Can't reproduce the result:epe 0.69

antabangun / coex

GNU General Public License v3.0

142 stars 19 forks source link

Can't reproduce the result:epe 0.69 #17

Closed GrimaceLittleBoss closed 7 months ago

GrimaceLittleBoss commented 9 months ago

Hi! Thank you for the great works! I'm trying to Re-train the model, But I got epe 0.799957. I wonder if I ignore some setting. I only made a few changes in cfg_coex.yaml:

device: [0,1,2,3,4,5,6,7] train_on: sceneflow: True kitti12: False kitti15: False kittiraw: False kitti360: False

Experiments were on 8 3090Ti GPUs I want to know on which dataset did you train and get epe 0.69?

antabangun commented 9 months ago

Hi, thanks for your interest in our work! That result was trained on only SceneFlow data.

I never tried training the model with multiple GPUs, I wonder if that had any effect on the results. I think training this model is relatively quick. So if you don't mind could you try training for more epochs to see what happens. Maybe with

sceneflow_max_epochs: 20
sceneflow_milestones: [15]

Or even

sceneflow_max_epochs: 30
sceneflow_milestones: [25]

if possible. Thanks!