Update README.md
Browse files
README.md
CHANGED
@@ -13,7 +13,7 @@ model-index:
|
|
13 |
type: object-detection
|
14 |
metrics:
|
15 |
- type: precision
|
16 |
-
value: 0.
|
17 |
name: mAP@0.5(box)
|
18 |
---
|
19 |
|
@@ -21,8 +21,6 @@ model-index:
|
|
21 |
|
22 |
<!-- Provide a quick summary of what the model is/does. -->
|
23 |
|
24 |
-
TBA
|
25 |
-
|
26 |
## Model Details
|
27 |
|
28 |
### Model Description
|
@@ -82,11 +80,11 @@ Training and validation data:
|
|
82 |
|
83 |
|Location|Date|Number of annotations|Annotated patches|Background patches|
|
84 |
|-----|----|-------|------|------|
|
85 |
-
|Archipelago sea
|
86 |
-
|Archipelago sea
|
87 |
-
|Archipelago sea
|
88 |
-
|Gulf of Finland|2022-06-06|
|
89 |
-
|Gulf of Finland|2022-06-26|
|
90 |
|Gulf of Finland|2022-07-21|971|260|119|
|
91 |
|Bothnian Bay|2022-06-27|122|81|88|
|
92 |
|Bothnian Bay|2022-07-12|162|98|71|
|
@@ -110,9 +108,9 @@ Test data consists of six Sentinel-2 mosaics:
|
|
110 |
|
111 |
|Location|Date|Number of annotations|
|
112 |
|--------|----|---------------------|
|
113 |
-
|
|
114 |
-
|
|
115 |
-
|
|
116 |
|Kvarken|2022-06-17|79|
|
117 |
|Kvarken|2022-07-12|167|
|
118 |
|Kvarken|2022-08-26|81|
|
@@ -142,22 +140,21 @@ Precision and Recall with IoU-threshold of 0.5, mAP50 and mAP.
|
|
142 |
|
143 |
| Model | ('Precision', 'max') | ('Precision', 'mean') | ('Precision', 'min') | ('Recall', 'max') | ('Recall', 'mean') | ('Recall', 'min') | ('mAP', 'max') | ('mAP', 'mean') | ('mAP', 'min') | ('mAP50', 'max') | ('mAP50', 'mean') | ('mAP50', 'min') |
|
144 |
|:--------|-----------------------:|------------------------:|-----------------------:|--------------------:|---------------------:|--------------------:|-----------------:|------------------:|-----------------:|-------------------:|--------------------:|-------------------:|
|
145 |
-
| yolov8n |
|
146 |
-
| yolov8s |
|
147 |
-
| yolov8m |
|
148 |
-
| yolov8l |
|
149 |
-
| yolov8x |
|
150 |
-
|
151 |
|
152 |
Models with best performance for test set for each model architecture:
|
153 |
|
154 |
| Model | Fold | Precision | Recall | mAP50 | mAP |
|
155 |
|:------|------|-----------|--------|-------|-----|
|
156 |
-
|yolov8n| 1|
|
157 |
-
|yolov8s| 4| 0.
|
158 |
-
|yolov8m| 4| 0.
|
159 |
-
|yolov8l| 1| 0.
|
160 |
-
|yolov8x| 1| 0.
|
161 |
|
162 |
### Compute Infrastructure
|
163 |
|
|
|
13 |
type: object-detection
|
14 |
metrics:
|
15 |
- type: precision
|
16 |
+
value: 0.810
|
17 |
name: mAP@0.5(box)
|
18 |
---
|
19 |
|
|
|
21 |
|
22 |
<!-- Provide a quick summary of what the model is/does. -->
|
23 |
|
|
|
|
|
24 |
## Model Details
|
25 |
|
26 |
### Model Description
|
|
|
80 |
|
81 |
|Location|Date|Number of annotations|Annotated patches|Background patches|
|
82 |
|-----|----|-------|------|------|
|
83 |
+
|Archipelago sea|2022-06-19|519|271|269|
|
84 |
+
|Archipelago sea|2022-07-21|1518|387|153|
|
85 |
+
|Archipelago sea|2022-08-13|1368|402|138|
|
86 |
+
|Gulf of Finland|2022-06-06|278|138|241|
|
87 |
+
|Gulf of Finland|2022-06-26|1206|269|110|
|
88 |
|Gulf of Finland|2022-07-21|971|260|119|
|
89 |
|Bothnian Bay|2022-06-27|122|81|88|
|
90 |
|Bothnian Bay|2022-07-12|162|98|71|
|
|
|
108 |
|
109 |
|Location|Date|Number of annotations|
|
110 |
|--------|----|---------------------|
|
111 |
+
|Bothnian sea|2021-07-14|433|
|
112 |
+
|Bothnian sea|2022-06-24|413|
|
113 |
+
|Bothnian sea|2022-08-13|391|
|
114 |
|Kvarken|2022-06-17|79|
|
115 |
|Kvarken|2022-07-12|167|
|
116 |
|Kvarken|2022-08-26|81|
|
|
|
140 |
|
141 |
| Model | ('Precision', 'max') | ('Precision', 'mean') | ('Precision', 'min') | ('Recall', 'max') | ('Recall', 'mean') | ('Recall', 'min') | ('mAP', 'max') | ('mAP', 'mean') | ('mAP', 'min') | ('mAP50', 'max') | ('mAP50', 'mean') | ('mAP50', 'min') |
|
142 |
|:--------|-----------------------:|------------------------:|-----------------------:|--------------------:|---------------------:|--------------------:|-----------------:|------------------:|-----------------:|-------------------:|--------------------:|-------------------:|
|
143 |
+
| yolov8n | 0.806493 | 0.787567 | 0.774563 | 0.844089 | 0.827987 | 0.809585 | 0.288 | 0.2826 | 0.275 | 0.771 | 0.7492 | 0.73 |
|
144 |
+
| yolov8s | 0.82737 | 0.816531 | 0.809291 | 0.867093 | 0.852268 | 0.842173 | 0.309 | 0.3044 | 0.298 | 0.789 | 0.7776 | 0.763 |
|
145 |
+
| yolov8m | 0.849967 | 0.824472 | 0.804688 | 0.874121 | 0.856741 | 0.832588 | 0.323 | 0.3162 | 0.311 | 0.81 | 0.784 | 0.765 |
|
146 |
+
| yolov8l | 0.837152 | 0.823104 | 0.811286 | 0.867093 | 0.860703 | 0.854313 | 0.323 | 0.3206 | 0.315 | 0.795 | 0.7888 | 0.782 |
|
147 |
+
| yolov8x | 0.830968 | 0.821126 | 0.804322 | 0.86262 | 0.852013 | 0.823003 | 0.32 | 0.3132 | 0.301 | 0.793 | 0.781 | 0.752 |
|
|
|
148 |
|
149 |
Models with best performance for test set for each model architecture:
|
150 |
|
151 |
| Model | Fold | Precision | Recall | mAP50 | mAP |
|
152 |
|:------|------|-----------|--------|-------|-----|
|
153 |
+
|yolov8n| 1| 0.794348|0.844089| 0.771|0.288|
|
154 |
+
|yolov8s| 4| 0.817963|0.867093| 0.784|0.303|
|
155 |
+
|yolov8m| 4| 0.825090|0.874121| 0.810|0.323|
|
156 |
+
|yolov8l| 1| 0.811603|0.867093| 0.795|0.322|
|
157 |
+
|yolov8x| 1| 0.825183|0.862620| 0.793|0.317|
|
158 |
|
159 |
### Compute Infrastructure
|
160 |
|