search

Tramac / Fast-SCNN-pytorch

A PyTorch Implementation of Fast-SCNN: Fast Semantic Segmentation Network
Apache License 2.0
380 stars 93 forks source link

AssertionError: Torch not compiled with CUDA enabled #33

Open mertmerci opened 4 years ago

mertmerci commented 4 years ago

Hi,

I'm trying to train your framework on Mac OS and got this assertion error, as expected because my device has not got an Nvidia GPU. Can I run the framework on my CPU, if yes how can I do it, which lines should I change or add?

Thank you for your time.

Tramac commented 4 years ago

Hi, you can set here to True.

mertmerci commented 4 years ago

Hello, thank you for your quick response. I changed the line parser.set_defaults(cpu=True) (demo.py line 25) but I still get the same error. The exact is error is presented to your attention as an attachment.

Thank you in advance.

Screenshot 2020-08-21 at 12 15 28
Tramac commented 4 years ago

Please modify here to target = Variable(torch.from_numpy(input_label.reshape(target.size())).long()