README.md

metadata

tags:
  - ultralyticsplus
  - yolov8
  - ultralytics
  - yolo
  - vision
  - image-classification
  - pytorch
  - awesome-yolov8-models
library_name: ultralytics
library_version: 8.0.23
inference: false
datasets:
  - keremberke/painting-style-classification
model-index:
  - name: keremberke/yolov8m-painting-classification
    results:
      - task:
          type: image-classification
        dataset:
          type: keremberke/painting-style-classification
          name: painting-style-classification
          split: validation
        metrics:
          - type: accuracy
            value: 0.05723
            name: top1 accuracy
          - type: accuracy
            value: 0.21463
            name: top5 accuracy

Supported Labels

['Abstract_Expressionism', 'Action_painting', 'Analytical_Cubism', 'Art_Nouveau_Modern', 'Baroque', 'Color_Field_Painting', 'Contemporary_Realism', 'Cubism', 'Early_Renaissance', 'Expressionism', 'Fauvism', 'High_Renaissance', 'Impressionism', 'Mannerism_Late_Renaissance', 'Minimalism', 'Naive_Art_Primitivism', 'New_Realism', 'Northern_Renaissance', 'Pointillism', 'Pop_Art', 'Post_Impressionism', 'Realism', 'Rococo', 'Romanticism', 'Symbolism', 'Synthetic_Cubism', 'Ukiyo_e']

How to use

• Install ultralyticsplus:

pip install ultralyticsplus==0.0.24 ultralytics==8.0.23

• Load model and perform prediction:

from ultralyticsplus import YOLO, postprocess_classify_output

# load model
model = YOLO('keremberke/yolov8m-painting-classification')

# set model parameters
model.overrides['conf'] = 0.25  # model confidence threshold

# set image
image = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'

# perform inference
results = model.predict(image)

# observe results
print(results[0].probs) # [0.1, 0.2, 0.3, 0.4]
processed_result = postprocess_classify_output(model, result=results[0])
print(processed_result) # {"cat": 0.4, "dog": 0.6}

More models available at: awesome-yolov8-models