search

xinghaochen / Pose-REN

Code for "Pose Guided Structured Region Ensemble Network for Cascaded Hand Pose Estimation", Neurocomputing 2020
168 stars 52 forks source link

Hi. I have some question about data augmentation and total learning time. #16

Open KwonTaewoong opened 5 years ago

KwonTaewoong commented 5 years ago

Hi.

I am interested in your project and have some question.

How many times did you do data augmentation?

and, how much time did need all to train in your project?(baseline and pose-ren)

Last, I wonder that which GPU device perform training in your project?

Thank you!!

xinghaochen commented 5 years ago

Hi, we do online data augmentation in training. That's to say, each sample is augmented randomly before being fed into the network for training.

I can't remember the precise training time. Maybe it was trained within two days or so using a Tesla K40 GPU.