Created by: jessionlin

when I run x2paddle , I got the following error: Traceback (most recent call last): File "/home/jxlin/anaconda3/envs/onnx2paddle/bin/x2paddle", line 11, in load_entry_point('x2paddle==0.7.1', 'console_scripts', 'x2paddle')() File "/home/jxlin/anaconda3/envs/onnx2paddle/lib/python3.6/site-packages/x2paddle-0.7.1-py3.6.egg/x2paddle/convert.py", line 251, in main onnx2paddle(args.model, args.save_dir, params_merge) File "/home/jxlin/anaconda3/envs/onnx2paddle/lib/python3.6/site-packages/x2paddle-0.7.1-py3.6.egg/x2paddle/convert.py", line 172, in onnx2paddle model = ONNXDecoder(model_path) File "/home/jxlin/anaconda3/envs/onnx2paddle/lib/python3.6/site-packages/x2paddle-0.7.1-py3.6.egg/x2paddle/decoder/onnx_decoder.py", line 324, in init check_model(model) File "/home/jxlin/anaconda3/envs/onnx2paddle/lib/python3.6/site-packages/onnx/checker.py", line 91, in check_model C.check_model(model.SerializeToString()) onnx.onnx_cpp2py_export.checker.ValidationError: No Op registered for Einsum with domain_version of 12

==> Context: Bad node spec: input: "177" input: "181" output: "183" name: "Einsum_148" op_type: "Einsum" attribute { name: "equation" s: "bfnd,ndh->bfh" type: STRING }

environment : python: 3.6 torch 1.5.0+cu92 torchvision 0.6.0+cu92 paddlepaddle 1.8.1 onnx 1.6.0 onnxruntime 1.0.0 opset_version 12