IndexError because pytorch does not support int32 for indexing like onnx

Been trying a bunch of things to solve this now but the error message isn’t very helpful. It just sounds like it’s just the input dtype that’s handled incorrectly.

  File "/home/richard/miniconda3/envs/3.9.13/lib/python3.9/site-packages/torch/fx/graph_module.py", line 630, in wrapped_call
    raise e.with_traceback(None)
IndexError: tensors used as indices must be long, byte or bool tensors

Here is the onnx file I’m trying to convert https://drive.google.com/file/d/1FX_D6dcYEoVssr-y29F5RLbhmhf4RmyZ/view?usp=sharing

It is supposed to take a tensor of type long. Here’s an example in json: https://drive.google.com/file/d/1yTSxwOY10g0cULEVt3KQZWSzziDpD8bC/view?usp=sharing

This is how I try to run it:

    model = torch.load(torch_path).eval().requires_grad_(False)

    tokens = torch.tensor(
        json.loads(Path(f"tests/{model_name}/tokens.json").read_text())
    ).long()
    text_encodings = torch.from_numpy(np.array(model(tokens)))

The onnx file works with onnxruntime and gives the correct result.

    tokens = np.array(
        json.loads(Path(f"tests/{model_name}/tokens.json").read_text())
    ).astype(np.int64)

    providers = ["CPUExecutionProvider"]
    m = rt.InferenceSession(onnx_path, providers=providers)
    text_encoding = m.run(output_names, dict(inputs=tokens))

Do you have any tips for what could be wrong?

[senysenyseny16]

Hi @samedii

Sorry for the wait, we will get back to this issue as soon as possible.

[samedii]

@senysenyseny16 Thank you! I had to give up eventually on fixing the ONNX file manually. At the moment I’m running the text encoder via ONNX because it’s not used as often as the image encoder (text-guided image generation) but it would be very nice if it wasn’t necessary.

The package is open source if you want to know what it would be used for: https://github.com/samedii/pytorch-zero-lit