onnx2paddle报错TypeError: object of type 'NoneType' has no len() `

[merlinarer]

想把resnest的deepv3转成paddle的，op9的时候上采样层会报错，所以用了op11,但是onnx转paddle的时候就报错了
`TensorRT dynamic library (libnvinfer.so) that Paddle depends on is not configured correctly. (error code is libnvinfer.so: cannot open shared object file: No such file or directory)
Suggestions:

1. Check if TensorRT is installed correctly and its version is matched with paddlepaddle you installed.
2. Configure TensorRT dynamic library environment variables as follows:

• Linux: set LD_LIBRARY_PATH by export LD_LIBRARY_PATH=...
• Windows: set PATH by set PATH=XXX;paddle.__version__ = 1.8.5 Now translating model from onnx to paddle. model ir_version: 6, op version: 11 shape inferencing ... shape inferenced. Now, onnx2paddle support convert onnx model opset_verison [9],opset_verison of your onnx model is 11, automatically treated as op_set: 9. Total nodes: 3547 Nodes converting ... convert failed node:2742, op_type is Pad Traceback (most recent call last): File "/root/miniconda3/bin/x2paddle", line 33, in <module> sys.exit(load_entry_point('x2paddle==0.8.8', 'console_scripts', 'x2paddle')()) File "/root/miniconda3/lib/python3.8/site-packages/x2paddle/convert.py", line 282, in main onnx2paddle(args.model, args.save_dir, params_merge) File "/root/miniconda3/lib/python3.8/site-packages/x2paddle/convert.py", line 171, in onnx2paddle mapper = ONNXOpMapper(model) File "/root/miniconda3/lib/python3.8/site-packages/x2paddle/op_mapper/onnx2paddle/onnx_op_mapper.py", line 42, in __init__ func(node) File "/root/miniconda3/lib/python3.8/site-packages/x2paddle/op_mapper/onnx2paddle/opset9/opset.py", line 73, in run_mapping res = func(*args, **kwargs) File "/root/miniconda3/lib/python3.8/site-packages/x2paddle/op_mapper/onnx2paddle/opset9/opset.py", line 408, in Pad if len(pads) == 4: TypeError: object of type 'NoneType' has no len()
  请问应该怎么处理呢？

[Channingss]

@merlinarer 麻烦把模型发给我们分析一下，chen_lingchi@163.com