p208p2002

PyTorch實作NLP中的Self-Attention

輸入準備

我們準備了兩個句子來進行這次實驗

sentences = ['helo attention','have a nice day']

一開始先建立詞表與對應的單詞one-hot encoding

vocabs = ' '.join(sentences).split()
vocabs = list(set(vocabs))

thehesiod

import asyncio
from datetime import datetime, timezone
import os

def utc_now():
    # utcnow returns a naive datetime, so we have to set the timezone manually <sigh>
    return datetime.utcnow().replace(tzinfo=timezone.utc)
  
class Terminator:
  pass

kastnerkyle

# (C) Kyle Kastner, June 2014
# License: BSD 3 clause

import scipy.stats as st
import numpy as np

class gmmhmm:
    #This class converted with modifications from https://code.google.com/p/hmm-speech-recognition/source/browse/Word.m
    def __init__(self, n_states):
        self.n_states = n_states

nicolashery

Elasticsearch: updating the mappings and settings of an existing index

Note: This was written using elasticsearch 0.9.

Elasticsearch will automatically create an index (with basic settings and mappings) for you if you post a first document:

$ curl -X POST 'http://localhost:9200/thegame/weapons/1' -d \
'{
  "_id": 1,