Encounter bad_function_call during compiler.compile() with a customized transformer model

[Ruofeng-Wang]

Describe the bug A clear and concise description of what the bug is. I am working on a transformer model in pytorch. After cleaning it up, I converted to onnx format and pass the onnx model to https://github.com/kendryte/nncase/blob/release/1.0/docs/USAGE_ZH.md#%E7%BC%96%E8%AF%91float32-onnx%E6%A8%A1%E5%9E%8B suggested as an onnx compile example.

To Reproduce Command line or scripts to reproduce the behavior: python k510_compile_script.py --target k510 --dump_dir temp --onnx model.onnx --kmodel transformer.kmodel

Expected behavior A clear and concise description of what you expected to happen.

Origin model and code If applicable, add orgin model and code to help explain your problem.

The k510_compile_script.py and model.onnx are all in this repo https://github.com/Ruofeng-Wang/diffusion_policy/tree/main

Environment (please complete the following information):

• OS: [e.g. Ubuntu18.04]
• nncase version [e.g. v1.0.0.dev24]
• DL Framework [e.g. TensorFlow 2.5.0]

ubuntu20

Additional context

Add any other context about the problem here.

[Ruofeng-Wang]

original pytorch model: https://github.com/T-K-233/Diffusion-Benchmark/tree/main model.py