Hi, I read more article but i cannot found nothing for my scope. I export yolo8 for Edge tpu Google Coral but how can I use in python code for detect the object?
I try to execute:
yolo predict task=detect model=yolov8n_saved_model/yolov8n_full_integer_quant_edgetpu.tflite imgsz=224,128
but I have this error:
WARNING ⚠️ 'source' is missing. Using default 'source=/home/geoinference/yolo/myenv/lib/python3.8/site-packages/ultralytics/assets'.
Ultralytics YOLOv8.0.49 🚀 Python-3.8.10 torch-1.13.1+cu117 CPU
Loading yolov8n_saved_model/yolov8n_full_integer_quant_edgetpu.tflite for TensorFlow Lite Edge TPU inference...
Traceback (most recent call last):
File "/home/geoinference/yolo/myenv/bin/yolo", line 8, in <module>
sys.exit(entrypoint())
File "/home/geoinference/yolo/myenv/lib/python3.8/site-packages/ultralytics/yolo/cfg/__init__.py", line 312, in entrypoint
getattr(model, mode)(**overrides) # default args from model
File "/home/geoinference/yolo/myenv/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/geoinference/yolo/myenv/lib/python3.8/site-packages/ultralytics/yolo/engine/model.py", line 220, in predict
return self.predictor.predict_cli(source=source) if is_cli else self.predictor(source=source, stream=stream)
File "/home/geoinference/yolo/myenv/lib/python3.8/site-packages/ultralytics/yolo/engine/predictor.py", line 119, in predict_cli
for _ in gen: # running CLI inference without accumulating any outputs (do not modify)
File "/home/geoinference/yolo/myenv/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 43, in generator_context
response = gen.send(None)
File "/home/geoinference/yolo/myenv/lib/python3.8/site-packages/ultralytics/yolo/engine/predictor.py", line 172, in stream_inference
preds = self.model(im, augment=self.args.augment, visualize=visualize)
File "/home/geoinference/yolo/myenv/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/home/geoinference/yolo/myenv/lib/python3.8/site-packages/ultralytics/nn/autobackend.py", line 361, in forward
self.interpreter.set_tensor(input['index'], im)
File "/home/geoinference/yolo/myenv/lib/python3.8/site-packages/tflite_runtime/interpreter.py", line 572, in set_tensor
self._interpreter.SetTensor(tensor_index, value)
ValueError: Cannot set tensor: Got value of type FLOAT32 but expected type INT8 for input 0, name: inputs_0
Sentry is attempting to send 2 pending error messages
Thank’s for support.
Stefano