Deployment problem. (torch.jit.script)

[JANGSOONMYUN]

I am trying to deploy the project for C++ but it doesn't work.

I just put the jit function in train.py

    model = Model(opt)
    my_module = torch.jit.script(model)
    my_module.save("my_module.pt")

Traceback (most recent call last): File "train.py", line 352, in train(opt) File "train.py", line 64, in train my_module = torch.jit.script(model) File "/home/contrel/anaconda3/envs/torch/lib/python3.7/site-packages/torch/jit/_script.py", line 1287, in script obj, torch.jit._recursive.infer_methods_to_compile File "/home/contrel/anaconda3/envs/torch/lib/python3.7/site-packages/torch/jit/_recursive.py", line 477, in create_script_module return create_script_module_impl(nn_module, concrete_type, stubs_fn) File "/home/contrel/anaconda3/envs/torch/lib/python3.7/site-packages/torch/jit/_recursive.py", line 539, in create_script_module_impl script_module = torch.jit.RecursiveScriptModule._construct(cpp_module, init_fn) File "/home/contrel/anaconda3/envs/torch/lib/python3.7/site-packages/torch/jit/_script.py", line 615, in _construct init_fn(script_module) File "/home/contrel/anaconda3/envs/torch/lib/python3.7/site-packages/torch/jit/_recursive.py", line 517, in init_fn scripted = create_script_module_impl(orig_value, sub_concrete_type, stubs_fn) File "/home/contrel/anaconda3/envs/torch/lib/python3.7/site-packages/torch/jit/_recursive.py", line 543, in create_script_module_impl create_methods_and_properties_from_stubs(concrete_type, method_stubs, property_stubs) File "/home/contrel/anaconda3/envs/torch/lib/python3.7/site-packages/torch/jit/_recursive.py", line 394, in create_methods_and_properties_from_stubs concrete_type._create_methods_and_properties(property_defs, property_rcbs, method_defs, method_rcbs, method_defaults) RuntimeError:

adaptive_avg_pool2d(Tensor input, int[2] output_size) -> Tensor: Expected a value of type 'List[int]' for argument 'output_size' but instead found type 'Tuple[NoneType, int]'. : File "/home/contrel/anaconda3/envs/torch/lib/python3.7/site-packages/torch/nn/modules/pooling.py", line 1184 def forward(self, input: Tensor) -> Tensor: return F.adaptive_avg_pool2d(input, self.output_size) ~~~~~~~~~~~~~~~~~~~~~ <--- HERE

Please help me to solve this.