app.py

import gradio as gr
import cv2
import requests
from ultralytics import YOLO

model = YOLO('best.pt')
path = [['image.jpg'],]
classes = ['ain', 'al', 'aleff','bb','dal','dha','dhad','fa','gaaf','ghain','ha','haa','jeem','kaaf','khaa','la','laam',
        'meem','nun','ra','saad','seen','sheen','ta','taa','thaa','thal','toot','waw','ya','yaa','zay']
TargetMapper = dict(zip(range(32),classes))
def show_preds_image(image_path):
    print(image_path)
    image = cv2.imread(image_path)
    outputs = model.predict(source=image_path)
    print(outputs)
    print(outputs[0])

    results = outputs[0]#.cpu().numpy()
    #for i, det in enumerate(results.boxes.xyxy):
    cls = TargetMapper[results.boxes.cls[0]]
    print(results.boxes)
    print(results[0].boxes)
    det = results.boxes.xyxy[0]
    #print(det)
    #print(cls)
    cv2.rectangle(
        image,
        (int(det[0]), int(det[1])),
        (int(det[2]), int(det[3])),
        color=(0, 0, 255),
        thickness=2,
        lineType=cv2.LINE_AA
    )
    cv2.putText(image, cls, (int(det[0]), int(det[1])-10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (36,255,12), 2)

    return cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

#image = cv2.imwrite('output.jpg', show_preds_image(path))
inputs_image = [
    gr.components.Image(type="filepath", label="Input Image"),
]
outputs_image = [
    gr.components.Image(type="numpy", label="Output Image"),
]
gr.Interface(
    fn=show_preds_image,
    inputs=inputs_image,
    outputs=outputs_image,
    title="Arab Sign Language Detection app",
    examples=path,
    cache_examples=False,
).launch()