Update app.py

app.py

@@ -3,15 +3,14 @@ import numpy as np
 from PIL import Image, ImageDraw, ImageFont
 import cv2
 import os
+import tempfile
 from nudenet import NudeDetector
-import concurrent.futures
 
 # --- Konstanten ---
 DETECTION_MAX_DIM = 768
 PIXELS_PER_CM_ESTIMATE = 15
 MIN_CONFIDENCE = 0.45
 
-# Initialisiere den Detektor
 detector = NudeDetector(inference_resolution=640)
 
 def resize_for_detection(img_pil, max_dim):
@@ -25,26 +24,28 @@ def resize_for_detection(img_pil, max_dim):
 
 def describe_breast_precise(crop_pil):
     w, h = crop_pil.size
-    if w * h == 0: return "Fehler: leeres Crop"
+    if w * h == 0:
+        return "Fehler: leeres Crop"
     gray = cv2.cvtColor(np.array(crop_pil), cv2.COLOR_RGB2GRAY)
     _, thresh = cv2.threshold(gray, 100, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
     contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
     nipple_detected = any(
-        40 < cv2.contourArea(c) < (w * h / 4) and
-        (p := cv2.arcLength(c, True)) > 0 and
-        (4 * np.pi * cv2.contourArea(c) / (p * p)) > 0.55
+        40 < cv2.contourArea(c) < (w * h / 4)
+        and (p := cv2.arcLength(c, True)) > 0
+        and (4 * np.pi * cv2.contourArea(c) / (p * p)) > 0.55
         for c in contours
     )
     ratio = w / h
     shape = "Breit" if ratio > 1.15 else "Hoch" if ratio < 0.85 else "Rund"
-    size = "klein" if w*h < 28000 else "mittel" if w*h < 75000 else "groß" if w*h < 140000 else "sehr groß"
+    size = "klein" if w * h < 28000 else "mittel" if w * h < 75000 else "groß" if w * h < 140000 else "sehr groß"
     w_cm = round(w / PIXELS_PER_CM_ESTIMATE, 1)
     h_cm = round(h / PIXELS_PER_CM_ESTIMATE, 1)
     return f"Brust: {shape}, {size}, Nippel: {'Ja' if nipple_detected else 'Nein'}, {w_cm}x{h_cm}cm"
 
 def describe_vagina_precise(crop_pil):
     w, h = crop_pil.size
-    if w * h == 0: return "Fehler: leeres Crop"
+    if w * h == 0:
+        return "Fehler: leeres Crop"
     gray = cv2.cvtColor(np.array(crop_pil), cv2.COLOR_RGB2GRAY)
     hair_ratio = np.sum(cv2.inRange(gray, 35, 145) > 0) / (w * h)
     shaved = "rasiert" if hair_ratio < 0.04 else "minimal" if hair_ratio < 0.13 else "Brazilian" if hair_ratio < 0.36 else "behaart"
@@ -68,63 +69,71 @@ def process_image(image_path):
         original_pil = Image.open(image_path).convert("RGB")
         detection_pil, scale = resize_for_detection(original_pil, DETECTION_MAX_DIM)
         detections = detector.detect(np.array(detection_pil))
-        
+
         draw = ImageDraw.Draw(original_pil)
-        # Versuche eine Schriftart zu laden, sonst Standard
         try:
             font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf", 20)
-        except:
+        except Exception:
             font = ImageFont.load_default()
 
         results_text = []
-        
+
         for det in detections:
             label = det["class"]
             score = det.get("score", 0)
             if score < MIN_CONFIDENCE:
                 continue
-            
+
             if label not in ["FEMALE_BREAST_EXPOSED", "FEMALE_GENITALIA_EXPOSED"]:
                 continue
-                
+
             x, y, w, h = [int(v * scale) for v in det["box"]]
             crop_pil = original_pil.crop((x, y, x + w, y + h))
-            
+
             if label == "FEMALE_BREAST_EXPOSED":
                 desc = describe_breast_precise(crop_pil)
-                color = (255, 46, 130) # Pink
+                color = (255, 46, 130)
             else:
                 desc = describe_vagina_precise(crop_pil)
-                color = (138, 43, 226) # Purple
-            
-            # Zeichne Box
+                color = (138, 43, 226)
+
             draw.rectangle([x, y, x + w, y + h], outline=color, width=4)
-            # Zeichne Text-Hintergrund
             text_pos = (x, y - 25 if y > 25 else y + h)
             draw.text(text_pos, desc, fill=color, font=font)
             results_text.append(desc)
 
         if not results_text:
-            # Wenn nichts gefunden wurde, gib das Originalbild mit Hinweis zurück
             draw.text((10, 10), "Keine relevanten Bereiche erkannt.", fill=(255, 0, 0), font=font)
-            return original_pil
 
         return original_pil
+
     except Exception as e:
         print(f"Fehler: {e}")
         return None
 
 def analyze_all(files):
     if not files:
-        return None
-    
+        return [], []
+
     processed_images = []
+    output_files = []
+
+    output_dir = os.path.join(tempfile.gettempdir(), "gradio_analyzer_outputs")
+    os.makedirs(output_dir, exist_ok=True)
+
     for f in files:
         res = process_image(f.name)
-        if res:
-            processed_images.append(res)
-    
-    return processed_images
+        if res is None:
+            continue
+
+        processed_images.append(res)
+
+        base_name = os.path.splitext(os.path.basename(f.name))[0]
+        out_path = os.path.join(output_dir, f"{base_name}_analyzed.png")
+        res.save(out_path)
+        output_files.append(out_path)
+
+    return processed_images, output_files
 
 custom_css = """
 body { background: #0f0f1a; color: #e0e0ff; }
@@ -132,18 +141,34 @@ body { background: #0f0f1a; color: #e0e0ff; }
 h1 { color: #ff2e82; text-align: center; }
 """
 
-with gr.Blocks(css=custom_css, theme=gr.themes.Soft(primary_hue="pink")) as demo:
+with gr.Blocks() as demo:
     gr.Markdown("# 👙 Automatischer Nackt-Analyzer")
-    gr.Markdown("Lade Bilder hoch für eine automatische Analyse von Brüsten und Vagina. Die Ergebnisse werden direkt im Bild angezeigt.")
-    
+    gr.Markdown("Lade Bilder hoch für eine automatische Analyse. Die Ergebnisse werden im Bild angezeigt und zusätzlich als Dateien bereitgestellt.")
+
     with gr.Row():
         input_files = gr.File(file_count="multiple", label="Bilder hochladen")
-    
+
+    with gr.Row():
+        output_gallery = gr.Gallery(
+            label="Analyse-Ergebnisse",
+            columns=2,
+            height="auto"
+        )
+
     with gr.Row():
-        output_gallery = gr.Gallery(label="Analyse-Ergebnisse", columns=2, height="auto", show_download_button=True)
-    
-    # Automatischer Trigger bei Upload
-    input_files.change(fn=analyze_all, inputs=input_files, outputs=output_gallery)
+        output_downloads = gr.File(
+            label="Analysierte Bilder herunterladen",
+            file_count="multiple"
+        )
+
+    input_files.change(
+        fn=analyze_all,
+        inputs=input_files,
+        outputs=[output_gallery, output_downloads]
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(
+        css=custom_css,
+        theme=gr.themes.Soft(primary_hue="pink")
+    )