CODEWITHSUNDEEP
pythontensorflowtensorflow-litegoogle-coral
mevada.ravikumar
mevada.ravikumar

Reputation: 109

RuntimeError: Mmap of '/home/pi/object-detector/model' failed

I am using Raspberry pi 4 Model B, armv7l, with Raspbian stretch. I am having one 'mobilenet_v2_1.0_224_quant_edgetpu.tflite' model which I want to run with the google coral edge TPU. When I am trying to run the model it fails. I am using a standard Raspberry Pi V2 camera.

What can be the reason (not enough memory, TPU is damaged, the model is not prepared properly )? How can I get to know the edge TPU is working or not? How can I fix it?

Her is the traceback call:

 pi@raspberrypi:~/object-detector $ python3 detect_object_video_edge.py --model  
/home/pi/object-mask-detector/model --labels /home/pi/object-detector/model/object_labels.txt
[INFO] parsing class labels...
[INFO] loading Coral model...
Traceback (most recent call last):
  File "detect_object_video_edge.py", line 29, in <module>
model = DetectionEngine(args["model"])
  File "/usr/lib/python3/dist-packages/edgetpu/detection/engine.py", line 73, in __init__
super().__init__(model_path)
  File "/usr/lib/python3/dist-packages/edgetpu/basic/basic_engine.py", line 92, in __init__
    self._engine = BasicEnginePythonWrapper.CreateFromFile(model_path)
RuntimeError: Mmap of '/home/pi/object-detector/model' failed.

Upvotes: 0

Views: 560

Answers (2)

Nam Vu
Nam Vu

Reputation: 1757

--model /home/pi/object-mask-detector/model

and 

RuntimeError: Mmap of '/home/pi/object-detector/model' failed.

suggested that you are giving the api a directory, not a model.

Upvotes: 1

CristiC777
CristiC777

Reputation: 481

we can't guess your configuration

follow this tutorial..

Look here : github.com/EdjeElectronics/TensorFlow-Object-Detection

Upvotes: 0

Related Questions