import gradio as gr
import tensorflow as tf
import numpy as np
from PIL import Image






# Initial parameters for pretrained model
IMG_SIZE = 300

labelsBreast = {'Benign':0,
                'Malignant':1,
                'Normal':2}

# Load the model from the H5 file
model = tf.keras.models.load_model('model/BreastCancer.h5')

# Define the prediction function
def predict(img):
    img_height = 224
    img_width = 224

    # Convert the NumPy array to a PIL Image object
    pil_img = Image.fromarray(img)

    # Resize the image using the PIL Image object
    pil_img = pil_img.resize((img_height, img_width))

    # Convert the PIL Image object to a NumPy array
    x = tf.keras.preprocessing.image.img_to_array(pil_img)

    x = x.reshape(1, img_height, img_width, 3)
    np.set_printoptions(formatter={'float': '{: 0.3f}'.format})


    predi = model.predict(x)
    accuracy_of_class = '{:.1f}'.format(predi[0][np.argmax(predi)] * 100) + "%"
    classes = list(labelsBreast.keys())[np.argmax(predi)]
    context = {
        'predictedLabel': classes,
        # 'y_class': y_class,
        # 'z_class': z_class,
        'accuracy_of_class': accuracy_of_class
    }


   
    return context



demo = gr.Interface(fn=predict, inputs="image", outputs="text" , examples=[["b1.png"],["b2.png"]],)

demo.launch()