Upload app.py

app.py

@@ -1,43 +1,65 @@
-import gradio as gr
 from PIL import Image
-import random
-
-# 💡 Placeholder classifier — replace with actual model or API call
-def classify_mushroom(image):
-    # Simulate prediction
-    prediction = random.choice(["Edible", "Poisonous"])
-    confidence = round(random.uniform(0.7, 0.99), 2)
-
-    bilingual_map = {
-        "Edible": "กินได้",
-        "Poisonous": "พิษ"
-    }
-
-    return {
-        "Prediction (EN)": prediction,
-        "คำทำนาย (TH)": bilingual_map[prediction],
-        "Confidence": f"{confidence * 100:.1f}%"
-    }
-
-# 🧪 Gradio App UI
-with gr.Blocks() as demo:
-    gr.Markdown("## 🍄 Mushroom Safety Classifier")
-    gr.Markdown("Upload a photo of a mushroom to check if it's edible or poisonous.\nอัปโหลดรูปเห็ดเพื่อทำนายว่าเห็ดกินได้หรือมีพิษ")
-
-    with gr.Row():
-        image_input = gr.Image(type="pil", label="📷 Upload Mushroom Image")
-        with gr.Column():
-            label_en = gr.Textbox(label="🧠 Prediction (English)")
-            label_th = gr.Textbox(label="🗣️ คำทำนาย (ภาษาไทย)")
-            confidence = gr.Textbox(label="📶 Confidence Score")
-
-    classify_btn = gr.Button("🔍 Classify")
-
-    # 🔁 Connect button to function
-    classify_btn.click(
-        fn=classify_mushroom,
-        inputs=image_input,
-        outputs=[label_en, label_th, confidence]
-    )
-
-demo.launch()
+from transformers import pipeline
+import gradio as gr
+
+# 🌐 Load pre-trained image classification model
+classifier = pipeline("image-classification", model="microsoft/resnet-50")
+
+# 🔍 Define bilingual label mapping
+label_map = {
+    "agaric": ("Edible", "กินได้"),
+    "bolete": ("Edible", "กินได้"),
+    "gyromitra": ("Poisonous", "พิษ"),
+    "amanita": ("Poisonous", "พิษ"),
+    "earthstar": ("Edible", "กินได้"),
+    "hen-of-the-woods": ("Edible", "กินได้"),
+    "mushroom": ("Unknown", "ไม่ทราบ"),
+    "coral fungus": ("Poisonous", "พิษ"),
+    # Add more if needed
+}
+
+# 🧠 Classification function
+def classify_mushroom(image: Image.Image):
+    print("✅ classify_mushroom: NEW VERSION")
+
+    try:
+        image = image.convert("RGB")
+        result = classifier(image)
+        print("🔍 Raw result from model:", result)
+
+        result = result[0]
+        label = result['label'].lower()
+        score = round(result['score'] * 100, 2)
+
+        prediction_en, prediction_th = label_map.get(label, ("Unknown", "ไม่ทราบ"))
+        print("✅ RETURNING:", prediction_en, prediction_th, f"{score:.2f}%", label)
+
+        return prediction_en, prediction_th, f"{score:.2f}%", label
+
+    except Exception as e:
+        print(f"❌ Error: {e}")
+        return "Error", "ผิดพลาด", "N/A", "N/A"
+
+# 🎨 Gradio UI
+if __name__ == "__main__":
+    with gr.Blocks() as demo:
+        gr.Markdown("## 🍄 Mushroom Safety Classifier")
+        gr.Markdown("Upload a mushroom photo to check if it’s edible or poisonous.\nอัปโหลดรูปเห็ดเพื่อทำนายว่าเห็ดกินได้หรือมีพิษ")
+
+        with gr.Row():
+            image_input = gr.Image(type="pil", label="📷 Upload Mushroom Image")
+            with gr.Column():
+                label_en = gr.Textbox(label="🧠 Prediction (English)")
+                label_th = gr.Textbox(label="🗣️ คำทำนาย (ภาษาไทย)")
+                confidence = gr.Textbox(label="📶 Confidence Score")
+                label_raw = gr.Textbox(label="🏷️ Predicted Mushroom Name")
+
+        classify_btn = gr.Button("🔍 Classify")
+
+        classify_btn.click(
+            fn=classify_mushroom,
+            inputs=image_input,
+            outputs=[label_en, label_th, confidence, label_raw]
+        )
+
+    demo.launch()