Update app.py

app.py

@@ -40,12 +40,11 @@ model = Classifier()
 model.load_state_dict(torch.load("classify_nsfw_v3.0.pth", map_location="cpu"))
 model.eval()
 
-# ---------------- PREDICT ----------------
+# ---------------- FUNZIONE ----------------
 def predict(base64_input: str):
     if not base64_input:
         return "Nessun input fornito", {}
 
-    # se arriva "data:image/jpeg;base64,...."
     if base64_input.startswith("data:image"):
         base64_input = base64_input.split(",", 1)[1]
 
@@ -62,7 +61,7 @@ def predict(base64_input: str):
 
     return max_label, probs_dict
 
-# ---------------- HELPERS ----------------
+# ---------------- HELPER ----------------
 def image_to_base64(img: Image.Image):
     if img is None:
         return ""
@@ -70,9 +69,9 @@ def image_to_base64(img: Image.Image):
     img.save(buf, format="JPEG", quality=90)
     return "data:image/jpeg;base64," + base64.b64encode(buf.getvalue()).decode("utf-8")
 
-# ---------------- UI ----------------
+# ---------------- INTERFACCIA ----------------
 with gr.Blocks(title="NSFW Classifier") as demo:
-    gr.Markdown("## 🎨 NSFW Image Classifier\nCarica un'immagine o incolla una stringa base64.\n\nAPI disponibile su **/api/predict**")
+    gr.Markdown("## 🎨 NSFW Image Classifier\nCarica un'immagine o incolla la stringa base64.\n\nAPI standard: **/api/predict**")
 
     with gr.Row():
         with gr.Column(scale=2):
@@ -87,10 +86,10 @@ with gr.Blocks(title="NSFW Classifier") as demo:
             label_output = gr.Textbox(label="Classe predetta")
             result_display = gr.Label(label="Distribuzione probabilità", num_top_classes=len(labels))
 
-    # immagine -> converte in base64
+    # immagine → converte in base64 → textbox
     img_input.change(fn=image_to_base64, inputs=img_input, outputs=base64_input)
 
-    # unico endpoint API
+    # unico endpoint API standard
     analyze_btn.click(fn=predict,
                       inputs=base64_input,
                       outputs=[label_output, result_display],
@@ -98,7 +97,6 @@ with gr.Blocks(title="NSFW Classifier") as demo:
 
     clear_btn.click(fn=lambda: "", inputs=None, outputs=base64_input)
 
-# ---------------- LAUNCH ----------------
+# ---------------- AVVIO ----------------
 if __name__ == "__main__":
     demo.launch()
-