README.md

metadata

tags:
  - yolov5
  - yolo
  - vision
  - object-detection
  - pytorch
library_name: yolov5
library_version: 7.0.6
inference: true
datasets:
  - niki-stha/asl-detection-roboflow
model-index:
  - name: niki-stha/asl-detection-yolov5
    results:
      - task:
          type: object-detection
        dataset:
          type: niki-stha/asl-detection-roboflow
          name: niki-stha/asl-detection-roboflow
          split: validation
        metrics:
          - type: precision
            value: 0.9854910682105946
            name: mAP@0.5

How to use

• Install yolov5:

pip install -U yolov5

• Load model and perform prediction:

import yolov5

# load model
model = yolov5.load('niki-stha/asl-detection-yolov5')
  
# set model parameters
model.conf = 0.80  # NMS confidence threshold
model.iou = 0.45  # 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 = 'https://datasets-server.huggingface.co/assets/niki-stha/asl-detection-roboflow/--/niki-stha--asl-detection-roboflow/test/2/image/image.jpg'

# perform inference
results = model(img, size=640)

# inference with test time augmentation
results = model(img, augment=True)

# parse results
predictions = results.pred[0]
boxes = predictions[:, :4] # x1, y1, x2, y2
scores = predictions[:, 4]
categories = predictions[:, 5]

# show detection bounding boxes on image
results.show()

# save results into "results/" folder
results.save(save_dir='results/')

• Finetune the model on your custom dataset:

yolov5 train --data data.yaml --img 416 --batch 32 --weights keremberke/yolov5s-license-plate --epochs 10

More models available at: awesome-yolov5-models