Invalid: Protobuf parsing failed?

[jryebread]

Hi when I run it get this error, any idea what could be wrong?

GPU: A10G 24GB VRAM

  return torch._C._cuda_getDeviceCount() > 0
Traceback (most recent call last):
  File "/home/ubuntu/hallo-webui/scripts/inference.py", line 424, in <module>
    inference_process(
  File "/home/ubuntu/hallo-webui/scripts/inference.py", line 181, in inference_process
    with ImageProcessor(img_size, face_analysis_model_path) as image_processor:
  File "/home/ubuntu/hallo-webui/hallo/datasets/image_processor.py", line 97, in __init__
    self.face_analysis = FaceAnalysis(
  File "/home/ubuntu/hallo-webui/venv/lib/python3.10/site-packages/insightface/app/face_analysis.py", line 31, in __init__
    model = model_zoo.get_model(onnx_file, **kwargs)
  File "/home/ubuntu/hallo-webui/venv/lib/python3.10/site-packages/insightface/model_zoo/model_zoo.py", line 96, in get_model
    model = router.get_model(providers=providers, provider_options=provider_options)
  File "/home/ubuntu/hallo-webui/venv/lib/python3.10/site-packages/insightface/model_zoo/model_zoo.py", line 40, in get_model
    session = PickableInferenceSession(self.onnx_file, **kwargs)
  File "/home/ubuntu/hallo-webui/venv/lib/python3.10/site-packages/insightface/model_zoo/model_zoo.py", line 25, in __init__
    super().__init__(model_path, **kwargs)
  File "/home/ubuntu/hallo-webui/venv/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 419, in __init__
    self._create_inference_session(providers, provider_options, disabled_optimizers)
  File "/home/ubuntu/hallo-webui/venv/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 472, in _create_inference_session
    sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model)
onnxruntime.capi.onnxruntime_pybind11_state.InvalidProtobuf: [ONNXRuntimeError] : 7 : INVALID_PROTOBUF : Load model from ./pretrained_models/face_analysis/models/1k3d68.onnx failed:Protobuf parsing failed.```

[xumingw]

Could you check your package versions and models sha256sum?

[xingdi1990]

same here

[SystemR]

I got this problem earlier and realized I don't have git lfs installed in the machine I was trying this project out.

Browse through the repo here https://huggingface.co/fudan-generative-ai/hallo/tree/main and see if the sha256 checksum matches with the ones in your machine.

[AricGamma]

Since there has been no further feedback, this issue will be closed. If needed, please reopen it.