Update app.py

app.py

@@ -1,23 +1,35 @@
 import gradio as gr
 import tensorflow as tf
+import keras
 import numpy as np
 import pickle
 from tensorflow.keras.preprocessing.sequence import pad_sequences
 import re
+import os
 
-# Load models and tokenizers
-def load_models():
-    # Load classifier model and tokenizer
-    classifier_model = tf.keras.models.load_model('classifier_model.keras')
-    with open('classifier_tokenizer.pkl', 'rb') as handle:
-        classifier_tokenizer = pickle.load(handle)
+# Define and register the custom Perplexity metric
+@keras.saving.register_keras_serializable(package="Custom")
+class Perplexity(keras.metrics.Metric):
+    def __init__(self, name='perplexity', dtype=None, **kwargs):
+        super().__init__(name=name, dtype=dtype, **kwargs)
+        self.cross_entropy = keras.metrics.Mean(name='cross_entropy')
+        
+    def update_state(self, y_true, y_pred, sample_weight=None):
+        # Calculate cross-entropy
+        cross_entropy_values = tf.keras.losses.sparse_categorical_crossentropy(y_true, y_pred)
+        # Update the internal mean metric
+        self.cross_entropy.update_state(cross_entropy_values, sample_weight)
+        
+    def result(self):
+        # Perplexity is the exponential of the cross-entropy
+        return tf.exp(self.cross_entropy.result())
     
-    # Load text generator model and tokenizer
-    textgen_model = tf.keras.models.load_model('textgen_model.keras')
-    with open('textgen_tokenizer.pkl', 'rb') as handle:
-        textgen_tokenizer = pickle.load(handle)
+    def reset_state(self):
+        self.cross_entropy.reset_state()
     
-    return classifier_model, classifier_tokenizer, textgen_model, textgen_tokenizer
+    def get_config(self):
+        config = super().get_config()
+        return config
 
 # Text cleaning function
 def clean_text(text):
@@ -28,6 +40,38 @@ def clean_text(text):
     text = ' '.join(text.split())
     return text
 
+# Load models and tokenizers
+def load_models():
+    print("Loading models and tokenizers...")
+    
+    # Load models with custom objects for Perplexity
+    custom_objects = {'Perplexity': Perplexity}
+    
+    try:
+        with keras.saving.custom_object_scope(custom_objects):
+            classifier_model = keras.models.load_model('classifier_model.keras')
+            textgen_model = keras.models.load_model('textgen_model.keras')
+        
+        print("Models loaded successfully with custom objects")
+    except Exception as e:
+        print(f"Error loading models with custom objects: {e}")
+        raise
+    
+    # Load tokenizers
+    try:
+        with open('classifier_tokenizer.pkl', 'rb') as handle:
+            classifier_tokenizer = pickle.load(handle)
+        
+        with open('textgen_tokenizer.pkl', 'rb') as handle:
+            textgen_tokenizer = pickle.load(handle)
+        
+        print("Tokenizers loaded successfully")
+    except Exception as e:
+        print(f"Error loading tokenizers: {e}")
+        raise
+    
+    return classifier_model, classifier_tokenizer, textgen_model, textgen_tokenizer
+
 # Classification function
 def classify_text(text, model, tokenizer):
     cleaned_text = clean_text(text)
@@ -74,10 +118,21 @@ def generate_text(prompt, model, tokenizer, max_length=50, temperature=0.7):
     
     return input_text
 
-# Load models
-classifier_model, classifier_tokenizer, textgen_model, textgen_tokenizer = load_models()
+# Print environment info for debugging
+print(f"TensorFlow version: {tf.__version__}")
+print(f"Keras version: {tf.keras.__version__}")
+print(f"Current directory contents: {os.listdir('.')}")
 
-# Create Gradio interface
+# Load models with error handling
+try:
+    print("Starting model loading process...")
+    classifier_model, classifier_tokenizer, textgen_model, textgen_tokenizer = load_models()
+    print("Models and tokenizers loaded successfully")
+except Exception as e:
+    print(f"Error in model loading process: {e}")
+    raise
+
+# Create Gradio interface functions
 def classify_interface(text):
     subject, confidence = classify_text(text, classifier_model, classifier_tokenizer)
     return f"Subject: {subject} (Confidence: {confidence:.2f}%)"
@@ -85,7 +140,7 @@ def classify_interface(text):
 def generate_interface(prompt, length=50, temp=0.7):
     return generate_text(prompt, textgen_model, textgen_tokenizer, max_length=int(length), temperature=float(temp))
 
-# Create tabs for different functionalities
+# Create Gradio interface
 with gr.Blocks(title="Science Text Analyzer") as demo:
     gr.Markdown("# Science Text Analyzer")