AM68A: Invalid model. The graph is not acyclic error when compiling a Custom Trained Model

https://github.com/TexasInstruments/edgeai-yolox.git 

And after that, I used onnxruntime to generate .onnx file from the .pth file. I still need to compile it to get the artifacts.

For this, I used Jupyter notebook given in the model evaluator in the Edge-AI Studio. I followed the steps in notebooks/custom-model-onnx.ipynb

When I upload my .onnx, follow the steps and run this bit:

so = rt.SessionOptions()
EP_list = ['TIDLCompilationProvider','CPUExecutionProvider']
sess = rt.InferenceSession(onnx_model_path ,providers=EP_list, provider_options=[compile_options, {}], sess_options=so)

input_details = sess.get_inputs()

for num in tqdm.trange(len(calib_images)):
output = list(sess.run(None, {input_details[0].name : preprocess_for_onnx_resent18v2(calib_images[num])}))[0]

-----------------------------

I get the error as;

---------------------------------------------------------------------------
Fail                                      Traceback (most recent call last)
<ipython-input-27-c8ebf5693570> in <module>
      1 so = rt.SessionOptions()
      2 EP_list = ['TIDLCompilationProvider','CPUExecutionProvider']
----> 3 sess = rt.InferenceSession(onnx_model_path ,providers=EP_list, provider_options=[compile_options, {}], sess_options=so)
      4 
      5 input_details = sess.get_inputs()

/usr/local/lib/python3.6/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py in __init__(self, path_or_bytes, sess_options, providers, provider_options)
    281 
    282         try:
--> 283             self._create_inference_session(providers, provider_options)
    284         except RuntimeError:
    285             if self._enable_fallback:

/usr/local/lib/python3.6/dist-packages/onnxruntime/capi/onnxruntime_inference_collection.py in _create_inference_session(self, providers, provider_options)
    313 
    314         # initialize the C++ InferenceSession
--> 315         sess.initialize_session(providers, provider_options)
    316 
    317         self._sess = sess

Fail: [ONNXRuntimeError] : 1 : FAIL : This is an invalid model. Error: the graph is not acyclic.
----------------------------------------------------

I am lost at what should I do at this point. Can you help? Do I have an easier way to generate the artifacts without having a linux pc?
Thanks,
Ibrahim