DomeKeeper YOLO v0
YOLO26n object detector for Dome Keeper gameplay frames, trained for the AIRI Dome Keeper plugin and the Game Playing AI Playground 2D.
The training dataset is available at proj-airi/domekeeper-yolo-dataset-v0.
Artifact
best.onnx is a fixed-shape ONNX export:
- Input:
images, float32,(1, 3, 640, 640), RGB normalized to[0, 1] - Output:
output0, float32,(1, 300, 6) - Output rows:
[x1, y1, x2, y2, confidence, class_id] - Postprocessing: YOLO26 end-to-end output; external non-maximum suppression is not required
The exported model is fixed to batch size 1 and 640x640; dynamic shapes are not enabled.
Classes
| ID | Name |
|---|---|
| 0 | player_engineer |
| 1 | dome_laser |
| 2 | ore_iron |
| 3 | ore_cobalt |
| 4 | ore_water |
| 5 | enemy |
Validation results
The best checkpoint was selected at epoch 76.
Validation batch predictions:
Training
- Architecture: YOLO26n detection
- Ultralytics: 8.4.104
- Resolution:
640x640 - Epochs: 100
- Batch size: 16
- Optimizer:
auto - Seed: 0, deterministic mode enabled
- Training device: Apple MPS
- Training source revision:
9b95720c7e7e6eeb6e1ae5b7402caa3de683631d
Limitations
This v0 model is an ore-focused proof of concept. The dataset contains no boxes for player_engineer, dome_laser, or enemy; those classes should be treated as unsupported. Cobalt has no validation or test examples, water has no test examples, and the test split contains only iron. The split comes from one temporally segmented gameplay session, so nearby frames may remain correlated even though there are no exact duplicate images.
Do not interpret the aggregate validation metrics as evidence that all six configured classes work. Additional independent sessions and balanced labels are required before using this model as a general Dome Keeper state detector.
References: Ultralytics YOLO26, end-to-end detection output, ONNX export.
- Downloads last month
- -