zhengthomastang / 2018AICity_TeamUW

The winning method in Track 1 and Track 3 at the 2nd AI City Challenge Workshop in CVPR 2018 - Official Implementation
http://openaccess.thecvf.com/content_cvpr_2018_workshops/w3/html/Tang_Single-Camera_and_Inter-Camera_CVPR_2018_paper.html
550 stars 198 forks source link

CUDA installation #19

Open Ali-Parsa opened 4 years ago

Ali-Parsa commented 4 years ago

Is it necessary to have CUDA installed to implement YOLO? Unfortunately, my GPU is not CUDA-supported!

zhengthomastang commented 4 years ago

The CPU version of YOLO is significantly slower than the GPU version, especially for training. You don't have to install CUDA, but it is highly recommended.

Ali-Parsa commented 4 years ago

Thank you Thomas