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.
Google Drive ——
Baidu Disk —— url：https://pan.baidu.com/s/1ua52_lB3vu180d9dxn6gOA password：FT12