Can code be tested on the non-CUDA system?

[EngineerKhan]

I have been trying to test your code (with a small video file) on my laptop (lacking the CUDA GPU), but it gives the following error:

python main.py --input ./input --video_root ./videos --output ./output.json --
model ./resnext-101-64f-kinetics.pth --mode feature
THCudaCheck FAIL file=/opt/conda/conda-bld/pytorch_1532502075707/work/aten/src/THC/THCGeneral.cpp line=74 error=35 : CUDA driver version is insufficient for CUDA runtime version
Traceback (most recent call last):
File "main.py", line 22, in
model = generate_model(opt)
File "/home/hd/PhD/ResNet/ResNet3D/video-classification-3d-cnn-pytorch-master/model.py", line 117, in generate_model
model = model.cuda()
File "/home/hd/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 258, in cuda
return self._apply(lambda t: t.cuda(device))
File "/home/hd/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 185, in _apply
module._apply(fn)
File "/home/hd/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 191, in _apply
param.data = fn(param.data)
File "/home/hd/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 258, in
return self._apply(lambda t: t.cuda(device))
RuntimeError: cuda runtime error (35) : CUDA driver version is insufficient for CUDA runtime version at /opt/conda/conda-bld/pytorch_1532502075707/work/aten/src/THC/THCGeneral.cpp:74

So, should I need to modify the code or this code can run on CPU as well? (Using the pre-trained model resnext-101-kinetics-hmdb51_split1.pth)
Thanks a lot for your help