import gradio as gr
import tensorflow as tf
import numpy as np

num_classes = 200
IMG_HEIGHT = 300
IMG_WIDTH = 300

with open("classlabel.txt", 'r') as file:
    CLASS_LABEL = [x.strip() for x in file.readlines()]

def normalize_image(img):
    img = tf.image.random_flip_left_right(img)
    img = tf.cast(img, tf.float32) / 255.0
    img = tf.image.resize(img, (IMG_HEIGHT, IMG_WIDTH), method='bilinear')
    return img

def predict_top_classes(img, num_top_classes=5):
     img = img.convert('RGB')
     img_data = normalize_image(img)
     x = np.array(img_data)
     x = np.expand_dims(x, axis=0)
     temp = model.predict(x)
     
     idx = np.argsort(np.squeeze(temp))[::-1]
     top5_value = np.asarray([temp[0][i] for i in idx[0:5]])
     top5_idx = idx[0:5]
     
     return {CLASS_LABEL[i]:str(v) for i,v in zip(top5_idx,top5_value)}
    
model = tf.keras.models.load_model("Xception.h5")

interface = gr.Interface(predict_top_classes, gr.inputs.Image(type='pil'), outputs='label', args={'num_top_classes': 5})
interface.launch()