vsitzmann / siren

Official implementation of "Implicit Neural Representations with Periodic Activation Functions"
MIT License
1.72k stars 247 forks source link

SDF training time #25

Open Skorkmaz88 opened 3 years ago

Skorkmaz88 commented 3 years ago

Are the parameter in SDF training file in experiments folder, reflect the parameters reported in the article? I am experimenting SDF train from scratch using thai statue point cloud, which was provided in google drive link using a V100 GPU but expected time to train so far estimated quite long. I previously tried to train it in a RTX 8000 but the result was the same. I think paper was mentioning 5-6 hours of training for 50k epochs .

Screen Shot 2020-10-27 at 1 45 04 PM
Skorkmaz88 commented 3 years ago

Also a small issue but in case you want to fix, option help strings in that file seems to be replicating:

p.add_argument('--model_type', type=str, default='sine',
               help='Options are "sine" (all sine activations) and "mixed" (first layer sine, other layers tanh)')
p.add_argument('--point_cloud_path', type=str, default='/home/sitzmann/data/point_cloud.xyz',
               help='Options are "sine" (all sine activations) and "mixed" (first layer sine, other layers tanh)')