Created by: amandazw

请问各位有没有遇到这样的问题，原来的paddleOCR的模型支持不定长输入，为32的倍数即可。转为onnx后输入固化了：如下onnxruntime.capi.onnxruntime_pybind11_state.InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Got invalid dimensions for input: image for the following indices index: 2 Got: 960 Expected: 640 index: 3 Got: 480 Expected: 640 Please fix either the inputs or the model. 必须要640*640 请教一下如何修改能让模型预测接受可变长度序列呢