Closed bafonso closed 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).
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)