Downloads · 30 days
0
petrol-v8b
licensy/petrol-v8b
petrol-v8b is a machine learning model from licensy. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Single 22.7 MB ONNX (havengo's proven-best weights). v8b drops the TTA passes that timed out in v8 and keeps only the information-adding components that fit in single-pass latency:
Access
Public
Updated May 2, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx22.7 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- May 2, 2026
- Updated
- May 2, 2026
- SHA
- ac7ed90f
Model card
From the Hugging Face model README
petrol-v8b — single-pass max-information
Single 22.7 MB ONNX (havengo's proven-best weights). v8b drops the TTA passes that timed out in v8 and keeps only the information-adding components that fit in single-pass latency:
- CLAHE on the L-channel (rescues low-contrast / dusk frames)
- Mean-color letterbox padding (vs grey 114) — fewer edge false positives
- WBF fusion within single pass (per-class)
- Class-aware confidence thresholds (pumps lower, canopy higher)
- Geometric sanity filter (drops 0px or full-image junk)
The honest local benchmark proved filtering moves (agreement gates) hurt scores. v8b only filters obvious geometric junk and uses information-adding preprocessing.
Repo size: 22.7 MB. Expected p95 latency: ~1.4–1.8 s (well under 10 s gate).
- License
- mit
- Created
- May 2, 2026
- Updated
- May 2, 2026