#BOHOL #Philippines #Scuba diving #Sea ecology #App #Flask
Download : https://drive.google.com/file/d/1-L5U2JCJG73HMfHJNIBsK9123N1yaHqf/view
# weights → tf
python save_model.py --weights ./data/yolov4-obj_best.weights --output ./checkpoints/bohol-416 --input_size 416 --model yolov4
created a 16 category saltwater fish dataset with roughly 200 images for each class.
16개의 클래스, 클래스 별 약 200장의 이미지 라벨링.
거북이 클래스 불균형..
Class_id | Name | Count |
---|---|---|
0 | Green_sea_turtle | 630 |
1 | Anthias | 287 |
2 | Blonde_naso_tang | 210 |
3 | Blue_damsel | 208 |
4 | Brown_tang | 248 |
5 | Domino_damsel | 259 |
6 | Foxface_rabbitfish | 227 |
7 | Jackfish | 254 |
8 | Lionfish | 315 |
9 | Regal_angelfish | 320 |
10 | Scissortail_sergeant_major_fish | 221 |
11 | Sergeant_major_fish | 183 |
12 | Snowflake_moray | 342 |
13 | Three_stripes_damsel | 271 |
14 | Tomato_clown | 193 |
15 | Yellow_boxfish | 308 |
Total | 4476 |
# image
python detect.py --weights ./checkpoints/bohol-416 --size 416 --model yolov4 --images ./data/images/img1.jpg
# video
python detect_video.py --weights ./checkpoints/bohol-416 --size 416 --model yolov4 --video ./data/video/vid1.mp4 --output ./detections/best2/vid1.avi