Update app.py

app.py

@@ -11,98 +11,123 @@ from numpy.linalg import norm
 from PIL import Image
 import zipfile
 
-# --- 1. ZIP DOSYASINI AÇMA ---
-# images klasörü yoksa zip'i açar.
-if not os.path.exists('images') and os.path.exists('images.zip'):
-    with st.spinner('Resim arşivi çıkartılıyor, bu işlem biraz zaman alabilir...'):
-        try:
-            with zipfile.ZipFile('images.zip', 'r') as zip_ref:
-                zip_ref.extractall('.')
-            st.success("Resimler başarıyla çıkartıldı!")
-        except Exception as e:
-            st.error(f"Zip açılırken hata oluştu: {e}")
-
-# Sayfa Ayarları
+# -----------------------------
+# 1 ZIP VARSA AÇ
+# -----------------------------
+if not os.path.exists("images"):
+    if os.path.exists("images.zip"):
+        with zipfile.ZipFile("images.zip", "r") as zip_ref:
+            zip_ref.extractall(".")
+        st.write("images klasörü zipten çıkarıldı")
+
+# -----------------------------
+# 2 SAYFA AYARI
+# -----------------------------
 st.set_page_config(page_title="Moda Öneri Sistemi", layout="centered")
-st.title('🛍️ Moda Öneri Sistemi')
+st.title("🛍️ Moda Öneri Sistemi")
 
-# --- 2. MODEL VE VERİLERİ YÜKLEME ---
+# -----------------------------
+# 3 MODEL YÜKLE
+# -----------------------------
 @st.cache_resource
-def load_data():
-    # ResNet50 Modelini Kur
-    base_model = ResNet50(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
+def load_model():
+
+    base_model = ResNet50(
+        weights='imagenet',
+        include_top=False,
+        input_shape=(224,224,3)
+    )
+
     base_model.trainable = False
-    model = tf.keras.models.Sequential([base_model, GlobalMaxPool2D()])
-    
-    # Pickle dosyalarını yükle
-    try:
-        with open('Images_features.pkl', 'rb') as f:
-            features = np.array(pkl.load(f))
-        with open('filenames.pkl', 'rb') as f:
-            filenames = pkl.load(f)
-        return model, features, filenames
-    except Exception as e:
-        st.error(f"Veri yükleme hatası (Pickle): {e}")
-        return None, None, None
-
-model, feature_list, filenames = load_data()
-
-# --- 3. ÖZELLİK ÇIKARMA FONKSİYONU ---
+
+    model = tf.keras.models.Sequential([
+        base_model,
+        GlobalMaxPool2D()
+    ])
+
+    return model
+
+model = load_model()
+
+# -----------------------------
+# 4 FEATURE VE DOSYA LİSTESİ
+# -----------------------------
+@st.cache_resource
+def load_data():
+
+    features = np.array(pkl.load(open("Images_features.pkl","rb")))
+    filenames = pkl.load(open("filenames.pkl","rb"))
+
+    return features, filenames
+
+feature_list, filenames = load_data()
+
+# -----------------------------
+# 5 FEATURE ÇIKAR
+# -----------------------------
 def extract_features(img_path, model):
-    img = image.load_img(img_path, target_size=(224, 224))
+
+    img = image.load_img(img_path, target_size=(224,224))
     img_array = image.img_to_array(img)
-    img_expand_dim = np.expand_dims(img_array, axis=0)
-    img_preprocess = preprocess_input(img_expand_dim)
-    result = model.predict(img_preprocess).flatten()
-    norm_result = result / norm(result)
-    return norm_result
-
-# --- 4. KULLANICI ARAYÜZÜ ---
-uploaded_file = st.file_uploader("Bir kıyafet resmi yükleyin...", type=['jpg', 'png', 'jpeg'])
-
-if uploaded_file is not None and model is not None:
-    # Yüklenen resmi göster
-    display_image = Image.open(uploaded_file)
-    st.image(display_image, width=300, caption='Yüklediğiniz Resim')
-    
-    # Resmi geçici olarak kaydet
-    temp_path = "temp_upload.jpg"
-    with open(temp_path, "wb") as f:
+
+    expanded = np.expand_dims(img_array, axis=0)
+
+    preprocessed = preprocess_input(expanded)
+
+    result = model.predict(preprocessed).flatten()
+
+    normalized = result / norm(result)
+
+    return normalized
+
+# -----------------------------
+# 6 RESİM YÜKLEME
+# -----------------------------
+uploaded_file = st.file_uploader("Bir kıyafet resmi yükleyin", type=["jpg","png","jpeg"])
+
+if uploaded_file is not None:
+
+    img = Image.open(uploaded_file)
+    st.image(img, width=300)
+
+    with open("temp.jpg","wb") as f:
         f.write(uploaded_file.getbuffer())
-    
-    # Önerileri Bul
-    with st.spinner('Benzer ürünler taranıyor...'):
-        input_features = extract_features(temp_path, model)
-        neighbors = NearestNeighbors(n_neighbors=6, algorithm='brute', metric='euclidean')
+
+    with st.spinner("Benzer ürünler aranıyor..."):
+
+        input_feature = extract_features("temp.jpg", model)
+
+        neighbors = NearestNeighbors(
+            n_neighbors=6,
+            algorithm="brute",
+            metric="euclidean"
+        )
+
         neighbors.fit(feature_list)
-        distances, indices = neighbors.kneighbors([input_features])
-    
-    st.markdown("---")
-    st.subheader('✨ Benzer Ürünler')
-    
-    # --- 5. AKILLI RESİM GÖSTERME SİSTEMİ ---
+
+        distances, indices = neighbors.kneighbors([input_feature])
+
+    st.subheader("✨ Benzer Ürünler")
+
+# -----------------------------
+# 7 RESİMLERİ GÖSTER
+# -----------------------------
     cols = st.columns(5)
-    
-    # Tüm resimleri tara ve küçük harf-yol eşleşmesi yap (Hata payını sıfırlar)
-    image_database = {}
-    if os.path.exists('images'):
-        for root, dirs, files in os.walk('images'):
-            for f in files:
-                image_database[f.lower()] = os.path.join(root, f)
-    
-    for i in range(1, 6):
+
+    for i in range(1,6):
+
         with cols[i-1]:
-            # Dosya adını temizle (C:\users\123.jpg -> 123.jpg)
-            full_raw_path = filenames[indices[0][i]].replace('\\', '/')
-            clean_name = os.path.basename(full_raw_path).lower()
-            
-            # Veritabanında (zip'ten çıkan dosyalarda) bu isim var mı?
-            if clean_name in image_database:
-                st.image(image_database[clean_name], use_container_width=True)
+
+            file_path = filenames[indices[0][i]]
+
+            file_name = os.path.basename(file_path)
+
+            image_path = os.path.join("images", file_name)
+
+            if os.path.exists(image_path):
+
+                st.image(image_path, use_container_width=True)
+
             else:
-                st.error(f"Eksik:\n{clean_name}")
 
-# Alt bilgi (Hata ayıklama için resim sayısını gösterir)
-if os.path.exists('images'):
-    count = sum([len(files) for r, d, files in os.walk('images')])
-    st.sidebar.write(f"Sistemdeki Toplam Resim: {count}")
+                st.write("Eksik:", file_name)