Using StackGAN demo without Nvidia CUDA

hanzhanggit / StackGAN

MIT License

1.86k stars 457 forks source link

Using StackGAN demo without Nvidia CUDA #4

Open gilgtc opened 7 years ago

gilgtc commented 7 years ago

I tried to get StackGAN to work on my cluster by it does not have an NVIDIA GPU. Is it possible to run StackGAN without CUDA, i.e. use the CPU instead? If possible what are the steps?

gdshen commented 7 years ago

maybe you could look at this https://github.com/brangerbriz/docker-StackGAN/#cpu-only

HamedMP commented 7 years ago

@gdshen It's for running the docker instance. But when you are inside the docker, you can't train/eval

Periter commented 6 years ago

I got the same problem，since i used the ‘top’ command found the usage of CPU so high, against NOT take any memory of GPU for train.

Dragomir2020 commented 5 years ago

I tired running code using cpu version of tensorflow in linux box. Seems to train, but is extremely slow. Like 30 days to run 600 epochs, if I left it running.