Bundle inference code, update quick start

README.md

@@ -53,16 +53,26 @@ For context: the original course leaderboard had 28 teams. This release would pl
 
 ## Quick start
 
-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.
+The two essential inference scripts (`predict_ensemble.py` and `train_global_unet.py`) ship inside this repo along with the weights, so the model is runnable without any external code.
 
-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.
+```bash
+hf download Enorenio/scribble-segmentation --local-dir release
+cd release
+pip install torch numpy pillow opencv-python scipy
+```
 
-Downloading the weights from this repo:
+Inference expects images at `dataset/test1/images/*.jpg` and matching scribbles at `dataset/test1/scribbles/*.png` (values 0=bg, 1=fg, 255=unlabeled). It also needs a reference palette file at `dataset/train/ground_truth/<any>.png` to colorize the output (any PASCAL VOC palette PNG works).
 
 ```bash
-hf download Enorenio/scribble-segmentation --local-dir runs/
+python predict_ensemble.py \
+    --ckpt-dirs runs_v4:64:44 runs_v7_pseudo:64:47 \
+    --gpu 0
 ```
 
+Predictions land at `dataset/test1/predictions/*.png`.
+
+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.
+
 ## What is in this repo
 
 Two sets of five fold checkpoints plus a tiny threshold model: