classify_image.py RuntimeError: Failed to allocate tensors.

[DrChungAlbert]

Hello Charles, The Requirements Any Linux computer with a USB port Debian 6.0 or higher, or any derivative thereof (such as Ubuntu 10.0+) System architecture of either x86_64 or ARM64 with ARMv8 instruction set

While I connect Edge tpu usb dongle to JETSON TX2 USB3 port, installed edgetpu_api and cd /usr/local/lib/python3.5/dist-packages/edgetpu/demo type python3 classify_image.py --model /home/nvidia/Downloads/mobilenet_v2_1.0_224_inat_bird_quant_edgetpu.tflite --label /home/nvidia/Downloads/inat_bird_labels.txt --image /home/nvidia/Downloads/parrot.jpg

I got the error below:

Traceback (most recent call last): File "classify_image.py", line 67, in <module> main() File "classify_image.py", line 58, in main engine = ClassificationEngine(args.model) File "/usr/local/lib/python3.5/dist-packages/edgetpu/classification/engine.py", line 38, in __init__ super().__init__(model_path) File "/usr/local/lib/python3.5/dist-packages/edgetpu/swig/edgetpu_cpp_wrapper.py", line 300, in __init__ this = _edgetpu_cpp_wrapper.new_BasicEngine(*args) RuntimeError: Failed to allocate tensors.

Can you give me some comment about it ?

[Namburger]

@DrChungAlbert Hi Chung, I suggest checking edgetpu run time version you have installed. The current version is 13, you can check with:

$ python3 -c "import edgetpu.basic.edgetpu_utils; print(edgetpu.basic.edgetpu_utils.GetRuntimeVersion())"

The nano should works fine as I've heard multiple success stories!