fix gr.Label

app.py

@@ -1,4 +1,5 @@
-# app.py
+# app.py (potongan penting saja)
+
 import os
 import gradio as gr
 from inference import predict, predict_batch  
@@ -6,24 +7,11 @@ from inference import predict, predict_batch
 APP_TITLE = "# Face Shape Classification — EfficientNetB4 (300×300)"
 APP_DESC = """
 **Model:** EfficientNetB4 (ImageNet) fine-tuned pada 5 kelas: **Heart, Oblong, Oval, Round, Square**.  
-**Input:** Foto wajah **frontal** RGB (1 orang), di-resize otomatis ke **300×300**.  
-**Output:** Prediksi kelas + confidence.  
-**Catatan:** Untuk **penelitian/edukasi**, bukan untuk keputusan sensitif.
-"""
-APP_FAQ = """
-### FAQ
-- **Perlu normalisasi manual?** Tidak. Aplikasi menyesuaikan preprocessing internal model.
-- **Format gambar?** JPG/PNG, RGB.
-- **Privasi:** Gambar diproses saat inferensi dan tidak disimpan.
+**Val Acc (best): ~96%** · **Input:** Foto wajah **frontal** RGB (1 orang), auto-resize **300×300**.  
+**Output:** Prediksi + confidence (Top-5).  
+**Disclaimer:** Untuk penelitian/edukasi.
 """
 
-def _payload(d: dict):
-    items = sorted(d.items(), key=lambda kv: kv[1], reverse=True)
-    return {
-        "label": items[0][0],
-        "confidences": [{"label": k, "confidence": float(v)} for k, v in items],
-    }
-
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gr.Markdown(APP_TITLE)
     gr.Markdown(APP_DESC)
@@ -31,25 +19,18 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
     with gr.Row():
         inp = gr.Image(type="pil", label="Upload face (frontal)")
         out = gr.Label(num_top_classes=5, label="Predictions")
+
     with gr.Row():
         btn = gr.Button("Predict", variant="primary")
         gr.ClearButton([inp, out])
-    btn.click(lambda im: _payload(predict(im)), inputs=inp, outputs=out)
 
-    with gr.Accordion("ℹ️ Detail & FAQ", open=False):
-        gr.Markdown(APP_FAQ)
+    btn.click(predict, inputs=inp, outputs=out)
 
     with gr.Tab("Batch (optional)"):
-        gal = gr.Gallery(label="Images", columns=4, height="auto")
+        gal = gr.Gallery(label="Images", columns=4, height="auto")   
         out_gal = gr.JSON(label="Batch outputs")
         runb = gr.Button("Run batch")
         runb.click(predict_batch, inputs=gal, outputs=out_gal)
 
-    if os.path.exists("examples"):
-        gr.Examples(
-            examples=[os.path.join("examples", f) for f in os.listdir("examples")],
-            inputs=inp
-        )
-
 if __name__ == "__main__":
     demo.launch()