Closed YongZh958 closed 1 year ago
Maybe the memory is inefficient, and try to use fewer samples to build memory banks with --max_sample
.
Thanks for your help. I solve this problem successfully!
I am having the same issue. How did you solve it??
(m3dm) root@d12f2348ebf0:~/ZY/model/M3DM# python3 main.py --method_name DINO+Point_MAE --memory_bank multiple --rgb_backbone_name vit_base_patch8_224_dino --xyz_backbone_name Point_MAE --save_feature Extracting train features for class bagel: 100%|???????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????| 244/244 [08:19<00:00, 2.05s/it]
Running coreset for DINO+Point_MAE on class bagel... Fitting random projections. Start dim = torch.Size([765184, 1152]). Killed