search

Kiteretsu77 / APISR

APISR: Anime Production Inspired Real-World Anime Super-Resolution (CVPR 2024)
GNU General Public License v3.0
752 stars 51 forks source link

About gpu inference #17

Open Kite-free opened 3 days ago

Kite-free commented 3 days ago

Why am I inferring this model through rtx4090? Its inference speed is very slow. The model used is DAT. Inference speed takes about five seconds to infer a picture. If you check the gpu, you can confirm that it is the gpu that is being called.

Kiteretsu77 commented 2 days ago

Did you try to check the time by 100 times in average? The initial loading to the weight is time-consuming. For the second run, it should be efficient. Also, the input resolution is an issue.