app.py

# Available backend options are: "jax", "torch", "tensorflow".
import os
#os.environ["KERAS_BACKEND"] = "tensorflow"
#pip install -U keras huggingface_hub

#import keras

#model = keras.saving.load_model("hf://Fluospark128/Cassava_Disease_Classifier")

import streamlit as st
import tensorflow as tf
import numpy as np
from PIL import Image

# Load the model
#@st.cache_resource
def load_model():
    model = tf.keras.models.load_model("cassava_leaf_disease_model.keras") #tf.keras.saving.load_model("hf://Fluospark128/Cassava_Disease_Classifier") cassava_model.h5
    return model

model = load_model()

# Class labels
CLASS_NAMES = ["Cassava Bacterial Blight Disease", "Cassava Brown Streak Disease", "Cassava Green Mottle Disease",  "Cassava Mosaic Disease", "Healthy"]

# Streamlit UI
st.title("Cassava Leaf Disease Identifier")
st.write("Upload an image of a cassava leaf to identify its disease.")

# File uploader
uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "png", "jpeg"])

if uploaded_file is not None:
    image = Image.open(uploaded_file).resize((224, 224))
    st.image(image, caption="Uploaded Image", use_column_width=True)

    # Preprocess image
    img_array = np.array(image) / 255.0  # Normalize
    img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension

    # Make prediction
    prediction = model.predict(img_array)
    predicted_class = CLASS_NAMES[np.argmax(prediction)]

    st.write(f"Prediction: **{predicted_class}**")