使用官方提供的pytorch的云开发环境把自己的模型转成离线模型时出现报错

报错信息如下：

  File "/networks/backbones/ResNetvd.py", line 201, in forward

    x = self.conv1(x)

  File "/opt/cambricon/pytorch/src/catch/venv/pytorch/lib/python3.5/site-packages/torch/nn/modules/module.py", line 539, in __call__

    result = self._slow_forward(*input, **kwargs)

  File "/opt/cambricon/pytorch/src/catch/venv/pytorch/lib/python3.5/site-packages/torch/nn/modules/module.py", line 525, in _slow_forward

    result = self.forward(*input, **kwargs)

  File "/opt/cambricon/pytorch/src/catch/venv/pytorch/lib/python3.5/site-packages/torch/nn/modules/container.py", line 92, in forward

    input = module(input)

  File "/opt/cambricon/pytorch/src/catch/venv/pytorch/lib/python3.5/site-packages/torch/nn/modules/module.py", line 539, in __call__

    result = self._slow_forward(*input, **kwargs)

  File "/opt/cambricon/pytorch/src/catch/venv/pytorch/lib/python3.5/site-packages/torch/nn/modules/module.py", line 525, in _slow_forward

    result = self.forward(*input, **kwargs)

  File "/home/PytorchOCR-master/torchocr/networks/backbones/DetResNetvd.py", line 29, in forward

    x = self.conv(x)

  File "/opt/cambricon/pytorch/src/catch/venv/pytorch/lib/python3.5/site-packages/torch/nn/modules/module.py", line 539, in __call__

    result = self._slow_forward(*input, **kwargs)

  File "/opt/cambricon/pytorch/src/catch/venv/pytorch/lib/python3.5/site-packages/torch/nn/modules/module.py", line 525, in _slow_forward

    result = self.forward(*input, **kwargs)

  File "/opt/cambricon/pytorch/src/catch/venv/pytorch/lib/python3.5/site-packages/torch/nn/modules/conv.py", line 345, in forward

    return self.conv2d_forward(input, self.weight)

  File "/opt/cambricon/pytorch/src/catch/venv/pytorch/lib/python3.5/site-packages/torch/nn/modules/conv.py", line 342, in conv2d_forward

    self.padding, self.dilation, self.groups)

RuntimeError: To do for CPU

导出离线模型的代码如下：

model = build_model(cfg[])
state_dict = {}
kv ckpt[].items():
    state_dict[k.replace()] = v
model.load_state_dict(state_dict)
device = torch.device()
model.eval()
torch_mlu
torch_mlu.core.mlu_model ctnet = model.float()

example_mlu = torch.randn(=torch.float)
randn_mlu = torch.randn(=torch.float)

ct.set_core_number()
ct.set_core_version()
ct.set_device(-)
ct.save_as_cambricon(model_name)
net_traced = torch.jit.trace(net.to(ct.mlu_device())randn_mlu.to(ct.mlu_device())=)

net_traced(example_mlu.to(ct.mlu_device()))

ct.save_as_cambricon()