# Bug Report ### Is the issue related to model conversion? <!-- If the ONNX checker reports issues with this model then this is most probably related to the converter used to convert the original framework model to ONNX. Please create this bug in the appropriate converter's GitHub repo (pytorch, tensorflow-onnx, sklearn-onnx, keras-onnx, onnxmltools) to get the best help. --> ### Describe the bug <!-- Please describe the bug clearly and concisely --> Since `all([])` is always `True` passing empty list to `make_attribute` will be always list of ints https://github.com/onnx/onnx/blob/a02166572855083b3b6f5a329ba438f8cd8635f9/onnx/helper.py#L858-L860 ### System information <!-- - OS Platform and Distribution (*e.g. Linux Ubuntu 20.04*): - ONNX version (*e.g. 1.13*): - Python version: - GCC/Compiler version (if compiling from source): - CMake version: - Protobuf version: - Visual Studio version (if applicable):--> ### Reproduction instructions <!-- - Describe the code to reproduce the behavior. ``` import onnx model = onnx.load('model.onnx') ... ``` - Attach the ONNX model to the issue (where applicable)--> ```python onnx.helper.make_attribute("attr_name", []) # Always .type == INTS which isn't always expected ``` ### Expected behavior <!-- A clear and concise description of what you expected to happen. --> For empty list `make_attribute` method should fail due to type inference error or there should be an explicit typed `make_attribute` method ### Notes <!-- Any additional information -->