search

PeihaoChen / RSPNet

Official Pytorch implementation for AAAI2021 paper (RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning)
36 stars 9 forks source link

Question about computational resources #1

Closed wjn922 closed 3 years ago

wjn922 commented 3 years ago

Hi, Thanks for your wonderful paper and code. I want to know the computational resources of your experiments.

  1. What and how many GPUs you use?
  2. The training time of pretraining on K400 for 200 epochs.
  3. The training time of finetuning on UCF101, HMDB51, Something-V2, respectively. Looking forward to your reply. Thanks.
PeihaoChen commented 3 years ago

Thanks for your interest!

  1. We use TITAN Xp and V100 GPUs for training.
  2. It takes 187h/ 140h/ 166h/ 150h for pretraining our R21D/ ResNet-18/ S3D-G/ C3D models using 6/ 4/ 4/ 4*V100 GPUs, respectively.
  3. For C3D model, it takes 0.52h/ 2.27h/ 26.72h for finetuning on UCF101/ HMDB51/ Something-V2 using 4/ 2/ 4*TITAN Xp GPUs, respectively.
wjn922 commented 3 years ago

Thanks for your kind reply.