Fail to convert resnet101 from PyTorch to IR

[Ivanfangsc]

Platform (like ubuntu 16.04/win10): Ubuntu 20.04 and Windows 10

Python version: 3.9.7

Source framework with version (like Tensorflow 1.4.1 with GPU): PyTorch 1.9.1 CPU only

Destination framework with version (like CNTK 2.3 with GPU): IR

Pre-trained model path (webpath or webdisk path): mmdownload -f pytorch -n resnet101

Running scripts: mmtoir -f pytorch -n imagenet_resnet101.pth -d resnet --inputShape 3,224,224

Error reported:

Traceback (most recent call last):
 File "mmdnn/conversion/_script/convertToIR.py", line 202, in <module>
   _main()
 File "mmdnn/conversion/_script/convertToIR.py", line 197, in _main
   ret = _convert(args)
 File "/mmdnn/conversion/_script/convertToIR.py", line 97, in _convert
   parser = PytorchParser151(model, inputshape[0])
 File "mmdnn/conversion/pytorch/pytorch_parser.py", line 533, in __init__
   self.build_graph(input_shape)
 File "mmdnn/conversion/pytorch/pytorch_parser.py", line 92, in build_graph
   self.pytorch_graph.build(self.input_shape)
 File "mmdnn/conversion/pytorch/pytorch_graph.py", line 135, in build
   output_shape = [int(x.replace('!', '')) for x in output_shape_str[1].split(',')]
 File "mmdnn/conversion/pytorch/pytorch_graph.py", line 135, in <listcomp>
   output_shape = [int(x.replace('!', '')) for x in output_shape_str[1].split(',')]
ValueError: invalid literal for int() with base 10: ' strides'