Hugging Face's logo

bag100
/
triangulang

Image Segmentation
3d-localization
multi-view
segmentation
language-grounding
pose-free
Model card Files
xet
 Community
bag100 commited on
Commit
1cfe0c8
·
verified ·
1 Parent(s): c7604cd

Update model card: 230 scenes

Browse files
Files changed (1) hide show
  1. README.md +3 -4
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- license: apache-2.0
3
  tags:
4
  - 3d-localization
5
  - multi-view
@@ -27,15 +27,14 @@ TrianguLang is a feed-forward, pose-free method for language-guided 3D localizat
27
 
28
  | Checkpoint | Description | Eval mIoU |
29
  |---|---|---|
30
- | `mo_v11/best.pt` | Multi-object (text + spatial), 245 scenes, 8 views, 100 epochs | **Best MO** |
31
- | `fullscale_no_qp/best.pt` | Single-object (text-only), 245 scenes, 100 epochs | **Best SO** |
32
 
33
  ## Usage
34
 
35
  ```python
36
  from triangulang.training.train import TrianguLangModel
37
 
38
- # Load checkpoint
39
  checkpoint = torch.load("best.pt", map_location="cpu")
40
  model = TrianguLangModel(...)
41
  model.load_state_dict(checkpoint["model_state_dict"])
 
1
  ---
2
+ license: mit
3
  tags:
4
  - 3d-localization
5
  - multi-view
 
27
 
28
  | Checkpoint | Description | Eval mIoU |
29
  |---|---|---|
30
+ | `mo_v11/best.pt` | Multi-object (text + spatial), 230 scenes, 8 views, 100 epochs | Best MO |
31
+ | `fullscale_no_qp/best.pt` | Single-object (text-only), 230 scenes, 100 epochs | Best SO |
32
 
33
  ## Usage
34
 
35
  ```python
36
  from triangulang.training.train import TrianguLangModel
37
 
 
38
  checkpoint = torch.load("best.pt", map_location="cpu")
39
  model = TrianguLangModel(...)
40
  model.load_state_dict(checkpoint["model_state_dict"])