This commit is contained in:
YaoFANGUK
2023-10-25 16:38:16 +08:00
commit 2b9360c299
602 changed files with 152490 additions and 0 deletions

View File

@@ -0,0 +1,22 @@
#!/usr/bin/env python3
import tqdm
import webdataset as wds
def main(args):
input_dataset = wds.Dataset(args.infile)
output_dataset = wds.ShardWriter(args.outpattern)
for rec in tqdm.tqdm(input_dataset):
output_dataset.write(rec)
if __name__ == '__main__':
import argparse
aparser = argparse.ArgumentParser()
aparser.add_argument('infile', type=str)
aparser.add_argument('outpattern', type=str)
main(aparser.parse_args())