Yolov8 model conversion

HareshHaresh
edited March 26 in KL720 related discussion

I tried to convert the YOLOv8 model into .nef after optimizing the ONNX model. I performed the following steps:

bie_path = model_config.analysis(input_mapping, threads=4)

fixed_results = ktc.kneron_inference(input_mapping, bie_file=bie_path, input_names=input_names_onnx, platform=630)

I'm encountering an error, and I have attached a screenshot of it."

Could you please help me with this?


Screenshot (68).png


Comments

  • Maria ChenMaria Chen

    Hi Haresh,

    The error says, "Input name does not match," with the onnx input ({input_nodes}) and given np ({input_np.keys()}), so you might want to make sure that the order of the names are matching the order of inputs in pre_results:

    image.png

    The onnx input seems to be (['images', '/model.22/Constant_24_output_0', '/model.22/Constant_23_output_0', '/model.22/Constant_16_output_0', '/model.22/Constant_14_output_0', '/model.22/Constant_13_output_0']) and the given np is (dict_keys(['images'])).

    If possible, you could also provide us with your model, script, and images so we could take a look. Thanks!

  • HareshHaresh

    Hi, Maria


    I have resolve that issue, thanks for your valuable response. If any further issues I am facing then I will let you know.

The discussion has been closed due to inactivity. To continue with the topic, please feel free to post a new discussion.

© Kneron, Inc.