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

Reformat source code with black.

Browse Source 
This is the result of:

    $ black --line-length 119 examples templates transformers utils hubconf.py setup.py

There's a lot of fairly long lines in the project. As a consequence, I'm
picking the longest widely accepted line length, 119 characters.

This is also Thomas' preference, because it allows for explicit variable
names, to make the code easier to understand.
This commit is contained in:
Aymeric Augustin
2019-12-21 15:46:46 +01:00
parent 63e3827c6b
commit fa84ae26d6
200 changed files with 17452 additions and 12594 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
examples/distillation/scripts/token_counts.py
View File

@@ -20,32 +20,36 @@ import argparse
import pickle
import logging
logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s - %(message)s',
datefmt = '%m/%d/%Y %H:%M:%S',
level = logging.INFO)
logging.basicConfig(
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", datefmt="%m/%d/%Y %H:%M:%S", level=logging.INFO
)
logger = logging.getLogger(__name__)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="Token Counts for smoothing the masking probabilities in MLM (cf XLM/word2vec)")
parser.add_argument("--data_file", type=str, default="data/dump.bert-base-uncased.pickle",
help="The binarized dataset.")
parser.add_argument("--token_counts_dump", type=str, default="data/token_counts.bert-base-uncased.pickle",
help="The dump file.")
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Token Counts for smoothing the masking probabilities in MLM (cf XLM/word2vec)"
)
parser.add_argument(
"--data_file", type=str, default="data/dump.bert-base-uncased.pickle", help="The binarized dataset."
)
parser.add_argument(
"--token_counts_dump", type=str, default="data/token_counts.bert-base-uncased.pickle", help="The dump file."
)
parser.add_argument("--vocab_size", default=30522, type=int)
args = parser.parse_args()
logger.info(f'Loading data from {args.data_file}')
with open(args.data_file, 'rb') as fp:
logger.info(f"Loading data from {args.data_file}")
with open(args.data_file, "rb") as fp:
data = pickle.load(fp)
logger.info('Counting occurences for MLM.')
logger.info("Counting occurences for MLM.")
counter = Counter()
for tk_ids in data:
counter.update(tk_ids)
counts = [0]*args.vocab_size
counts = [0] * args.vocab_size
for k, v in counter.items():
counts[k] = v
logger.info(f'Dump to {args.token_counts_dump}')
with open(args.token_counts_dump, 'wb') as handle:
logger.info(f"Dump to {args.token_counts_dump}")
with open(args.token_counts_dump, "wb") as handle:
pickle.dump(counts, handle, protocol=pickle.HIGHEST_PROTOCOL)