Update app.py

app.py

@@ -1,4 +1,5 @@
 import streamlit as st
+import pickle
 import tensorflow as tf
 import cv2
 import numpy as np
@@ -64,15 +65,13 @@ def standardize(inputs):
     )
 
 # Choose the most frequent words from the vocabulary & remove punctuation etc.
-tokenizer = TextVectorization(
-    max_tokens=VOCAB_SIZE,
-    standardize=standardize,
-    output_sequence_length=MAX_CAPTION_LEN,
-)
+file = open('./tokenizer.txt', 'rb')
+tokenizer = pickle.load(file)
+
 
 # Lookup table: Word -> Index
 word_to_index = StringLookup(
-    mask_token="", vocabulary=tokenizer.get_vocabulary()
+    mask_token="", vocabulary=tokenizer
 )
 
 
@@ -102,7 +101,7 @@ def predict_caption(file):
         chosen_id = tf.random.categorical([top_probs], 1)[0].numpy()
         predicted_id = top_idxs.numpy()[chosen_id][0]
 
-        result.append(tokenizer.get_vocabulary()[predicted_id])
+        result.append(tokenizer[predicted_id])
 
         if predicted_id == word_to_index("<end>"):
             return img, result