Views
No views yet
43663fb103fc86a5da28806d8aeecdc707c4d6e0 and upstream checkpoint:
https://drive.google.com/file/d/19gnkMTgFveJsrOvSmEPQXCTG6v9oQHN3.encoder.feature_projector.* tensors were omitted, and the checkpoint was saved with LibreYOLO metadata schema v1.0. The inference graph uses the exported student detector weights.LibreYOLO, and evaluated on coco128.yaml with workers=0, batch=8, conf=0.001, iou=0.6.| Metric | Value |
|---|---|
| COCO128 mAP50-95 | 0.6678 |
| COCO128 mAP50 | 0.8514 |
| SHA256 | b9dbf4e0b5ba40817fc5b8da09cd22567e162c0d48060fdca1f07c05991b3c9f |
| File size | 240.4 MB |