scorevision: push artifact
Browse files
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: agpl-3.0
|
|
|
|
| 3 |
tags:
|
| 4 |
- object-detection
|
| 5 |
- onnx
|
|
@@ -8,7 +9,7 @@ tags:
|
|
| 8 |
- scorevision
|
| 9 |
---
|
| 10 |
|
| 11 |
-
# Room-dirtiness detector
|
| 12 |
|
| 13 |
Detector for the Score element `manako/Detect-room-dirtiness-detection`.
|
| 14 |
|
|
@@ -20,36 +21,25 @@ Detector for the Score element `manako/Detect-room-dirtiness-detection`.
|
|
| 20 |
| 3 | mould |
|
| 21 |
| 4 | stain |
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
## How it runs
|
| 24 |
-
- `model.onnx` is a YOLO11n detector with a 640x640 input and a box-only head.
|
| 25 |
-
- `miner.py` letterbox-resizes the frame and runs onnxruntime on CPU with 2 threads. Everything is plain numpy/OpenCV, so the chute and Score's CPU compliance run give the same boxes.
|
| 26 |
-
- Score thresholds are 0.25 for every class except stain, which uses 0.35. Boxes then go through per-class NMS.
|
| 27 |
-
- **One box per object.** A box is dropped when it lies at least 70% inside a bigger box of the same class whose score is at least 0.9 times its own. Score's labeller gives each object a single box, so such a box is usually one piece of a larger object, for example one item of a litter pile.
|
| 28 |
|
| 29 |
-
|
| 30 |
-
|
| 31 |
|
| 32 |
-
|
| 33 |
-
|---|---|---|
|
| 34 |
-
| 0.25 | [manako/Detect-room-dirtiness-detection](https://huggingface.co/manako/Detect-room-dirtiness-detection), the Manako baseline (YOLO11n-seg) | AGPL-3.0 |
|
| 35 |
-
| 0.75 | [Targaryen101/dirtiness_01](https://huggingface.co/Targaryen101/dirtiness_01), a full fine-tune of that baseline | AGPL-3.0 |
|
| 36 |
|
| 37 |
-
-
|
| 38 |
-
-
|
|
|
|
| 39 |
|
| 40 |
## Results
|
| 41 |
-
Scores below use Score's own per-image scorer. The public test images are scored against answer keys rebuilt from Score's published per-miner verdicts.
|
| 42 |
-
|
| 43 |
-
| | 14 well-pinned public tests | all 31 public tests | 962 of our own generated images (SAM3 labels) |
|
| 44 |
-
|---|---|---|---|
|
| 45 |
-
| baseline, run the way public copies run it | 0.533 | 0.460 | 0.324 |
|
| 46 |
-
| v2 (blend, plain 0.25 threshold) | 0.551 | 0.502 | 0.368 |
|
| 47 |
-
| **v3 (this release)** | **0.567** | **0.515** | **0.373** |
|
| 48 |
|
| 49 |
-
|
| 50 |
-
- **No Score test images were used for training.** The public test images were used only to choose the blend ratio and the two thresholds, and to check the result.
|
| 51 |
|
| 52 |
-
|
| 53 |
|
| 54 |
-
|
| 55 |
-
AGPL-3.0. Both source ONNX files carry Ultralytics' AGPL-3.0 notice in their metadata, and this derived model keeps it.
|
|
|
|
| 1 |
---
|
| 2 |
license: agpl-3.0
|
| 3 |
+
base_model: crimedetector/room-dirtinessR
|
| 4 |
tags:
|
| 5 |
- object-detection
|
| 6 |
- onnx
|
|
|
|
| 9 |
- scorevision
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# Room-dirtiness detector, YOLO11n at 640 px (Score / SN44)
|
| 13 |
|
| 14 |
Detector for the Score element `manako/Detect-room-dirtiness-detection`.
|
| 15 |
|
|
|
|
| 21 |
| 3 | mould |
|
| 22 |
| 4 | stain |
|
| 23 |
|
| 24 |
+
## Base model
|
| 25 |
+
|
| 26 |
+
This model is a fine-tune of [crimedetector/room-dirtinessR](https://huggingface.co/crimedetector/room-dirtinessR) (revision `cb11ab1bb19d3b3f51a70f0567bc19c92f27fd89`), a public Ultralytics YOLO11n detector for the same element. Credit for the base weights goes to its author.
|
| 27 |
+
|
| 28 |
## How it runs
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
+
- `model.onnx` is a YOLO11n detector with a 640x640 input. For each of 8,400 anchors it gives one box (centre, width and height) and 5 class scores. There is no NMS inside the graph.
|
| 31 |
+
- `miner.py` letterbox-resizes the frame to 640x640 (centred, grey 114 border) and runs onnxruntime on CPU with 2 threads. Per anchor it keeps the best class, keeps scores of at least 0.25, maps the boxes back to picture pixels, clips them, runs class-wise NMS at IoU 0.5 and returns at most 100 boxes.
|
| 32 |
|
| 33 |
+
## Training
|
|
|
|
|
|
|
|
|
|
| 34 |
|
| 35 |
+
- The base model's exported weights (convolution and batch-norm folded together) were rebuilt into a trainable Ultralytics YOLO11n. The rebuilt network reproduces the base model's raw outputs (largest score difference 4e-6 on test pictures).
|
| 36 |
+
- It was fine-tuned for 20 epochs with SGD (lr0 0.002, cosine schedule, batch 32, 640 px, Ultralytics' default augmentation with mosaic). All batch-norm layers stayed frozen.
|
| 37 |
+
- Training data: Score's public test pictures for this element. The 20 most recent tests up to block 9432300 were used, each 20 times, when their reconstructed answer key reproduces reference miners' published scores (13 tests). 132 older test pictures were used twice each. The labels are those reconstructed answer keys.
|
| 38 |
|
| 39 |
## Results
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
| 41 |
+
No result on tests after training exists yet. Score's own records will show how it does on new tests.
|
|
|
|
| 42 |
|
| 43 |
+
## Licence
|
| 44 |
|
| 45 |
+
The base model's ONNX file carries Ultralytics' AGPL-3.0 licence notice. This model, a derivative of it, and the `miner.py` in this repository are released under the GNU Affero General Public License v3.0 (AGPL-3.0): https://www.gnu.org/licenses/agpl-3.0.html
|
|
|