我正在尝试并行执行
some machine learning algorithm
.
当我使用多处理时,它比不使用时慢。我的猜测是
pickle
我使用的模型的序列化减慢了整个过程。所以问题是:
如何用初始状态初始化池的worker,这样就不需要对模型的每次调用进行序列化/反序列化?
以下是我目前的代码:
import pickle
from pathlib import Path
from collections import Counter
from multiprocessing import Pool
from gensim.models.doc2vec import Doc2Vec
from wikimark import html2paragraph
from wikimark import tokenize
def process(args):
doc2vec, regressions, filepath = args
with filepath.open('r') as f:
string = f.read()
subcategories = Counter()
for index, paragraph in enumerate(html2paragraph(string)):
tokens = tokenize(paragraph)
vector = doc2vec.infer_vector(tokens)
for subcategory, model in regressions.items():
prediction = model.predict([vector])[0]
subcategories[subcategory] += prediction
# compute the mean score for each subcategory
for subcategory, prediction in subcategories.items():
subcategories[subcategory] = prediction / (index + 1)
# keep only the main category
subcategory = subcategories.most_common(1)[0]
return (filepath, subcategory)
def main():
input = Path('./build')
doc2vec = Doc2Vec.load(str(input / 'model.doc2vec.gz'))
regressions = dict()
for filepath in input.glob('./*/*/*.model'):
with filepath.open('rb') as f:
model = pickle.load(f)
regressions[filepath.parent] = model
examples = list(input.glob('../data/wikipedia/english/*'))
with Pool() as pool:
iterable = zip(
[doc2vec] * len(examples), # XXX!
[regressions] * len(examples), # XXX!
examples
)
for filepath, subcategory in pool.imap_unordered(process, iterable):
print('* {} -> {}'.format(filepath, subcategory))
if __name__ == '__main__':
main()
标有
XXX!
指向我调用时序列化的数据
pool.imap_unodered
。至少有200MB的数据被序列化。
如何避免序列化?