral example error #28

Closed SunBeenMoon closed 3 years ago

SunBeenMoon commented 3 years ago

Hardware : Google Coral Board Mini Host Computer : RPI 4

I'm just testing the Coral board. An error occurred at the beginning part as shown in the picture below. image

I got the error code `mendel@undefined-orange:~/coral/pycoral$ python3 examples/classify_image.py \

--model test_data/mobilenet_v2_1.0_224_inat_bird_quant_edgetpu.tflite \ --labels test_data/inat_bird_labels.txt \ --input test_data/parrot.jpg Traceback (most recent call last): File "examples/classify_image.py", line 84, in main() File "examples/classify_image.py", line 62, in main interpreter.allocate_tensors() File "/home/mendel/.local/lib/python3.7/site-packages/tflite_runtime/interpreter.py", line 242, in allocate_tensors return self._interpreter.AllocateTensors() File "/home/mendel/.local/lib/python3.7/site-packages/tflite_runtime/interpreter_wrapper.py", line 115, in AllocateTensors return _interpreter_wrapper.InterpreterWrapper_AllocateTensors(self) RuntimeError: Internal: Unsupported data type in custom op handler: 0Node number 1 (EdgeTpuDelegateForCustomOp) failed to prepare.`

Errors continue to occur in the same interpreter part.

I need help.

Regards, SunBeenMoon

manoj7410 commented 3 years ago

Just for the record. This got resolved by reflashing the board.

SunBeenMoon commented 3 years ago

Thanks to reply @manoj7410

I solved this problem with reflashing the board with option -H bash flash.sh -H

ergoego commented 2 years ago

This exact same thing is happening for me as well, but on a raspberry pi 4. Is there a way to flash he USB Accelerator or do I need to flash my raspberry pi and start from scratch?