HulkMaker / pytorch-yolov3

YOLOv3 PyTorch version, add cocoapi mAP evaluation. 增加了中文注释。
GNU General Public License v3.0
93 stars 18 forks source link

trainning speed #4

Open AsiamGit opened 5 years ago

AsiamGit commented 5 years ago

using multi-scale mode slows down the trainning speed Hi, thanks for sharing your excent work, about the trainning speed,I test several implement and this repo is much better ,but there is one problem:using multi-scale mode slows down the trainning speed when 416416 , 8V100, 64 batchsize, 0.45s/per epoh, cpu occupy 90% when multi-scale , 8*V100, 64 batchsize, 1.8s/per epoh, cpu occupy 20% have you ever met this problems?