import os; import psutil; import timeit
from nlp import load_dataset
mem_before = psutil.Process(os.getpid()).memory_info().rss >> 20
wiki = load_dataset("wikipedia", "20200501.en", split='train')
mem_after = psutil.Process(os.getpid()).memory_info().rss >> 20
print(f"RAM memory used: {(mem_after - mem_before)} MB")
s = """batch_size = 1000
for i in range(0, len(wiki), batch_size):
batch = wiki[i:i + batch_size]
"""
time = timeit.timeit(stmt=s, number=1, globals=globals())
size = wiki.dataset_size / 2**30
print(f"Iterated over the {size:.1f} GB dataset in {time:.1f} s, i.e. {size * 8/time:.1f} Gbit/s")
链接地址：https://gist.github.com/thomwolf/13ca2b2b172b2d17ac66685aa2eeba62