app,py.py

import cv2
from cvzone.HandTrackingModule import HandDetector
from cvzone.ClassificationModule import Classifier
import numpy as np
import math
import gradio as gr

#cap = cv2.VideoCapture(0)
detector = HandDetector(maxHands=1)
classifier = Classifier("Model/keras_model.h5", "Model/labels.txt")

offset = 20
imgSize = 300

folder = "Data/C"
counter = 0

labels = ["A", "B"]


def sign(img):
    #img = cv2.imread("sign.jpg")
    imgOutput = cv2.flip(img.copy(),1)
    hands, img = detector.findHands(cv2.flip(img[:,:,::-1],1))
    if hands:
        print('hand detected')
        hand = hands[0]
        x, y, w, h = hand['bbox']

        imgWhite = np.ones((imgSize, imgSize, 3), np.uint8) * 255
        imgCrop = img[y - offset:y + h + offset, x - offset:x + w + offset]

        imgCropShape = imgCrop.shape

        aspectRatio = h / w

        if aspectRatio > 1:
            k = imgSize / h
            wCal = math.ceil(k * w)
            imgResize = cv2.resize(imgCrop, (wCal, imgSize))
            imgResizeShape = imgResize.shape
            wGap = math.ceil((imgSize - wCal) / 2)
            imgWhite[:, wGap:wCal + wGap] = imgResize
            prediction, index = classifier.getPrediction(imgWhite, draw=False)
            print(prediction, index)

        else:
            k = imgSize / w
            hCal = math.ceil(k * h)
            imgResize = cv2.resize(imgCrop, (imgSize, hCal))
            imgResizeShape = imgResize.shape
            hGap = math.ceil((imgSize - hCal) / 2)
            imgWhite[hGap:hCal + hGap, :] = imgResize
            prediction, index = classifier.getPrediction(imgWhite, draw=False)

        
        cv2.rectangle(imgOutput, (x-offset, y-offset),
                      (x + w+offset, y + h+offset), (255, 0, 255), 4)
        imgOutput = cv2.flip(imgOutput,1)
        #cv2.rectangle(imgOutput, (x - offset, y - offset-50),
        #              (x - offset+90, y - offset-50+50), (255, 0, 255), cv2.FILLED)
        #cv2.putText(imgOutput, labels[index], (x, y -26), cv2.FONT_HERSHEY_COMPLEX, 1.7, (255, 255, 255), 2)
        cv2.rectangle(imgOutput, (30,30),
                      (80,80), (255, 0, 255), cv2.FILLED)
        cv2.putText(imgOutput, labels[index], (30, 80), cv2.FONT_HERSHEY_COMPLEX, 1.7, (255, 255, 255), 2)


        #cv2.imshow("ImageCrop", imgCrop)
        #cv2.imshow("ImageWhite", imgWhite)

    #cv2.imshow("Image", imgOutput)
    return imgOutput

with gr.Blocks() as demo:
  with gr.Tabs():
    with gr.TabItem('Webcam'):
      with gr.Row():
        with gr.Column():
          img_input2 = gr.Webcam()
          image_button2 = gr.Button("Submit")

        with gr.Column():
          output2 = gr.outputs.Image()

    image_button2.click(fn=sign,
        inputs = img_input2,
        outputs = output2) 

demo.launch(debug=True)