natanielruiz / deep-head-pose

:fire::fire: Deep Learning Head Pose Estimation using PyTorch.
Other
1.58k stars 368 forks source link

Batch size for training Hopenet #108

Open gitjohnnygit opened 3 years ago

gitjohnnygit commented 3 years ago

The paper mentioned epoch=25, lr=0.00001 but did not say how many batch size should be. How did you choose the batch size for re-producing the same result on training on the 300W-LP? Any suggestions? Thank you in advance :)