src/streamlit_app.py

import streamlit as st
import numpy as np
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing import image
from tensorflow.keras.applications.efficientnet import preprocess_input
from PIL import Image

model = load_model("src/best_efficientnet_model.keras")

class_names = [
    'apple', 'banana', 'beetroot', 'bell pepper', 'cabbage', 'capsicum', 'carrot',
    'cauliflower', 'chilli pepper', 'corn', 'cucumber', 'eggplant', 'garlic', 'ginger',
    'grapes', 'jalepeno', 'kiwi', 'lemon', 'lettuce', 'mango', 'onion', 'orange',
    'paprika', 'pear', 'peas', 'pineapple', 'pomegranate', 'potato', 'raddish',
    'soy beans', 'spinach', 'sweetcorn', 'sweetpotato', 'tomato', 'turnip', 'watermelon'
]

st.title("Fruit and Vegetable Recognition")

st.markdown("Upload an image of a fruit or vegetable. The model will predict its class.")

uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])

if uploaded_file is not None:
    img = Image.open(uploaded_file).convert("RGB")
    st.image(img, caption="Uploaded Image", use_container_width=True)

    img = img.resize((300, 300))
    img_array = image.img_to_array(img)
    img_array = np.expand_dims(img_array, axis=0)
    img_array = preprocess_input(img_array)

    predictions = model.predict(img_array)
    predicted_index = np.argmax(predictions)
    predicted_label = class_names[predicted_index]
    confidence = predictions[0][predicted_index] * 100

    st.markdown(f"### Prediction: **{predicted_label}**")