Update app.py

app.py

@@ -74,14 +74,14 @@ def load_index(index_path):
     """Load FAISS index once and cache it"""
     return faiss.read_index(index_path)
 
-def distance_to_similarity(distance, temp=1e-4):
+def distance_to_similarity(distances, temp=1e-4):
     """Convert distance to similarity"""
-    for ii in range(len(distance)):
-        contribs = distance[ii].max() - distance[ii]
+    for ii in range(len(distances)):
+        contribs = distances[ii].max() - distances[ii]
         contribs = contribs / temp
         sum_contribs = np.exp(contribs).sum()
-        distance[ii] = np.exp(contribs) / sum_contribs
-    return distance
+        distances[ii] = np.exp(contribs) / sum_contribs
+    return distances
 
 def calculate_rewards(subscription, num_generations, author_share, ro_share, num_users_k, similarities, num_authors=1800):
     """Calculate rewards based on user inputs and similarities"""
@@ -99,12 +99,6 @@ def calculate_rewards(subscription, num_generations, author_share, ro_share, num
         author_month_reward = (authors_monthly_revenue / num_authors) * attribution_bonus
         ro_month_reward = author_month_reward / (author_share / 100) * (ro_share / 100)
 
-        try:
-            sim_value = float(sim.item()) if hasattr(sim, "item") else float(sim)
-        except Exception as e:
-            print("Erreur de conversion de sim:", e)
-            sim_value = 0.0  # valeur par défaut en cas d'erreur
-
         rewards.append({
             'paid_per_month': f"{subscription:.0f}€",
             'attribution': f"{sim * 100:.0f}%",
@@ -179,15 +173,13 @@ def select_preset(preset_id):
         #image2 = load_image(PRESET_IMAGES[2])
         
         # Extraire les features
-        image1 = Image.open("static/1.webp")
-        image2 = Image.open("static/2.webp")
-        features1 = get_ft(model, image1)
-        features2 = get_ft(model, image2)
+        #image1 = Image.open("static/1.webp")
+        #image2 = Image.open("static/2.webp")
+        #features1 = get_ft(model, image1)
+        #features2 = get_ft(model, image2)
         
         # Calculer la distance euclidienne
-        distances = np.linalg.norm(features1 - features2)
-        
-        #print(f"Distance euclidienne entre l'image 1 et l'image 2 : {distances}")
+        #distances = np.linalg.norm(features1 - features2)
         
         # Collect valid results first
         valid_results = []