search

jcorsetti / oryon

Official implementation of CVPR24 Highlight paper "Open-vocabulary object 6D pose estimation"
20 stars 2 forks source link

Question abot inference time #7

Closed ran894694447 closed 1 month ago

ran894694447 commented 1 month ago

Thanks for your great work! Can you tell me about the inference speed of this model? How many images can it process per second? I'm looking foward to your early reply!

jcorsetti commented 1 month ago

Hi, in the supplementary material we reported the inference time. A complete inference on one dataset (2000 image pairs) takes about one hour on an Nvidia V100, so that's about 1.1 image per second, considering 4000 images in 3600 seconds. This as an upper bound, as it also includes the I/O time, the metric computation and saving the results on disk.

ran894694447 commented 1 month ago

Thank you for your reply!