After executing ”python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs” command, it gets stuck and there is no other information

[Le1q]

The environment is as follows：
(ml-env) PS C:\workspace\ml\Real-ESRGAN\Real-ESRGAN> pip list
Package Version Editable project location

---

absl-py 2.1.0
addict 2.4.0
autocommand 2.2.2
backports.tarfile 1.2.0
basicsr 1.4.2
certifi 2025.1.31
charset-normalizer 3.4.1
colorama 0.4.6
contourpy 1.3.1
cycler 0.12.1
facexlib 0.3.0
filelock 3.18.0
filterpy 1.4.5
fonttools 4.56.0
fsspec 2025.3.0
future 1.0.0
gfpgan 1.3.8
grpcio 1.71.0
idna 3.10
imageio 2.37.0
importlib_metadata 8.0.0
inflect 7.3.1
jaraco.collections 5.1.0
jaraco.context 5.3.0
jaraco.functools 4.0.1
jaraco.text 3.12.1
Jinja2 3.1.6
kiwisolver 1.4.8
lazy_loader 0.4
llvmlite 0.44.0
lmdb 1.6.2
Markdown 3.7
MarkupSafe 3.0.2
matplotlib 3.10.1
more-itertools 10.3.0
mpmath 1.3.0
networkx 3.4.2
numba 0.61.0
numpy 2.1.3
opencv-python 4.11.0.86
packaging 24.2
pillow 11.1.0
pip 25.0.1
platformdirs 4.3.6
protobuf 6.30.1
pyparsing 3.2.1
python-dateutil 2.9.0.post0
PyYAML 6.0.2
realesrgan 0.3.0 C:\workspace\ml\Real-ESRGAN\Real-ESRGAN
requests 2.32.3
scikit-image 0.25.2
scipy 1.15.2
setuptools 76.1.0
six 1.17.0
sympy 1.13.1
tb-nightly 2.20.0a20250318
tensorboard-data-server 0.7.2
tifffile 2025.3.13
tomli 2.0.1
torch 2.6.0
torchvision 0.21.0
tqdm 4.67.1
typeguard 4.3.0
typing_extensions 4.12.2
urllib3 2.3.0
Werkzeug 3.1.3
wheel 0.43.0
yapf 0.43.0
zipp 3.19.2

Execute the following command:
python inference_realesrgan.py -n RealESRGAN_x4plus -i inputs
Testing 0 00017_gray

Output after manual cancellation via ctrl+c：

Traceback (most recent call last):
File "C:\workspace\ml\Real-ESRGAN\Real-ESRGAN\inference_realesrgan.py", line 166, in
main()
File "C:\workspace\ml\Real-ESRGAN\Real-ESRGAN\inference_realesrgan.py", line 147, in main
output, _ = upsampler.enhance(img, outscale=args.outscale) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\workspace\ml\ml-env\Lib\site-packages\torch\utils_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\Real-ESRGAN\Real-ESRGAN\realesrgan\utils.py", line 223, in enhance
self.process()
File "C:\workspace\ml\Real-ESRGAN\Real-ESRGAN\realesrgan\utils.py", line 115, in process
self.output = self.model(self.img)
^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\basicsr\archs\rrdbnet_arch.py", line 113, in forward
body_feat = self.conv_body(self.body(feat))
^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\torch\nn\modules\container.py", line 250, in forward
input = module(input)
^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\basicsr\archs\rrdbnet_arch.py", line 60, in forward
out = self.rdb2(out)
^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\basicsr\archs\rrdbnet_arch.py", line 35, in forward
x3 = self.lrelu(self.conv3(torch.cat((x, x1, x2), 1)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\torch\nn\modules\conv.py", line 554, in forward
return self._conv_forward(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\workspace\ml\ml-env\Lib\site-packages\torch\nn\modules\conv.py", line 549, in _conv_forward
return F.conv2d(
^^^^^^^^^
KeyboardInterrupt

[Le1q]

def process(self):
     self.output = self.model(self.img)，

it stops here.

and model is exist.
I try print the info of the model. as follows:

RRDBNet(
  (conv_first): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))  (body): Sequential(
    (0): RRDB(
      (rdb1): ResidualDenseBlock(
        (conv1): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (conv2): Conv2d(96, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
        (conv3): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 
1))
        (conv4): Conv2d(160, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 
1))
        (conv5): Conv2d(192, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 
1))
        (lrelu): LeakyReLU(negative_slope=0.2, inplace=True)

[czdelete]

hello,is this issue already fixed?I also met it

[Joxterian]

Hi there,

I had this problem, and in my case, I did pip install -r requirements.txt which installs all dependencies listed in the requirements.txt, installing default torch version (not the cuda version), this version uses CPU as far as I understand, so it's significantly slower. In my case I have a NVIDIA and in order to solve it I had to install cuda version: pip install torch torchvision --index-url https://download.pytorch.org/whl/cu121. Hope it helps.