Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,7 +1,6 @@
 import streamlit as st
 import numpy as np
 from PIL import Image
-import base64
 import io
 from tensorflow.keras.models import load_model
 
@@ -10,48 +9,40 @@ st.set_page_config(page_title="Hurma Sınıflandırıcı", layout="centered")
 st.title("📷 Hurma Resmi Sınıflandırma")
 st.write("Lütfen bir hurma resmi yükleyin ve hangi tür olduğunu tahmin edelim.")
 
-# --- MODEL ---
-try:
-    model = load_model("src/dates_classifier_model.h5")
-except Exception as e:
-    st.error(f"Model yüklenemedi: {e}")
-    st.stop()
+# Model yükleniyor
+@st.cache_resource
+def load_model_cached():
+    return load_model("src/dates_classifier_model.h5")
+
+model = load_model_cached()
 
 class_names = [
     'Rutab', 'Meneifi', 'Sokari', 'Galaxy', 'Shaishe',
     'Medjool', 'Ajwa', 'Nabtat Ali', 'Sugaey'
 ]
 
-# --- IMAGE SESSION ---
-def image_to_base64(image_bytes):
-    return base64.b64encode(image_bytes).decode("utf-8")
-
-def base64_to_image(base64_str):
-    return Image.open(io.BytesIO(base64.b64decode(base64_str))).convert("RGB")
-
+# Fotoğraf işleme fonksiyonu
 def process_image(img):
     img = img.resize((224, 224))
     img = np.array(img) / 255.0
     img = np.expand_dims(img, axis=0)
     return img
 
-if "image_data" not in st.session_state:
-    st.session_state.image_data = None
-
+# Dosya yükleme
 uploaded_file = st.file_uploader("Resim Seç (.jpg, .jpeg, .png)", type=["jpg", "jpeg", "png"])
 
 if uploaded_file is not None:
-    st.session_state.image_data = image_to_base64(uploaded_file.read())
-
-if st.session_state.image_data:
     try:
-        img = base64_to_image(st.session_state.image_data)
-        st.image(img, caption="Yüklenen Resim", use_column_width=True)
+        # BytesIO üzerinden oku
+        image = Image.open(io.BytesIO(uploaded_file.read())).convert("RGB")
+        st.image(image, caption="Yüklenen Resim", use_column_width=True)
 
-        processed_img = process_image(img)
-        prediction = model.predict(processed_img)
+        # Tahmin
+        processed = process_image(image)
+        prediction = model.predict(processed)
         predicted_class = np.argmax(prediction)
 
-        st.success(f"Tahmin: **{class_names[predicted_class]}**")
+        st.success(f"Tahmin edilen sınıf: **{class_names[predicted_class]}**")
+
     except Exception as e:
-        st.error(f"Fotoğraf işlenemedi: {e}")
+        st.error(f"Resim işlenemedi: {e}")