ESRGANの実行について

インターネット上で画像を高解像度化することができるか調べていたら"ESRGAN"というものを見つけ、環境構築を行い、実際に実行してみたのですが、エラーがでます。

error
1C:\ESRGAN>python test.py
2Traceback (most recent call last):
3  File "C:\ESRGAN\test.py", line 17, in <module>
4    model = model.to(device)
5  File "C:\Users\USERNAME\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\nn\modules\module.py", line 673, in to
6    return self._apply(convert)
7  File "C:\Users\USERNAME\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\nn\modules\module.py", line 387, in _apply
8    module._apply(fn)
9  File "C:\Users\USERNAME\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\nn\modules\module.py", line 409, in _apply
10    param_applied = fn(param)
11  File "C:\Users\USERNAME\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\nn\modules\module.py", line 671, in convert
12    return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
13  File "C:\Users\USERNAME\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\cuda\__init__.py", line 170, in _lazy_init
14    torch._C._cuda_init()
15RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx

実行したファイルはそのリポジトリ(https://github.com/xinntao/ESRGAN)についてあるサンプルプログラムです。

Python
1import os.path as osp
2import glob
3import cv2
4import numpy as np
5import torch
6import RRDBNet_arch as arch
7
8model_path = 'models/RRDB_ESRGAN_x4.pth'  # models/RRDB_ESRGAN_x4.pth OR models/RRDB_PSNR_x4.pth
9device = torch.device('cuda')  # if you want to run on CPU, change 'cuda' -> cpu
10# device = torch.device('cpu')
11
12test_img_folder = 'LR/*'
13
14model = arch.RRDBNet(3, 3, 64, 23, gc=32)
15model.load_state_dict(torch.load(model_path), strict=True)
16model.eval()
17model = model.to(device)
18
19print('Model path {:s}. \nTesting...'.format(model_path))
20
21idx = 0
22for path in glob.glob(test_img_folder):
23    idx += 1
24    base = osp.splitext(osp.basename(path))[0]
25    print(idx, base)
26    # read images
27    img = cv2.imread(path, cv2.IMREAD_COLOR)
28    img = img * 1.0 / 255
29    img = torch.from_numpy(np.transpose(img[:, :, [2, 1, 0]], (2, 0, 1))).float()
30    img_LR = img.unsqueeze(0)
31    img_LR = img_LR.to(device)
32
33    with torch.no_grad():
34        output = model(img_LR).data.squeeze().float().cpu().clamp_(0, 1).numpy()
35    output = np.transpose(output[[2, 1, 0], :, :], (1, 2, 0))
36    output = (output * 255.0).round()
37    cv2.imwrite('results/{:s}_rlt.png'.format(base), output)
38