-
Notifications
You must be signed in to change notification settings - Fork 482
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
same input image in animation folder #38
Comments
You're not doing anything wrong. Your MacBook doesn't have a NVidia GPU that is capable to do the treatment. So, your CPU is working instead. |
ok. so How much time does the whole process take to complete? |
You've set 2000 iterations, on your CPU, simply multiply 50 minutes by 2000. On a GPU it should take less than 8 minutes |
But in the terminal i see nothing and after a very long time, the input image appears in animation folder. all of that is normal? I know I using my CPU. |
The only lines in the terminal you will see are the iterations. "Iteration xx, Cost xx" |
My macbook has a Intel Onboard Integrated GPU. Do you think I can use it for this neural network? is it possible? |
Unfortunately not. You need an NVidia card in order to have the NVdia tools (drivers, Cudnn...) |
I running the neural network like this:
python neural_artistic_style.py --subject /Users/user/Documents/matias.jpg --style images/skrik.jpg --iterations 2000 --out salida.png
Then, I get this:
CUDArray: CUDA back-end not available, using NumPy.
Later, after 50min more or less, the same input image appear in the animation folder.
Am I doing something wrong?
I am running the neural network in my macbook air 2011.
The text was updated successfully, but these errors were encountered: