search

lhoyer / improving_segmentation_with_selfsupervised_depth

[CVPR21] Implementation of our work "Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation"
244 stars 30 forks source link

About inference time and deployment #16

Closed FangJingYunner closed 2 years ago

FangJingYunner commented 2 years ago

Hi，this is a very great work! And l have some question. What GPU is used for this work as well as its inference time？can it be deployed on an embedded platform? Looking forward to your reply!

lhoyer commented 2 years ago

Hi @FangJingYunner,

Thanks for your interest in our work! The inference times and information on the GPU are provided in Tab. S4 on page 12 of the arxiv paper. The network architecture is quite heavy and not optimized for platforms with limited resources. Therefore, it probably cannot be deployed out-of-the-box on embedded platforms.