Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,11 @@ tags:
|
|
| 6 |
- detection
|
| 7 |
- fish
|
| 8 |
- marine biology
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
# Model Card for YOLOv8 based Otolith detection
|
| 11 |
|
|
@@ -21,3 +26,10 @@ This results in two distinct caveats:
|
|
| 21 |
(NOTE: Remember that this requires careful partition of the dataset by specimen, and not by image, as to avoid data leakage)
|
| 22 |
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
- detection
|
| 7 |
- fish
|
| 8 |
- marine biology
|
| 9 |
+
- yolo
|
| 10 |
+
- yolov8
|
| 11 |
+
- ultralytics
|
| 12 |
+
language:
|
| 13 |
+
- en
|
| 14 |
---
|
| 15 |
# Model Card for YOLOv8 based Otolith detection
|
| 16 |
|
|
|
|
| 26 |
(NOTE: Remember that this requires careful partition of the dataset by specimen, and not by image, as to avoid data leakage)
|
| 27 |
|
| 28 |
|
| 29 |
+
## Training Information
|
| 30 |
+
|
| 31 |
+
To train the model, we used a data cohort from 2020, consisting of 333 images of Blue whiting, manually labelled using RoboFlow, and split it into Training (80%) / Validation (10%) / Holdout-Test (10%).
|
| 32 |
+
|
| 33 |
+
Additionally, after training, we performed inference on the cohorts from 2021 and 2022, consisting of a total of 2018 images, and visually validated their quality as they had no labels.
|
| 34 |
+
|
| 35 |
+
All images are the same size, 1280x960.
|