linux运行到ngram2vec/pairs2sgns.py报错

[zhezhaoa]

linux运行到ngram2vec/pairs2sgns.py报错

[yongzhuo]

解决了，不知道怎么回事，在这里断开，单独抽出来训练，又可以了
i@ubuntu:/yongzhuo/ngram2vec$ memory_size=4
i@ubuntu:/yongzhuo/ngram2vec$ cpus_num=4
i@ubuntu:/yongzhuo/ngram2vec$ corpus=wikipedia
i@ubuntu:/yongzhuo/ngram2vec$ output_path=outputs/${corpus}/word_word
i@ubuntu:~/yongzhuo/ngram2vec$ python ngram2vec/pairs2sgns.py --pairs_file ${output_path}/pairs --input_vocab_file ${output_path}/vocab.input --output_vocab_file ${output_path}/vocab.output --input_vector_file ${output_path}/sgns/sgns.input --output_vector_file ${output_path}/sgns/sgns.output --threads_num ${cpus_num}

Pairs2sgns
Starting training using file outputs/wikipedia/word_word/pairs
Vocab size: 1495416
Number of pairs: 500291968
Vocab size: 1495416
Number of pairs: 500291968
Alpha: 0.000002 Progress: 100.00% Pairs/thread/sec: 182.93k
Pairs2sgns finished