search

svip-lab / impersonator

PyTorch implementation of our ICCV 2019 paper: Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis
https://svip-lab.github.io/project/impersonator
Other
1.72k stars 317 forks source link

Can you run this on a 8gb nvidia 1070? #19

Closed bafonso closed 4 years ago

bafonso commented 4 years ago

Has anyone successfully used a 1070 with 8GB? I can't run the demo code while using the 1070 for display but I wonder if I dedicate it for CUDA it will work.

RuntimeError: CUDA out of memory. Tried to allocate 64.00 MiB (GPU 0; 7.93 GiB total capacity; 5.94 GiB already allocated; 41.25 MiB free; 252.07 MiB cached)

StevenLiuWen commented 4 years ago

@bafonso , Hi, we have optimized the minimal requirements of GPU memory and updated the codes righit now. If you get the errors, RuntimeError: CUDA out of memory, please add the flag --batch_size 1. For example, 

python demo_imitator.py --gpu_ids 1 --batch_size 1

The usage of GPU memory is 3.8 GB (tested on my GTX 1080).