Update app.py

app.py

@@ -1,63 +1,76 @@
+# ================================
+# ENVIRONMENT (MUST BE FIRST)
+# ================================
 import os
-os.environ["TF_ENABLE_ONEDNN_OPTS"] = "0"
+os.environ["KERAS_BACKEND"] = "tensorflow"
+os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
 
+# ================================
+# IMPORTS
+# ================================
 import gradio as gr
 import tensorflow as tf
 import numpy as np
 import pickle
 from PIL import Image
 
-# ======================
-# LOAD MODEL
-# ======================
+# ================================
+# CONSTANTS (MUST MATCH TRAINING)
+# ================================
+IMG_SIZE = (128, 128)
+MAX_LEN = 50
+LABELS = ["Critical", "High", "Medium", "Low"]
+
+# ================================
+# LOAD MODEL (KERAS 3 SAFE)
+# ================================
 model = tf.keras.models.load_model(
-    "fusion_ticket_model_final.keras",
+    "fusion_model_keras3.keras",
     compile=False
 )
-
 print("✅ Fusion model loaded")
 
-# ======================
+# ================================
 # LOAD TOKENIZER
-# ======================
+# ================================
 with open("tokenizer.pkl", "rb") as f:
     tokenizer = pickle.load(f)
 
 print("✅ Tokenizer loaded")
 
-# ======================
-# CONSTANTS
-# ======================
-IMG_SIZE = (128, 128)
-MAX_LEN = 50
-LABELS = ["Critical", "High", "Medium", "Low"]
-
-# ======================
-# PREPROCESS IMAGE
-# ======================
+# ================================
+# IMAGE PREPROCESS
+# ================================
 def preprocess_image(image: Image.Image):
     image = image.convert("RGB")
     image = image.resize(IMG_SIZE)
     img = np.array(image, dtype=np.float32) / 255.0
-    return np.expand_dims(img, axis=0)
+    img = np.expand_dims(img, axis=0)
+    return img
 
-# ======================
-# PREPROCESS TEXT
-# ======================
-def preprocess_text(text):
+# ================================
+# TEXT PREPROCESS
+# ================================
+def preprocess_text(text: str):
     if text is None:
         text = ""
     seq = tokenizer.texts_to_sequences([text])
-    return tf.keras.preprocessing.sequence.pad_sequences(
+    padded = tf.keras.preprocessing.sequence.pad_sequences(
         seq, maxlen=MAX_LEN
     )
+    return padded
 
-# ======================
-# PREDICTION
-# ======================
+# ================================
+# PREDICTION FUNCTION
+# ================================
 def predict_ticket(image, text):
     if image is None:
-        return {"Critical": 0, "High": 0, "Medium": 0, "Low": 0}
+        return {
+            "Critical": 0.0,
+            "High": 0.0,
+            "Medium": 0.0,
+            "Low": 0.0,
+        }
 
     img = preprocess_image(image)
     txt = preprocess_text(text)
@@ -71,18 +84,25 @@ def predict_ticket(image, text):
         "Low": float(probs[3]),
     }
 
-# ======================
+# ================================
 # GRADIO UI
-# ======================
+# ================================
 interface = gr.Interface(
     fn=predict_ticket,
     inputs=[
         gr.Image(type="pil", label="📤 Upload Ticket Screenshot"),
-        gr.Textbox(lines=4, label="✍️ Ticket Description")
+        gr.Textbox(
+            lines=4,
+            placeholder="Describe the issue (recommended)",
+            label="✍️ Ticket Description"
+        )
     ],
-    outputs=gr.Label(num_top_classes=4, label="🚨 Severity"),
-    title="🎫 Multimodal Ticket Severity Classifier",
-    description="CNN + LSTM Fusion Model"
+    outputs=gr.Label(num_top_classes=4, label="🚨 Predicted Severity"),
+    title="🎫 Ticket Severity Classification",
+    description=(
+        "CNN + NLP **Fusion Model** for ticket urgency detection.\n\n"
+        "**Classes:** Critical | High | Medium | Low"
+    )
 )
 
-interface.launch()
+interface.launch()