Update app.py

app.py

@@ -22,7 +22,7 @@ tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
 bert_model = TFBertModel.from_pretrained("bert-base-uncased")
 
 # Define function to create embeddings
-def bert_embeddings(texts, max_length=128):
+def bert_embeddings(texts, max_length=64):
     inputs = tokenizer(
         texts.tolist(),
         return_tensors="tf",
@@ -89,14 +89,14 @@ print("\nClassification Report:")
 print(class_report)
 
 # Save the trained model to a file
-classifier.save("movie_sentiment_model.h5")
+#classifier.save("movie_sentiment_model.h5")
 
 def fn(test_review):
     review=remove_tags(test_review)
     review=remove_stop_wrods(review)
     cls_embeddings = bert_embeddings([review])
-    loaded_model = load_model("movie_sentiment_model.h5")
-    prediction = loaded_model.predict(cls_embeddings)
+    #loaded_model = load_model("movie_sentiment_model.h5")
+    prediction = classifier.predict(cls_embeddings)
     return "Positive" if prediction[0] > 0.5 else "Negative"
     
 description = "Give a review of a movie that you like(or hate, sarcasm intended XD) and the model will let you know just how much your review truely reflects your emotions. "