red_cube_yolo

Ultralytics YOLO 객체 탐지 λͺ¨λΈμž…λ‹ˆλ‹€. ν•™μŠ΅ μ‹€ν–‰ cube 의 κ²°κ³Όμž…λ‹ˆλ‹€.

  • 클래슀 (1개): cube
  • μž…λ ₯ 해상도: 640 x 640
  • 베이슀 λͺ¨λΈ: yolo26n.pt

μ„±λŠ₯

79 epoch ν•™μŠ΅ ν›„ validation κ²°κ³Όμž…λ‹ˆλ‹€.

μ§€ν‘œ κ°’
Precision 0.9100
Recall 0.9275
mAP@50 0.9657
mAP@50-95 0.9637

μ‚¬μš©λ²•

pip install ultralytics huggingface_hub
from huggingface_hub import hf_hub_download
from ultralytics import YOLO

weights = hf_hub_download("roboseasylabs/red_cube_yolo", "best.pt")
model = YOLO(weights)

results = model.predict("image.jpg", conf=0.25, iou=0.45)
results[0].show()

ν•™μŠ΅ μ„€μ •

ν•­λͺ© κ°’
베이슀 κ°€μ€‘μΉ˜ yolo26n.pt
epochs 200
imgsz 640
batch 16
patience 20

데이터셋 Β· νŒŒμ΄ν”„λΌμΈ

ν•œκ³„

  • 단일 ν™˜κ²½μ—μ„œ μˆ˜μ§‘ν•œ λ°μ΄ν„°λ‘œ ν•™μŠ΅ν–ˆμŠ΅λ‹ˆλ‹€. λ°°κ²½Β·μ‘°λͺ…·카메라가 λ°”λ€Œλ©΄ μ„±λŠ₯이 λ–¨μ–΄μ§ˆ 수 μžˆμŠ΅λ‹ˆλ‹€.
  • 640x640 μž…λ ₯ κΈ°μ€€μž…λ‹ˆλ‹€. μ•„μ£Ό μž‘κ²Œ 찍힌 λ¬Όμ²΄λŠ” 놓칠 수 μžˆμŠ΅λ‹ˆλ‹€.
Downloads last month
68
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Evaluation results