Hugging Face's logo

mayrajeo
/
marine-vessel-detection-yolov8

ultralytics
satellite imagery
marine traffic
sentinel-2
yolov8
Eval Results
Model card Files Community
mayrajeo commited on
Commit
dde1d4d
•
1 Parent(s): 05a1662

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -22
README.md CHANGED
@@ -13,7 +13,7 @@ model-index:
13
  type: object-detection
14
  metrics:
15
  - type: precision
16
- value: 0.801
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 1|2022-06-19|519|271|269|
86
- |Archipelago sea 1|2022-07-21|1518|387|153|
87
- |Archipelago sea 1|2022-08-13|1368|402|138|
88
- |Gulf of Finland|2022-06-06|275|138|241|
89
- |Gulf of Finland|2022-06-26|1190|269|110|
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
- |Archipelago sea 2|2021-07-14|433|
114
- |Archipelago sea 2|2022-06-24|413|
115
- |Archipelago sea 2|2022-08-13|391|
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 | 0.85001 | 0.840136 | 0.82782 | 0.82951 | 0.804012 | 0.78738 | 0.38816 | 0.380828 | 0.37637 | 0.84525 | 0.833424 | 0.81883 |
146
- | yolov8s | 0.86717 | 0.854216 | 0.84347 | 0.84939 | 0.84065 | 0.83222 | 0.41098 | 0.406258 | 0.40374 | 0.86933 | 0.861404 | 0.84934 |
147
- | yolov8m | 0.86108 | 0.853192 | 0.84191 | 0.87385 | 0.846722 | 0.83 | 0.41739 | 0.410742 | 0.40496 | 0.87772 | 0.862594 | 0.84602 |
148
- | yolov8l | 0.86911 | 0.863254 | 0.85604 | 0.86468 | 0.841572 | 0.82725 | 0.41694 | 0.411712 | 0.40505 | 0.88288 | 0.867134 | 0.85743 |
149
- | yolov8x | 0.86411 | 0.856008 | 0.85045 | 0.86086 | 0.845044 | 0.83029 | 0.42065 | 0.411532 | 0.40231 | 0.87069 | 0.863538 | 0.85316 |
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| 0.7639|0.833611| 0.766|0.290|
157
- |yolov8s| 4| 0.776751|0.845133| 0.784|0.304|
158
- |yolov8m| 4| 0.790741|0.857435| 0.801|0.324|
159
- |yolov8l| 1| 0.772199|0.851569| 0.797|0.326|
160
- |yolov8x| 1| 0.780507|0.838783| 0.788|0.319|
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