When In try to create nef file using LittleNet.onnx model for kl720 , it fails
When In try to create nef file using LittleNet.onnx model for kl720 , it fails but I tried creating for kl520 and nef file is created properly
Below is error log for KL720
(base) root@edf75761b2af:/workspace# python examples/LittleNet/python_api_workflow.py
/workspace/miniconda/lib/python3.7/site-packages/numpy/__init__.py:156: UserWarning: mkl-service package failed to import, therefore Intel(R) MKL initialization ensuring its correct out-of-the box operation under condition when Gnu OpenMP had already been loaded by Python process is not assured. Please install mkl-service package, see http://github.com/IntelPython/mkl-service
from . import _distributor_init
Using TensorFlow backend.
running compiler and ipEvaluator...
Compilation and IP Evaluation finished.
Section 3 E2E simulator result:
[array([[[[-12.30762 , 8.2846937]]]])]
Segmentation fault (core dumped)=======================================]100% 0.003000s
The only change I did is change ktc.ModelConfig ...Below is the change
km = ktc.ModelConfig(1001, "0001", "720", onnx_path="/workspace/examples/LittleNet/LittleNet.onnx")
Please share how to fix this error
Comments
For KL720 BIE simulator need extra parameter "platform=720"
fixed_results = ktc.kneron_inference(input_data, bie_file=bie_path, input_names=["data_out"], platform=720, radix=radix)
its working now, thanks
Can you please share how I can write the inference code for testing model_720.nef in kl720