src/streamlit_app.py

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

# Şimdi model mimarisini kuruyoruz

model = tf.keras.models.Sequential([
    
    tf.keras.layers.Conv2D(32, (3,3), activation="relu", input_shape=(128,128,3)),
    tf.keras.layers.MaxPooling2D(2,2),

    tf.keras.layers.Conv2D(64, (3,3), activation="relu"),
    tf.keras.layers.MaxPooling2D(2,2),

    tf.keras.layers.Conv2D(128, (3,3), activation="relu"),
    tf.keras.layers.MaxPooling2D(2,2),

    tf.keras.layers.Conv2D(256, (3,3), activation="relu"),
    tf.keras.layers.MaxPooling2D(2,2),

    tf.keras.layers.Conv2D(256, (3,3), activation="relu"),

    tf.keras.layers.Flatten(),

    tf.keras.layers.Dense(256, activation="relu"),
    tf.keras.layers.Dropout(0.3),

    tf.keras.layers.Dense(36, activation="softmax")
])

model.load_weights("src/fruit_veg_cnn.weights.h5")

# Şimdi sınıf isimlerini yazıyoruz

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("CNN ile Meyve Sebze Sınıflandırma")

st.write("Bir meyve veya sebze görseli yükleyin.")

# Kullanıcıdan görsel alıyoruz

uploaded_file = st.file_uploader(
    "Bir görsel yükleyin",
    type=["jpg", "jpeg", "png"]
)

# tahmin işlemini yapıyoruz

if uploaded_file is not None:

    image = Image.open(uploaded_file).convert("RGB")

    st.image(image, caption="Yüklenen Görsel", use_container_width=True)

    image = image.resize((128,128))

    image_array = np.array(image) / 255.0

    image_array = np.expand_dims(image_array, axis=0)

    prediction = model.predict(image_array)

    predicted_index = np.argmax(prediction)

    predicted_class = class_names[predicted_index]

    confidence = np.max(prediction) * 100

    st.success(f"Tahmin: {predicted_class}")

    st.write(f"Güven Oranı: %{confidence:.2f}")