ariffaizin19/yolov5-sewaka-detc

YOLOv5 for Aksara Jawa

Supported Labels

[
    '1 Ha', '2 Na', '3 Ca', '4 Ra', '5 Ka', '6 Da', '7 Ta', '8 Sa', '9 Wa', '10 La', 
    '11 Pa', '12 Dha', '13 Ja', '14 Ya', '15 Nya', '16 Ma', '17 Ga', '18 Ba', '19 Tha', '20 Nga', 
    '21 Pasangan Ha', '22 Pasangan Na', '23 Pasangan Ca', '24 Pasangan Ra', '25 Pasangan Ka', 
    '26 Pasangan Da', '27 Pasangan Ta', '28 Pasangan Sa', '29 Pasangan Wa', '30 Pasangan La', 
    '31 Pasangan Pa', '32 Pasangan Dha', '33 Pasangan Ja', '34 Pasangan Ya', '35 Pasangan Nya', 
    '36 Pasangan Ma', '37 Pasangan Ga', '38 Pasangan Ba', '39 Pasangan Tha', '40 Pasangan Nga', 
    '41 Wulu', '42 Pepet', '43 Suku', '44 Taling', '45 Taling Tarung', 
    '46 Cecak', '47 Layar', '48 Pangkon', '49 Pengkol', '50 Wignyan', 
    '51 Cakra', '52 Pa Cerek', '53 Nga Lelet', '54 Pada Lingsa', '55 Pada Madya', '56 Purwa Pada', 
    '57 Murda Na', '58 Murda Ka', '59 Murda Ta', '60 Murda Sa', '61 Murda Pa', '63 Murda Ga', '64 Murda Ba', 
    '67 Pasangan Murda Ga', '71 Pasangan Murda Ta', 
    '73 Rekan Kha', '76 Rekan Za', 
    '81 Pasangan Murda Za', 
    '83 Swara A', '84 Swara E', '85 Swara U', '86 Swara I', 
    '95 Mahaprana Sha', '97 Cakra Keret'
]

How to use

• Install library

pip install yolov5==7.0.5 torch

Load model and perform prediction

import yolov5
from PIL import Image
model = yolov5.load(models_id)
model.overrides['conf'] = 0.25  # NMS confidence threshold
model.overrides['iou'] = 0.45  # NMS IoU threshold
model.overrides['max_det'] = 1000  # maximum number of detections per image
# set image
image = 'https://huggingface.co/spaces/ariffaizin19/yolov5-sewaka-detc/raw/main/test_images/example1.jpg'
# perform inference
results = model.predict(image)
# observe results
print(results[0].boxes)
render = render_result(model=model, image=image, result=results[0])
render.show()