Enorenio commited on
Commit
b528421
·
verified ·
1 Parent(s): 440b2e0

Remove links to private GitHub repo

Browse files
Files changed (1) hide show
  1. README.md +7 -12
README.md CHANGED
@@ -53,19 +53,15 @@ For context: the original course leaderboard had 28 teams. This release would pl
53
 
54
  ## Quick start
55
 
56
- ```bash
57
- git clone https://github.com/enorenio/Challenge
58
- cd Challenge
59
- pip install torch numpy pillow opencv-python scipy
60
 
61
- hf download Enorenio/scribble-segmentation --local-dir runs/
62
 
63
- python predict_ensemble.py \
64
- --ckpt-dirs runs/runs_v4:64:44 runs/runs_v7_pseudo:64:47 \
65
- --gpu 0
66
- ```
67
 
68
- The interactive demo at https://enorenio.github.io/scribble-seg-demo/ shows side by side predictions for every method on all 682 train and test images, plus an analysis of the five universally hardest cases.
 
 
69
 
70
  ## What is in this repo
71
 
@@ -109,8 +105,7 @@ PASCAL VOC domain. Training images are natural indoor and outdoor scenes from PA
109
  @misc{morshnev2025scribbleseg,
110
  author = {Aleksey Morshnev},
111
  title = {Scribble Segmentation Ensemble},
112
- year = {2025},
113
- url = {https://github.com/enorenio/Challenge}
114
  }
115
  ```
116
 
 
53
 
54
  ## Quick start
55
 
56
+ The inference code is not yet public. The weights here are usable once paired with the matching loader, which will be released alongside a writeup.
 
 
 
57
 
58
+ In the meantime, the interactive demo at https://enorenio.github.io/scribble-seg-demo/ shows side by side predictions for every method on all 682 train and test images, plus an analysis of the five universally hardest cases.
59
 
60
+ Downloading the weights from this repo:
 
 
 
61
 
62
+ ```bash
63
+ hf download Enorenio/scribble-segmentation --local-dir runs/
64
+ ```
65
 
66
  ## What is in this repo
67
 
 
105
  @misc{morshnev2025scribbleseg,
106
  author = {Aleksey Morshnev},
107
  title = {Scribble Segmentation Ensemble},
108
+ year = {2025}
 
109
  }
110
  ```
111