Using HailoDFC and HailoModelZoo to compile ONNX model to HEF model costs 2 hours

[Erez]

Check this thread

Failing to compile onnx to hef

If you are able to train a model using your GPU, but not to optimize the model when running Hailo DFC, the issue is likely a mismatch of the CUDA/CUDNN and driver version with respect to the Tensorflow version used by the DFC. In fact, the DFC uses Tensorflow (version 2.12.0 for DFC 3.30) as backend, which has its own requirements (Build from source  |  TensorFlow). When using the Docker, you are sure that you have the right CUDA/CUDNN dependencies. If you still have the issue, you can try the …

Are you sure that you have GPU available?
In addition, are you using Docker based solution?

I’ve compiling onnx to have without --performance for around 20-30 mins.

With the performance flag is can be up to 5 hours.