fixed bugs in chatbot

Author: chiphuyen

assignments/chatbot/chatbot.py

@@ -169,7 +169,8 @@ def _get_user_input():
     """ Get user's input, which will be transformed into encoder input later """
     print("> ", end="")
     sys.stdout.flush()
-    return sys.stdin.readline()
+    text = sys.stdin.readline()
+    return data.tokenize_helper(text)
 
 def _find_right_bucket(length):
     """ Find the proper bucket for an encoder input based on its length """
@@ -183,7 +184,6 @@ def _construct_response(output_logits, inv_dec_vocab):
     
     This is a greedy decoder - outputs are just argmaxes of output_logits.
     """
-    print(output_logits[0])
     outputs = [int(np.argmax(logit, axis=1)) for logit in output_logits]
     # If there is an EOS symbol in outputs, cut them at that point.
     if config.EOS_ID in outputs:

assignments/chatbot/config.py

@@ -48,5 +48,3 @@
 MAX_GRAD_NORM = 5.0
 
 NUM_SAMPLES = 512
-ENC_VOCAB = 24133
-DEC_VOCAB = 22879

assignments/chatbot/model.py

@@ -86,31 +86,6 @@ def _seq2seq_f(encoder_inputs, decoder_inputs, do_decode):
                                         config.BUCKETS,
                                         lambda x, y: _seq2seq_f(x, y, False),
                                         softmax_loss_function=self.softmax_loss_function)
-
-        # if self.fw_only:
-        #     self.outputs, self.losses = tf.contrib.training.bucket_by_sequence_length(
-        #                                 self.encoder_inputs, 
-        #                                 self.decoder_inputs, 
-        #                                 self.targets,
-        #                                 self.decoder_masks, 
-        #                                 config.BUCKETS, 
-        #                                 lambda x, y: _seq2seq_f(x, y, True),
-        #                                 softmax_loss_function=self.softmax_loss_function)
-        #     # If we use output projection, we need to project outputs for decoding.
-        #     if self.output_projection:
-        #         for bucket in range(len(config.BUCKETS)):
-        #             self.outputs[bucket] = [tf.matmul(output, 
-        #                                     self.output_projection[0]) + self.output_projection[1]
-        #                                     for output in self.outputs[bucket]]
-        # else:
-        #     self.outputs, self.losses = tf.contrib.training.bucket_by_sequence_length(
-        #                                 self.encoder_inputs, 
-        #                                 self.decoder_inputs, 
-        #                                 self.targets,
-        #                                 self.decoder_masks,
-        #                                 config.BUCKETS,
-        #                                 lambda x, y: _seq2seq_f(x, y, False),
-        #                                 softmax_loss_function=self.softmax_loss_function)
         print('Time:', time.time() - start)
 
     def _creat_optimizer(self):