AssertionError: Torch not compiled with CUDA enabled in PyTorch - pytorch

Question

I've created new environment using Anconda and tried to run my model which is built on Pytorch. But, I am having troudlbe with AssertionError. Here is my CUDA version with nvcc --version command.
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2021 NVIDIA Corporation
Built on Sun_Mar_21_19:24:09_Pacific_Daylight_Time_2021
Cuda compilation tools, release 11.3, V11.3.58
Build cuda_11.3.r11.3/compiler.29745058_0
and, I've installed Pytorch following the link https://pytorch.org/get-started/locally/, by below command.
pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu113
and , I got:
>>> import torch
>>> print(torch.__version__)
1.11.0
>>>
It seems than I installed right Pytorch version with right CUDA version, however I got following error :
(torch) PS C:\Users\Administrator\Desktop> python .\torch_test.py
Traceback (most recent call last):
File ".\torch_test.py", line 136, in <module>
model = TFModel(24*7*2, 24*7, 512, 8, 4, 0.1).to(device)
File "C:\Users\Administrator\.conda\envs\torch\lib\site-packages\torch\nn\modules\module.py", line 907, in to
return self._apply(convert)
File "C:\Users\Administrator\.conda\envs\torch\lib\site-packages\torch\nn\modules\module.py", line 578, in _apply
module._apply(fn)
File "C:\Users\Administrator\.conda\envs\torch\lib\site-packages\torch\nn\modules\module.py", line 578, in _apply
module._apply(fn)
File "C:\Users\Administrator\.conda\envs\torch\lib\site-packages\torch\nn\modules\module.py", line 578, in _apply
module._apply(fn)
File "C:\Users\Administrator\.conda\envs\torch\lib\site-packages\torch\nn\modules\module.py", line 601, in _apply
param_applied = fn(param)
File "C:\Users\Administrator\.conda\envs\torch\lib\site-packages\torch\nn\modules\module.py", line 905, in convert
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
File "C:\Users\Administrator\.conda\envs\torch\lib\site-packages\torch\cuda\__init__.py", line 210, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
How can I resolve the AssertionError?