Failed to load delegate from libedgetpu.so.1

[Demonytro]

(.venv) rpi5@raspberrypi:~/silva $ silvatpu -p det -m 240_yolov8n_full_integer_quant_edgetpu.tflite -i Working_Man_7.mp4 -z 192 -t 0.5
Loading 240_yolov8n_full_integer_quant_edgetpu.tflite for TensorFlow Lite Edge TPU inference...
Traceback (most recent call last):
File "/home/rpi5/silva/.venv/lib/python3.9/site-packages/tflite_runtime/interpreter.py", line 160, in load_delegate
delegate = Delegate(library, options)
File "/home/rpi5/silva/.venv/lib/python3.9/site-packages/tflite_runtime/interpreter.py", line 119, in init
raise ValueError(capture.message)
ValueError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/rpi5/silva/.venv/bin/silvatpu", line 8, in
sys.exit(silvatpu())
File "/home/rpi5/silva/.venv/lib/python3.9/site-packages/edge_tpu_silva/main.py", line 97, in silvatpu
for _, _ in outs:
File "/home/rpi5/silva/.venv/lib/python3.9/site-packages/edge_tpu_silva/silva/silva_detect.py", line 38, in process_detection
outs = model.predict(
File "/home/rpi5/silva/.venv/lib/python3.9/site-packages/ultralytics/engine/model.py", line 446, in predict
self.predictor.setup_model(model=self.model, verbose=is_cli)
File "/home/rpi5/silva/.venv/lib/python3.9/site-packages/ultralytics/engine/predictor.py", line 297, in setup_model
self.model = AutoBackend(
File "/home/rpi5/silva/.venv/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/rpi5/silva/.venv/lib/python3.9/site-packages/ultralytics/nn/autobackend.py", line 337, in init
interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)])
File "/home/rpi5/silva/.venv/lib/python3.9/site-packages/tflite_runtime/interpreter.py", line 162, in load_delegate
raise ValueError('Failed to load delegate from {}\n{}'.format(
ValueError: Failed to load delegate from libedgetpu.so.1

(.venv) rpi5@raspberrypi:~/silva $

[stefcarpi]

Hi!
After some problems in configuring the coral on a raspberrypi4 I tried your package @DAVIDNYARKO123 , to install all dependencies and run a model. I'm running python 3.9, and I'm using the process_detection function, but I get the same error as @Demonytro

Loading ../240_yolov8n_full_integer_quant_edgetpu.tflite for TensorFlow Lite Edge TPU inferen
ce...
Traceback (most recent call last):
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/tflite_runtime/interpreter.py", li
ne 160, in load_delegate
delegate = Delegate(library, options)
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/tflite_runtime/interpreter.py", li
ne 119, in init
raise ValueError(capture.message)
ValueError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "", line 17, in __PYTHON_EL_eval
File "/home/pi/traxer-testing/silvaprocess.py", line 9, in
for _, _ in outs:
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/edge_tpu_silva/silva/silva_detect.
py", line 38, in process_detection
outs = model.predict(
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/ultralytics/engine/model.py", line
446, in predict
self.predictor.setup_model(model=self.model, verbose=is_cli)
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/ultralytics/engine/predictor.py",
line 297, in setup_model
self.model = AutoBackend(
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/torch/utils/_contextlib.py", line
115, in decorate_context
return func(*args, **kwargs)
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/ultralytics/nn/autobackend.py", li
ne 337, in init
interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)])
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/tflite_runtime/interpreter.py", li
ne 162, in load_delegate
raise ValueError('Failed to load delegate from {}\n{}'.format(
ValueError: Failed to load delegate from libedgetpu.so.1

[holmesha]

getting the same error...cannot make this work using a live feed instead of an uploaded file...it was the freaking cord...

[NUB-DISTRAIT]

Hi!
After some problems in configuring the coral on a raspberrypi4 I tried your package @DAVIDNYARKO123 , to install all dependencies and run a model. I'm running python 3.9, and I'm using the process_detection function, but I get the same error as @Demonytro

Loading ../240_yolov8n_full_integer_quant_edgetpu.tflite for TensorFlow Lite Edge TPU inferen
ce...
Traceback (most recent call last):
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/tflite_runtime/interpreter.py", li
ne 160, in load_delegate
delegate = Delegate(library, options)
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/tflite_runtime/interpreter.py", li
ne 119, in init
raise ValueError(capture.message)
ValueError

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "", line 17, in __PYTHON_EL_eval
File "/home/pi/traxer-testing/silvaprocess.py", line 9, in
for _, _ in outs:
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/edge_tpu_silva/silva/silva_detect.
py", line 38, in process_detection
outs = model.predict(
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/ultralytics/engine/model.py", line
446, in predict
self.predictor.setup_model(model=self.model, verbose=is_cli)
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/ultralytics/engine/predictor.py",
line 297, in setup_model
self.model = AutoBackend(
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/torch/utils/_contextlib.py", line
115, in decorate_context
return func(*args, **kwargs)
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/ultralytics/nn/autobackend.py", li
ne 337, in init
interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)])
File "/home/pi/.pyenvs/silva/lib/python3.9/site-packages/tflite_runtime/interpreter.py", li
ne 162, in load_delegate
raise ValueError('Failed to load delegate from {}\n{}'.format(
ValueError: Failed to load delegate from libedgetpu.so.1

Same issue "ValueError: Failed to load delegate from libedgetpu.so.1" encountered.
@DAVIDNYARKO123 Kindly guide us through.

[NUB-DISTRAIT]

Found it: #3