Can the virtual machine executor support inference on dynamic shape of OCR model?

Hi everyone, I observe that tvm only support transform on Oneflow or Onnx models with dynamic shape. I have tried to tranform so many OCR Onnx models to relay but all failed because the presence of the LSTM operator I guess. Fortunately, I succeed to tranform a Onnx model named “ch_PP-OCRv3_rec_infer”, which can be converted from the Paddle model via the paddle2onnx tool. Then, I load this model to create a virtual machine executor by using the relay.build_module.create_executor func. But, there still exists a problem called “RuntimeError : Invalid type of axis: <class ‘tvm.tir.expr.add’>”, as shown below.

Well, I can provide the code and data for you, which can be downloaded from Google Drive or Baidu Disk as follows. We build and run it in 0.10.0 TVM with clang+llvm-14.0.0-x86_64-linux-gnu-ubuntu-18.04. Is it the conv2d operator problem ? or the virtual machine executor are not friendly to the dynamic shape tensor?

Google Drive ——

Baidu Disk —— url: password:FT12