Function export_onnx_model

detectron2/export/api.py:165–184

Export a detectron2 model to ONNX format. Note that the exported model contains custom ops only available in caffe2, therefore it cannot be directly executed by other runtime. Post-processing or transformation passes may be applied on the model to accommodate different runtimes, but

(cfg, model, inputs)

def export_onnx_model(cfg, model, inputs):
    """
    Export a detectron2 model to ONNX format.
    Note that the exported model contains custom ops only available in caffe2, therefore it
    cannot be directly executed by other runtime. Post-processing or transformation passes
    may be applied on the model to accommodate different runtimes, but we currently do not
    provide support for them.

    Args:
        cfg (CfgNode): a detectron2 config, with extra export-related options
            added by :func:`add_export_config`.
        model (nn.Module): a model built by
            :func:`detectron2.modeling.build_model`.
            It will be modified by this function.
        inputs: sample inputs that the given model takes for inference.
            Will be used to trace the model.
    Returns:
        onnx.ModelProto: an onnx model.
    """
    return Caffe2Tracer(cfg, model, inputs).export_onnx()


class Caffe2Model(nn.Module):