Hugging Face's logo

labelmaker
/
PTv3-ARKit-LabelMaker

TensorBoard
Model card Files
xet
 Metrics Community
1
quantaji commited on
Commit
c9ff7e5
·
verified ·
1 Parent(s): 023f02f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -3
README.md CHANGED
@@ -1,3 +1,34 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ datasets:
4
+ - labelmaker/arkit_labelmaker
5
+ base_model:
6
+ - Pointcept/PointTransformerV3
7
+ ---
8
+
9
+ # Models Trained with [ARKit LabelMaker](https://huggingface.co/datasets/labelmaker/arkit_labelmaker)
10
+
11
+ 1. Please check out out project page [labelmaker.org](https://labelmaker.org/). 😁
12
+ 2. The major dataset is [here](https://huggingface.co/datasets/labelmaker/arkit_labelmaker) and the processing code and preprocessed dataset for PTv3 is [here](https://huggingface.co/datasets/labelmaker/ALC_pointcept).
13
+ 3. Training log tensorboard [link](https://huggingface.co/labelmaker/PTv3-ARKit-LabelMaker/tensorboard)
14
+ 4. We made some modification on [Pointcept](https://github.com/quantaji/LabelMaker-Pointcept). You can also download per-experiment code base in each experiment folder.
15
+
16
+ ## 1. 3D Semantic Segmentation
17
+
18
+ Model: PointTransformer V3 + PPT.
19
+ Additional dataset: ScanNet++, Structured3D.
20
+
21
+ | Task | ScanNet | ScanNet200 | ScanNet mIoU | ScanNet200 mIoU | ckpt | config | folder |
22
+ | ---------------------- | ----------- | ----------- | ------------ | --------------- | -------------------------------------------------------------------------------------- | --------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- |
23
+ | Eval ScanNet on val | train | train + val | 79.1 | - | [link](./scannet/semseg-pt-v3m1-1-ppt-extreme-with-alc/model/model_last.pth) | [link](./scannet/semseg-pt-v3m1-1-ppt-extreme-with-alc/config.py) | [link](https://huggingface.co/labelmaker/PTv3-ARKit-LabelMaker/tree/main/scannet/semseg-pt-v3m1-1-ppt-extreme-with-alc) |
24
+ | Eval ScanNet200 on val | train + val | train | - | 37.5 | [link](./scannet200/semseg-pt-v3m1-1-ppt-extreme-with-alc/model/model_last.pth) | [link](./scannet200/semseg-pt-v3m1-1-ppt-extreme-with-alc/config.py) | [link](https://huggingface.co/labelmaker/PTv3-ARKit-LabelMaker/tree/main/scannet200/semseg-pt-v3m1-1-ppt-extreme-with-alc) |
25
+ | Eval on both on test | train + val | train + val | 79.8 | 41.4 | [link](./scannet200/semseg-pt-v3m1-1-ppt-extreme-with-alc-submit/model/model_last.pth) | [link](./scannet200/semseg-pt-v3m1-1-ppt-extreme-with-alc-submit/config.py) | [link](https://huggingface.co/labelmaker/PTv3-ARKit-LabelMaker/tree/main/scannet200/semseg-pt-v3m1-1-ppt-extreme-with-alc-submit) |
26
+
27
+ ## 2. 3D Instance Segmentation
28
+ Pre-trained model checkpoints: PointTransformer V3 + PPT.
29
+ Training dataset: ScanNet/ScanNet200 training split.
30
+
31
+ | Task | val mAP | ckpt | config | folder |
32
+ | ---------- | ------- | ------------------------------------------------------------------------------- | -------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |
33
+ | ScanNet | 41.4 | [link](./scannet/insseg-pointgroup-v1m1-pt-v3m1-ppt-ft/model/model_last.pth) | [link](./scannet/insseg-pointgroup-v1m1-pt-v3m1-ppt-ft/config.py) | [link](https://huggingface.co/labelmaker/PTv3-ARKit-LabelMaker/tree/main/scannet/insseg-pointgroup-v1m1-pt-v3m1-ppt-ft/) |
34
+ | ScanNet200 | 24.5 | [link](./scannet200/insseg-pointgroup-v1m1-pt-v3m1-ppt-ft/model/model_last.pth) | [link](./scannet200/insseg-pointgroup-v1m1-pt-v3m1-ppt-ft/config.py) | [link](https://huggingface.co/labelmaker/PTv3-ARKit-LabelMaker/tree/main/scannet200/insseg-pointgroup-v1m1-pt-v3m1-ppt-ft) |