add do_lower_case in examples

examples/extract_features.py

@@ -199,6 +199,7 @@ def main():
                              "bert-large-uncased, bert-base-cased, bert-base-multilingual, bert-base-chinese.")
 
     ## Other parameters
+    parser.add_argument("--do_lower_case", default=False, action='store_true', help="Set this flag if you are using an uncased model.")
     parser.add_argument("--layers", default="-1,-2,-3,-4", type=str)
     parser.add_argument("--max_seq_length", default=128, type=int,
                         help="The maximum total input sequence length after WordPiece tokenization. Sequences longer "
@@ -227,7 +228,7 @@ def main():
 
     layer_indexes = [int(x) for x in args.layers.split(",")]
 
-    tokenizer = BertTokenizer.from_pretrained(args.bert_model)
+    tokenizer = BertTokenizer.from_pretrained(args.bert_model, do_lower_case=args.do_lower_case)
 
     examples = read_examples(args.input_file)
 

examples/run_classifier.py

@@ -376,6 +376,10 @@ def main():
                         default=False,
                         action='store_true',
                         help="Whether to run eval on the dev set.")
+    parser.add_argument("--do_lower_case",
+                        default=False,
+                        action='store_true',
+                        help="Set this flag if you are using an uncased model.")
     parser.add_argument("--train_batch_size",
                         default=32,
                         type=int,
@@ -473,7 +477,7 @@ def main():
     processor = processors[task_name]()
     label_list = processor.get_labels()
 
-    tokenizer = BertTokenizer.from_pretrained(args.bert_model)
+    tokenizer = BertTokenizer.from_pretrained(args.bert_model, do_lower_case=args.do_lower_case)
 
     train_examples = None
     num_train_steps = None