NVIDIA / vid2vid

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
Other
8.62k stars 1.2k forks source link

Potential training time of 512 pixel size videos in 4*1080-ti GPU #102

Open momo1986 opened 5 years ago

momo1986 commented 5 years ago

Hello, I want to train the vide synthesis with city landscape dataset.

I am not sure, how long will it last for 4 1080-ti GPUs.

Here is the code:

python train.py --name label2city_512 \
--label_nc 35 --loadSize 512 --use_instance --fg \
--gpu_ids 0,1,2,3 --n_gpus_gen 2 \
--n_frames_total 6 --max_frames_per_gpu 2

Thanks & Regards!