search

mks0601 / V2V-PoseNet_RELEASE

Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018
https://arxiv.org/abs/1711.07399
MIT License
377 stars 69 forks source link

BatchSize setting #43

Closed dragonbook closed 5 years ago

dragonbook commented 5 years ago

Hi,

What's your batchSize values in those different datasets(e.g. msra, nyu) experiments? I see batchSz=1 in config.lua, is that applied to all your experiments?

I trained few models on MSRA hand dataset and my own smaller dataset(not about hand) with V2V-PoseNet-pytorch, I found that the smaller batchSizes often achieve much better results. And the models perform bad if batchSize upto 32 or 64. Have you faced similar situation in your trainings(with your own torch7 implementation)?

Thanks.

mks0601 commented 5 years ago

Sorry, that was a typo. I changed it to batchsize=8. Also, I havent't experiment for more batch size cases.

dragonbook commented 5 years ago

Ok, thanks!