Oriented Bounding Boxes Object Detection
๋ฐฉํฅ์ฑ ๋ฌผ์ฒด ๊ฐ์ง๋ ๋ฌผ์ฒด ๊ฐ์ง๋ณด๋ค ํ ๋จ๊ณ ๋ ๋์๊ฐ ์ด๋ฏธ์ง์์ ๋ฌผ์ฒด๋ฅผ ๋ ์ ํํ๊ฒ ์ฐพ์ ์ ์๋๋ก ์ถ๊ฐ ๊ฐ๋๋ฅผ ๋์ ํฉ๋๋ค.
๋ฐฉํฅ์ฑ ๊ฐ์ฒด ๊ฐ์ง๊ธฐ์ ์ถ๋ ฅ์ ์ด๋ฏธ์ง์์ ๊ฐ์ฒด๋ฅผ ์ ํํ ๋๋ฌ์ธ๋ ํ์ ๋ ๊ฒฝ๊ณ ์์ ์งํฉ๊ณผ ๊ฐ ์์์ ๋ํ ํด๋์ค ๋ ์ด๋ธ ๋ฐ ์ ๋ขฐ๋ ์ ์๋ก ํ์๋ฉ๋๋ค. ๊ฐ์ฒด ๊ฐ์ง๋ ์ฅ๋ฉด์์ ๊ด์ฌ ์๋ ๊ฐ์ฒด๋ฅผ ์๋ณํด์ผ ํ์ง๋ง ๊ฐ์ฒด์ ์ ํํ ์์น๋ ๋ชจ์์ ์ ํํ ์ ํ์๋ ์๋ ๊ฒฝ์ฐ์ ์ ํฉํ ์ ํ์ ๋๋ค.
ํ
YOLO11 OBB models use the -obb
์ ๋ฏธ์ฌ, ์ฆ yolo11n-obb.pt
์ ๋ํด ์ฌ์ ๊ต์ก์ ๋ฐ์์ผ๋ฉฐ DOTAv1.
Watch: Object Detection using Ultralytics YOLO Oriented Bounding Boxes (YOLO-OBB)
์๊ฐ์ ์ํ
OBB๋ฅผ ์ฌ์ฉํ ์ ๋ฐ ๊ฐ์ง | OBB๋ฅผ ์ฌ์ฉํ ์ฐจ๋ ๊ฐ์ง |
---|---|
๋ชจ๋ธ
YOLO11 pretrained OBB models are shown here, which are pretrained on the DOTAv1 dataset.
๋ชจ๋ธ์ ์ฒ์ ์ฌ์ฉํ ๋ ์ต์ Ultralytics ๋ฆด๋ฆฌ์ค์์ ์๋์ผ๋ก ๋ค์ด๋ก๋๋ฉ๋๋ค.
๋ชจ๋ธ | ํฌ๊ธฐ (ํฝ์ ) |
mAPtest 50 |
์๋ CPU ONNX (ms) |
Speed T4 TensorRT10 (ms) |
๋งค๊ฐ๋ณ์ (M) |
FLOPs (B) |
---|---|---|---|---|---|---|
YOLO11n-obb | 1024 | 78.4 | 117.6 ยฑ 0.8 | 4.4 ยฑ 0.0 | 2.7 | 17.2 |
YOLO11s-obb | 1024 | 79.5 | 219.4 ยฑ 4.0 | 5.1 ยฑ 0.0 | 9.7 | 57.5 |
YOLO11m-obb | 1024 | 80.9 | 562.8 ยฑ 2.9 | 10.1 ยฑ 0.4 | 20.9 | 183.5 |
YOLO11l-obb | 1024 | 81.0 | 712.5 ยฑ 5.0 | 13.5 ยฑ 0.6 | 26.2 | 232.0 |
YOLO11x-obb | 1024 | 81.3 | 1408.6 ยฑ 7.7 | 28.6 ยฑ 1.0 | 58.8 | 520.2 |
- mAPtest ๊ฐ์ ๋จ์ผ ๋ชจ๋ธ ๋ฉํฐ์ค์ผ์ผ์์ DOTAv1 ๋ฐ์ดํฐ ์ธํธ.
๋ณต์ ๋์yolo val obb data=DOTAv1.yaml device=0 split=test
์ ํด๋ฆญํ๊ณ ๋ณํฉ๋ ๊ฒฐ๊ณผ๋ฅผ ๋ค์ ์ฃผ์๋ก ์ ์ถํฉ๋๋ค. DOTA ํ๊ฐ. - ์๋ ๋ฅผ ์ฌ์ฉํ์ฌ DOTAv1 val ์ด๋ฏธ์ง์ ๋ํ ํ๊ท ๊ฐ์ Amazon EC2 P4d ์ธ์คํด์ค.
๋ณต์ ๋์yolo val obb data=DOTAv1.yaml batch=1 device=0|cpu
๊ธฐ์ฐจ
Train YOLO11n-obb on the dota8.yaml
dataset for 100 epochs at image size 640. For a full list of available arguments see the ๊ตฌ์ฑ ํ์ด์ง๋ก ์ด๋ํฉ๋๋ค.
์
from ultralytics import YOLO
# Load a model
model = YOLO("yolo11n-obb.yaml") # build a new model from YAML
model = YOLO("yolo11n-obb.pt") # load a pretrained model (recommended for training)
model = YOLO("yolo11n-obb.yaml").load("yolo11n.pt") # build from YAML and transfer weights
# Train the model
results = model.train(data="dota8.yaml", epochs=100, imgsz=640)
# Build a new model from YAML and start training from scratch
yolo obb train data=dota8.yaml model=yolo11n-obb.yaml epochs=100 imgsz=640
# Start training from a pretrained *.pt model
yolo obb train data=dota8.yaml model=yolo11n-obb.pt epochs=100 imgsz=640
# Build a new model from YAML, transfer pretrained weights to it and start training
yolo obb train data=dota8.yaml model=yolo11n-obb.yaml pretrained=yolo11n-obb.pt epochs=100 imgsz=640
Watch: How to Train Ultralytics YOLO-OBB (Oriented Bounding Boxes) Models on DOTA Dataset using Ultralytics HUB
๋ฐ์ดํฐ ์งํฉ ํ์
OBB ๋ฐ์ดํฐ์ ํ์์ ๋ฐ์ดํฐ์ ๊ฐ์ด๋์์ ์์ธํ ํ์ธํ ์ ์์ต๋๋ค.
Val
Validate trained YOLO11n-obb model accuracy on the DOTA8 dataset. No arguments are needed as the model
๊ต์ก ์ ์ง data
๋ฐ ์ธ์๋ฅผ ๋ชจ๋ธ ์์ฑ์ผ๋ก ์ฌ์ฉํฉ๋๋ค.
์
from ultralytics import YOLO
# Load a model
model = YOLO("yolo11n-obb.pt") # load an official model
model = YOLO("path/to/best.pt") # load a custom model
# Validate the model
metrics = model.val(data="dota8.yaml") # no arguments needed, dataset and settings remembered
metrics.box.map # map50-95(B)
metrics.box.map50 # map50(B)
metrics.box.map75 # map75(B)
metrics.box.maps # a list contains map50-95(B) of each category
์์ธก
Use a trained YOLO11n-obb model to run predictions on images.
์
Watch: How to Detect and Track Storage Tanks using Ultralytics YOLO-OBB | Oriented Bounding Boxes | DOTA
์ ์ฒด ๋ณด๊ธฐ predict
๋ชจ๋ ์ธ๋ถ ์ ๋ณด์์ ์์ธก ํ์ด์ง๋ก ์ด๋ํฉ๋๋ค.
๋ด๋ณด๋ด๊ธฐ
Export a YOLO11n-obb model to a different format like ONNX, CoreML, etc.
์
Available YOLO11-obb export formats are in the table below. You can export to any format using the format
์ธ์, ์ฆ format='onnx'
๋๋ format='engine'
. ๋ด๋ณด๋ธ ๋ชจ๋ธ์์ ์ง์ ์์ธกํ๊ฑฐ๋ ์ ํจ์ฑ์ ๊ฒ์ฌํ ์ ์์ต๋๋ค. yolo predict model=yolo11n-obb.onnx
. ๋ด๋ณด๋ด๊ธฐ๊ฐ ์๋ฃ๋ ํ ๋ชจ๋ธ์ ๋ํ ์ฌ์ฉ ์๊ฐ ํ์๋ฉ๋๋ค.
ํ์ | format ์ธ์ |
๋ชจ๋ธ | ๋ฉํ๋ฐ์ดํฐ | ์ธ์ |
---|---|---|---|---|
PyTorch | - | yolo11n-obb.pt |
โ | - |
TorchScript | torchscript |
yolo11n-obb.torchscript |
โ | imgsz , optimize , batch |
ONNX | onnx |
yolo11n-obb.onnx |
โ | imgsz , half , dynamic , simplify , opset , batch |
OpenVINO | openvino |
yolo11n-obb_openvino_model/ |
โ | imgsz , half , int8 , batch |
TensorRT | engine |
yolo11n-obb.engine |
โ | imgsz , half , dynamic , simplify , workspace , int8 , batch |
CoreML | coreml |
yolo11n-obb.mlpackage |
โ | imgsz , half , int8 , nms , batch |
TF SavedModel | saved_model |
yolo11n-obb_saved_model/ |
โ | imgsz , keras , int8 , batch |
TF GraphDef | pb |
yolo11n-obb.pb |
โ | imgsz , batch |
TF Lite | tflite |
yolo11n-obb.tflite |
โ | imgsz , half , int8 , batch |
TF Edge TPU | edgetpu |
yolo11n-obb_edgetpu.tflite |
โ | imgsz |
TF.js | tfjs |
yolo11n-obb_web_model/ |
โ | imgsz , half , int8 , batch |
PaddlePaddle | paddle |
yolo11n-obb_paddle_model/ |
โ | imgsz , batch |
NCNN | ncnn |
yolo11n-obb_ncnn_model/ |
โ | imgsz , half , batch |
์ ์ฒด ๋ณด๊ธฐ export
์ธ๋ถ ์ ๋ณด์์ ๋ด๋ณด๋ด๊ธฐ ํ์ด์ง๋ก ์ด๋ํฉ๋๋ค.
์์ฃผ ๋ฌป๋ ์ง๋ฌธ
OBB(์ค๋ฆฌ์ํฐ๋ ๋ฐ์ด๋ฉ ๋ฐ์ค)๋ ๋ฌด์์ด๋ฉฐ ์ผ๋ฐ ๋ฐ์ด๋ฉ ๋ฐ์ค์ ์ด๋ป๊ฒ ๋ค๋ฅธ๊ฐ์?
OBB(์ค๋ฆฌ์ํฐ๋ ๋ฐ์ด๋ฉ ๋ฐ์ค)๋ ์ด๋ฏธ์ง์์ ๊ฐ์ฒด์ ์์น ์ ํ๋๋ฅผ ๋์ด๊ธฐ ์ํด ์ถ๊ฐ ๊ฐ๋๋ฅผ ํฌํจํฉ๋๋ค. ์ถ์ด ์ ๋ ฌ๋ ์ง์ฌ๊ฐํ์ธ ์ผ๋ฐ ๋ฐ์ด๋ฉ ๋ฐ์ค์ ๋ฌ๋ฆฌ OBB๋ ๊ฐ์ฒด์ ๋ฐฉํฅ์ ๋ ์ ๋ง๋๋ก ํ์ ํ ์ ์์ต๋๋ค. ์ด๋ ํญ๊ณต ๋๋ ์์ฑ ์ด๋ฏธ์ง์ ๊ฐ์ด ์ ํํ ๊ฐ์ฒด ๋ฐฐ์น๊ฐ ํ์ํ ์ ํ๋ฆฌ์ผ์ด์ ์ ํนํ ์ ์ฉํฉ๋๋ค(๋ฐ์ดํฐ ์ธํธ ๊ฐ์ด๋).
How do I train a YOLO11n-obb model using a custom dataset?
To train a YOLO11n-obb model with a custom dataset, follow the example below using Python or CLI:
์
๋ ๋ง์ ๊ต์ก ์ธ์๋ฅผ ํ์ธํ๋ ค๋ฉด ๊ตฌ์ฑ ์น์ ์ ํ์ธํ์ธ์.
What datasets can I use for training YOLO11-OBB models?
YOLO11-OBB models are pretrained on datasets like DOTAv1 but you can use any dataset formatted for OBB. Detailed information on OBB dataset formats can be found in the Dataset Guide.
How can I export a YOLO11-OBB model to ONNX format?
Exporting a YOLO11-OBB model to ONNX format is straightforward using either Python or CLI:
์
๋ด๋ณด๋ด๊ธฐ ํ์ ๋ฐ ์์ธํ ๋ด์ฉ์ ๋ด๋ณด๋ด๊ธฐ ํ์ด์ง๋ฅผ ์ฐธ์กฐํ์ธ์.
How do I validate the accuracy of a YOLO11n-obb model?
To validate a YOLO11n-obb model, you can use Python or CLI commands as shown below:
์
Val ์น์ ์์ ์ ์ฒด ์ ํจ์ฑ ๊ฒ์ฌ ์ธ๋ถ ์ ๋ณด๋ฅผ ํ์ธํ์ธ์.