appp.py

import streamlit as st
import tensorflow as tf
from PIL import Image
import os

model = tf.keras.models.load_model('Brain_tumor/')
st.write('Model is loaded successfully')

TEMP_DIR = 'temp'
if not os.path.exists(TEMP_DIR):
    os.makedirs(TEMP_DIR)

class_names = ['glioma', 'meningioma', 'notumor', 'pituitary']

def load_and_prep_imgg(filename ,img_shape=229, scale=True):

  img = tf.io.read_file(filename)

  img = tf.io.decode_image(img)

  img = tf.image.resize(img,size=[img_shape,img_shape])

  if scale :
    return img/255
  else :
    return img
      
st.title('Brain Tumor Classidfication Predition using Xception ImageNet ')

uploaded_file = st.sidebar.file_uploader('Upload your Image', type=['jpg'])

if uploaded_file:
    
    #file_path = os.path.join(uploaded_file.name)
    img = load_and_prep_imgg(uploaded_file.name,scale=True)
    imgg = Image.open(uploaded_file.name)
    st.image(img,caption ="Predicted brain tumor is : {pred_class} with probs : {pred_img:max():.2f}" )
    
    pred_img = model.predict(tf.expand_dims(img,axis=0))
    pred_class = class_names[pred_img.argmax()]
    st.write(f"Predicted brain tumor is : {pred_class} with probs : {pred_img:max():.2f}")