README.md

metadata

tags:
  - yolov5
  - yolo
  - vision
  - object-detection
  - biology
  - climate
library_name: yolov5
library_version: 7.0.7
inference: false
model-index:
  - name: mbari-org/megamidwater
    results:
      - task:
          type: object-detection
        metrics:
          - type: precision
            value: 0.73555
            name: mAP@0.5
license: apache-2.0
language:
  - en
pipeline_tag: object-detection

How to use

• Install yolov5:

pip install -U yolov5

• Load model and perform prediction:

import yolov5
model = yolov5.load('MBARI-org/megamidwater')

# Run the yolo
# set model parameters
model.conf = 0.25  # NMS confidence threshold
model.iou = 0.1  # NMS IoU threshold
model.agnostic = False  # NMS class-agnostic
model.multi_label = False  # NMS multiple labels per box
model.max_det = 1000  # maximum number of detections per image

# set image
img = 'http://dsg.mbari.org/images/dsg/external/Ctenophora/Deiopea_01.png'

# perform inference
results = model(img, size=1280)

# print results
print(results.pandas().xyxy[0])

• Finetune the model on your custom dataset:

yolov5 train --data data.yaml --img 1280 --batch 16 --weights mbari-org/megamidwater --epochs 10