Update app.py

app.py

@@ -1,5 +1,5 @@
 import streamlit as st
-from transformers import pipeline
+from transformers import pipeline, AutoImageProcessor
 from PIL import Image, ImageDraw
 import torch
 
@@ -20,12 +20,30 @@ st.markdown("""
         --background-color: #ffffff;
         --text-color: #1f2937;
         --border-color: #e5e7eb;
+        --button-color: #2563eb;
+        --button-hover: #1d4ed8;
     }
     
     [data-theme="dark"] {
         --background-color: #1f2937;
         --text-color: #f3f4f6;
         --border-color: #4b5563;
+        --button-color: #3b82f6;
+        --button-hover: #2563eb;
+    }
+    
+    .stButton > button {
+        background-color: var(--button-color) !important;
+        color: white !important;
+        border: none !important;
+        padding: 0.5rem 1rem !important;
+        border-radius: 0.375rem !important;
+        font-weight: 500 !important;
+        transition: background-color 0.2s !important;
+    }
+    
+    .stButton > button:hover {
+        background-color: var(--button-hover) !important;
     }
     
     .block-container {
@@ -66,6 +84,11 @@ st.markdown("""
     
     .row-widget.stButton {
         text-align: center;
+        margin: 1rem 0;
+    }
+    
+    div[data-testid="stFileUploader"] {
+        width: 100%;
     }
 </style>
 """, unsafe_allow_html=True)
@@ -74,8 +97,12 @@ st.markdown("""
 def load_models():
     return {
         "KnochenAuge": pipeline("object-detection", model="D3STRON/bone-fracture-detr"),
-        "KnochenWächter": pipeline("image-classification", model="Heem2/bone-fracture-detection-using-xray"),
-        "RöntgenMeister": pipeline("image-classification", model="nandodeomkar/autotrain-fracture-detection-using-google-vit-base-patch-16-54382127388")
+        "KnochenWächter": pipeline("image-classification", 
+            model="Heem2/bone-fracture-detection-using-xray",
+            image_processor=AutoImageProcessor.from_pretrained("Heem2/bone-fracture-detection-using-xray")),
+        "RöntgenMeister": pipeline("image-classification", 
+            model="nandodeomkar/autotrain-fracture-detection-using-google-vit-base-patch-16-54382127388",
+            image_processor=AutoImageProcessor.from_pretrained("nandodeomkar/autotrain-fracture-detection-using-google-vit-base-patch-16-54382127388"))
     }
 
 def draw_boxes(image, predictions):
@@ -101,36 +128,77 @@ def main():
     models = load_models()
     
     st.markdown("### 📤 Röntgenbilder Upload")
-    uploaded_files = st.file_uploader("", type=['png', 'jpg', 'jpeg'], accept_multiple_files=True)
+    
+    # File uploader avec label caché
+    uploaded_files = st.file_uploader(
+        "Wählen Sie Röntgenbilder aus",
+        type=['png', 'jpg', 'jpeg'],
+        accept_multiple_files=True,
+        label_visibility="collapsed"
+    )
     
     if uploaded_files:
-        col1, col2 = st.columns([1, 1])
-        
-        for idx, uploaded_file in enumerate(uploaded_files):
-            image = Image.open(uploaded_file)
+        # Bouton d'analyse
+        if st.button("Bilder analysieren", key="analyze_button"):
+            col1, col2 = st.columns([1, 1])
+            
+            for idx, uploaded_file in enumerate(uploaded_files):
+                image = Image.open(uploaded_file)
+                
+                # Analyse avec KnochenAuge (localisierung)
+                predictions = models["KnochenAuge"](image)
+                fractures_found = any(p['label'].lower() == 'fracture' and p['score'] > 0.6 for p in predictions)
+                
+                # Afficher uniquement si des fractures sont détectées
+                if fractures_found:
+                    with col1 if idx % 2 == 0 else col2:
+                        result_image = image.copy()
+                        result_image = draw_boxes(result_image, predictions)
+                        st.image(result_image, caption=f"Bild {idx + 1}", use_column_width=True)
+                        
+                        # Analyse KnochenWächter et RöntgenMeister
+                        pred_wachter = models["KnochenWächter"](image)[0]
+                        pred_meister = models["RöntgenMeister"](image)[0]
+                        
+                        if pred_wachter['score'] > 0.6 or pred_meister['score'] > 0.6:
+                            st.markdown(f"""
+                                <div class='result-box'>
+                                    <span style='color: #2563eb'>KnochenWächter:</span> {pred_wachter['score']:.1%}<br>
+                                    <span style='color: #2563eb'>RöntgenMeister:</span> {pred_meister['score']:.1%}
+                                </div>
+                            """, unsafe_allow_html=True)
+
+    # Script pour la synchronisation du thème
+    st.markdown("""
+        <script>
+            // Fonction pour mettre à jour le thème
+            function updateTheme(isDark) {
+                document.documentElement.setAttribute('data-theme', isDark ? 'dark' : 'light');
+                
+                // Mise à jour des styles en fonction du thème
+                const root = document.documentElement;
+                if (isDark) {
+                    root.style.setProperty('--background-color', '#1f2937');
+                    root.style.setProperty('--text-color', '#f3f4f6');
+                    root.style.setProperty('--border-color', '#4b5563');
+                } else {
+                    root.style.setProperty('--background-color', '#ffffff');
+                    root.style.setProperty('--text-color', '#1f2937');
+                    root.style.setProperty('--border-color', '#e5e7eb');
+                }
+            }
             
-            # Analyse avec KnochenAuge (localisierung)
-            predictions = models["KnochenAuge"](image)
-            fractures_found = any(p['label'].lower() == 'fracture' and p['score'] > 0.6 for p in predictions)
+            // Écouter les messages du parent
+            window.addEventListener('message', function(e) {
+                if (e.data.type === 'theme-change') {
+                    updateTheme(e.data.theme === 'dark');
+                }
+            });
             
-            # Afficher uniquement si des fractures sont détectées
-            if fractures_found:
-                with col1 if idx % 2 == 0 else col2:
-                    result_image = image.copy()
-                    result_image = draw_boxes(result_image, predictions)
-                    st.image(result_image, caption=f"Bild {idx + 1}", use_column_width=True)
-                    
-                    # Analyse KnochenWächter et RöntgenMeister
-                    pred_wachter = models["KnochenWächter"](image)[0]
-                    pred_meister = models["RöntgenMeister"](image)[0]
-                    
-                    if pred_wachter['score'] > 0.6 or pred_meister['score'] > 0.6:
-                        st.markdown(f"""
-                            <div class='result-box'>
-                                <span style='color: #2563eb'>KnochenWächter:</span> {pred_wachter['score']:.1%}<br>
-                                <span style='color: #2563eb'>RöntgenMeister:</span> {pred_meister['score']:.1%}
-                            </div>
-                        """, unsafe_allow_html=True)
+            // Thème initial basé sur les préférences système
+            updateTheme(window.matchMedia('(prefers-color-scheme: dark)').matches);
+        </script>
+    """, unsafe_allow_html=True)
 
 if __name__ == "__main__":
     main()