Update app.py

app.py

@@ -8,38 +8,7 @@ from tensorflow.keras.preprocessing.image import load_img, img_to_array
 from tensorflow.keras.preprocessing.text import Tokenizer
 from tensorflow.keras.preprocessing.sequence import pad_sequences
 from tensorflow.keras.models import Model
-###############################################
 
-# from keras.layers import Input, Dense, Dropout, Embedding, LSTM, Concatenate, Bidirectional
-# from keras.models import Model
-
-# max_length = 35
-# vocab_size = 8485
-
-# # Encoder Model
-# inputs1 = Input(shape=(2560,))
-# fe1 = Dropout(0.5)(inputs1)
-# fe2 = Dense(512, activation='relu')(fe1)  # Increased units
-# fe3 = Dense(256, activation='relu')(fe2)  # Increased units
-
-# # Sequence Feature Layer
-# inputs2 = Input(shape=(max_length,))
-# se1 = Embedding(vocab_size, 256, mask_zero=True)(inputs2)
-# se2 = Dropout(0.5)(se1)
-# se3 = Bidirectional(LSTM(512))(se2)  # Increased units
-
-# # Decoder Model
-# decoder1 = Concatenate()([fe3, se3])
-# decoder2 = Dense(512, activation='relu')(decoder1)  # Increased units
-# decoder3 = Dropout(0.5)(decoder2)
-# outputs = Dense(vocab_size, activation='softmax')(decoder3)
-
-# model = Model(inputs=[inputs1, inputs2], outputs=outputs)
-# # optimizer = Adam(lr=0.001)  # Adjusted learning rate
-# model.compile(optimizer="adam", loss='categorical_crossentropy')
-
-# model.load_weights("Modified_Image_Captioner_model.h5")
-##############################################################################
 
 # load vgg16 model
 pre_trained = EfficientNetB7(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
@@ -52,9 +21,9 @@ pre_trained_model = Model(inputs=pre_trained.input, outputs=x)
 
 # model = tf.keras.models.load_model("Modified_Image_Captioner_model.h5")
 
-# tokenizer = Tokenizer()
-# with open("Image_Captioner_tokenizer.pkl", "rb") as f:
-#     tokenizer = pickle.load(f)
+tokenizer = Tokenizer()
+with open("Image_Captioner_tokenizer.pkl", "rb") as f:
+    tokenizer = pickle.load(f)
 
 def idx_to_word(integer, tokenizer):
     for word, index in tokenizer.word_index.items():