search

WongKinYiu / PyTorch_YOLOv4

PyTorch implementation of YOLOv4
1.87k stars 585 forks source link

About Training Time compare with Darknet #51

Open lq0104 opened 4 years ago

lq0104 commented 4 years ago

Hi, thank you very much for your work in Yolo, I have a question about the training time compare with AlexeyAB darknet, that is which is faster when training with the same network cfg (e.g Yolov4.cfg) and the same iterator counts, Because My computer GPU is not so good, so I'm more concerned with training time. Thank you again.

WongKinYiu commented 4 years ago

if your gpu has tensor core, the training of this implementation is about 3 to 4 times faster.

lq0104 commented 4 years ago

Hi, thank you for your quick reply. My computer GPU is NVidia 2080Ti, so it has tensor core. And I also see the AlexeyAB's repo supports Tensor core too, So my question is that: Does "PyTorch_YOLOv4+Tensor core" is train faster than "AlexeyAB darknet+Tensor core"? Thank you very much.

WongKinYiu commented 4 years ago

yes.