SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

add do_lower_case in examples

Browse Source
This commit is contained in:
thomwolf
2018-11-30 13:47:33 +01:00
parent 3951c2c189
commit 0541442558
2 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/extract_features.py
View File

@@ -199,6 +199,7 @@ def main():
"bert-large-uncased, bert-base-cased, bert-base-multilingual, bert-base-chinese.") "bert-large-uncased, bert-base-cased, bert-base-multilingual, bert-base-chinese.")
## Other parameters ## 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("--layers", default="-1,-2,-3,-4", type=str)
parser.add_argument("--max_seq_length", default=128, type=int, parser.add_argument("--max_seq_length", default=128, type=int,
help="The maximum total input sequence length after WordPiece tokenization. Sequences longer " 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(",")] 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 = read_examples(args.input_file)

6
examples/run_classifier.py
View File

@@ -376,6 +376,10 @@ def main():
default=False, default=False,
action='store_true', action='store_true',
help="Whether to run eval on the dev set.") 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", parser.add_argument("--train_batch_size",
default=32, default=32,
type=int, type=int,
@@ -473,7 +477,7 @@ def main():
processor = processors[task_name]() processor = processors[task_name]()
label_list = processor.get_labels() 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 train_examples = None
num_train_steps = None num_train_steps = None