Update app.py

app.py

@@ -117,7 +117,55 @@ if option == '13M_OLD':
     weights = "predict3"
     datafile = "data2.txt"
     dict = "dict_predict3.bin.npz"
-    out2 = completion_model(vocab_size, max_len, d_model, n_head, ff_dim, dropout_rate,weights,datafile,dict,len2,text2)
+    with open(datafile,"r") as f:
+        text = f.read()
+    text = text.lower()
+    words = text.split()
+    loaded_dict = np.load(dict, allow_pickle=True)
+    word_to_num = loaded_dict["word_to_num"].item()
+    num_to_word = loaded_dict["num_to_word"].item()
+    X = []
+    Y = []
+    for i in range(len(words)-1):
+        word = words[i]
+        next_word = words[i+1]
+        X.append(word_to_num[word])
+        Y.append(word_to_num[next_word])
+    Y.append(0)
+
+    X.append(word_to_num[words[-1]])
+    X_train = pad_sequences([X])
+    y_train = pad_sequences([Y])
+    
+
+
+    chatbot = TransformerChatbot(vocab_size, max_len, d_model, n_head, ff_dim, dropout_rate)
+    chatbot.load_weights(weights)
+    chatbot.build(input_shape=(None, max_len)) # Build the model
+    chatbot.compile(optimizer="adam", loss="sparse_categorical_crossentropy")
+    
+    for i in range(1):
+        other_text2 = text2
+        other_text2 = other_text2.lower()
+        other_words2 = other_text2.split()
+        other_num2 = [word_to_num[word] for word in other_words2]
+        given_X2 = other_num2
+        input_sequence2 = pad_sequences([given_X2], maxlen=max_len, padding='post')
+        output_sentence = other_text2 + ""
+        for _ in range(len2):
+            predicted_token = np.argmax(chatbot.predict(input_sequence2), axis=-1)
+            predicted_token = predicted_token.item()
+            out = num_to_word[predicted_token]
+            # if out == ".":
+                # break
+
+            output_sentence += " " + out
+            given_X2 = given_X2[1:]
+            given_X2.append(predicted_token)
+            input_sequence2 = pad_sequences([given_X2], maxlen=max_len, padding='post')
+
+        out2 = output_sentence    
+    
     st.write("Predicted Text: ")
     st.write(out2)
         
@@ -137,7 +185,63 @@ elif option=="26M_OLD":
     weights = "predict1"
     datafile = "data2.txt"
     dict = "dict_predict1.bin.npz"
-    out2 = completion_model(vocab_size, max_len, d_model, n_head, ff_dim, dropout_rate,weights,datafile,dict,len2,text2)
+        vocab_size = 100000
+    max_len = 1
+    d_model = 64  # 64 , 1024
+    n_head = 4  # 8 , 16
+    ff_dim = 256  # 256 , 2048
+    dropout_rate = 0.1  # 0.5 , 0.2
+    weights = "predict3"
+    datafile = "data2.txt"
+    dict = "dict_predict3.bin.npz"
+    with open(datafile,"r") as f:
+        text = f.read()
+    text = text.lower()
+    words = text.split()
+    loaded_dict = np.load(dict, allow_pickle=True)
+    word_to_num = loaded_dict["word_to_num"].item()
+    num_to_word = loaded_dict["num_to_word"].item()
+    X = []
+    Y = []
+    for i in range(len(words)-1):
+        word = words[i]
+        next_word = words[i+1]
+        X.append(word_to_num[word])
+        Y.append(word_to_num[next_word])
+    Y.append(0)
+
+    X.append(word_to_num[words[-1]])
+    X_train = pad_sequences([X])
+    y_train = pad_sequences([Y])
+    
+
+
+    chatbot = TransformerChatbot(vocab_size, max_len, d_model, n_head, ff_dim, dropout_rate)
+    chatbot.load_weights(weights)
+    chatbot.build(input_shape=(None, max_len)) # Build the model
+    chatbot.compile(optimizer="adam", loss="sparse_categorical_crossentropy")
+    
+    for i in range(1):
+        other_text2 = text2
+        other_text2 = other_text2.lower()
+        other_words2 = other_text2.split()
+        other_num2 = [word_to_num[word] for word in other_words2]
+        given_X2 = other_num2
+        input_sequence2 = pad_sequences([given_X2], maxlen=max_len, padding='post')
+        output_sentence = other_text2 + ""
+        for _ in range(len2):
+            predicted_token = np.argmax(chatbot.predict(input_sequence2), axis=-1)
+            predicted_token = predicted_token.item()
+            out = num_to_word[predicted_token]
+            # if out == ".":
+                # break
+
+            output_sentence += " " + out
+            given_X2 = given_X2[1:]
+            given_X2.append(predicted_token)
+            input_sequence2 = pad_sequences([given_X2], maxlen=max_len, padding='post')
+
+        out2 = output_sentence  
     st.write("Predicted Text: ")
     st.write(out2)    
 else: