hummingbird
/
fastNLP
Not watched
2
0
Fork 0
Code
Releases 13 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
1137 Commits
3 Branches
25 MB
221 Download
Tree: d6ae241bbb
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'd6ae241bbb'
${ noResults }
fastNLP/reproduction/text_classification/utils/util_init.py

util_init.py 229 B
Raw Normal View History

-update DPCNN & train script -use spacy tokenizer for yelp data -add set_rng_seed
6 years ago
​
​
​
​
​
​
​
​
​
​
 1234567891011 
  1. import numpy

  2. import torch

  3. import random

  4. 

  5. 

  6. def set_rng_seeds(seed):

  7.     random.seed(seed)

  8.     numpy.random.seed(seed)

  9.     torch.random.manual_seed(seed)

  10.     torch.cuda.manual_seed_all(seed)

  11.     # print('RNG_SEED {}'.format(seed))

一款轻量级的自然语言处理（NLP）工具包，目标是减少用户项目中的工程型代码，例如数据处理循环、训练循环、多卡运行等