luckmoon

def top_k_top_p_filtering(logits, top_k=0, top_p=0.0, filter_value=-float('Inf')):
    """ Filter a distribution of logits using top-k and/or nucleus (top-p) filtering
        Args:
            logits: logits distribution shape (vocabulary size)
            top_k >0: keep only top k tokens with highest probability (top-k filtering).
            top_p >0.0: keep the top tokens with cumulative probability >= top_p (nucleus filtering).
                Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751)
    """
    assert logits.dim() == 1  # batch size 1 for now - could be updated for more but the code would be less clear
    top_k = min(top_k, logits.size(-1))  # Safety check

luckmoon

import numpy as np
import matplotlib.pyplot as plt

# ensure your arr is sorted from lowest to highest values first!
arr = np.array([1,4,6,9,100])

def gini(arr):
    count = arr.size
    coefficient = 2 / count
    indexes = np.arange(1, count + 1)

luckmoon

import numpy as np
import matplotlib.pyplot as plt

# ensure your arr is sorted from lowest to highest values first!
arr = np.array([1,4,6,9,100])

def gini(arr):
    count = arr.size
    coefficient = 2 / count
    indexes = np.arange(1, count + 1)

luckmoon

# Working example for my blog post at:
# http://danijar.com/variable-sequence-lengths-in-tensorflow/
import functools
import sets
import tensorflow as tf
from tensorflow.models.rnn import rnn_cell
from tensorflow.models.rnn import rnn


def lazy_property(function):

luckmoon

import numpy as np
import tensorflow as flow
from tensorflow.python.saved_model import loader

# first, read the pretrained weights into a dictionary
variables = {}
g1 = tf.Graph()
with g1.as_default():
    restore_from = 'pretrained_model/1513006564'
    with tf.Session() as sess:

luckmoon

import tensorflow as tf


def create_bad_dataset(create_batches=True):
  dataset = tf.data.Dataset.from_tensor_slices([1., 2., 0., 4., 8., 16.])
  # Computing `tf.check_numerics(1. / 0.)` will raise an InvalidArgumentError.
  if create_batches:
    # Demonstrates that error handling works with map_and_batch
    dataset = dataset.apply(tf.contrib.data.map_and_batch(
                  map_func=lambda x: tf.check_numerics(1. / x, 'error'), batch_size=2))

luckmoon

看論文要注意的三點

(1)其分析的資料為何？(2) 其應用為何？ (3) 要達成該應用有什麼問題需要解決？

Ontoloty比賽

https://competitions.codalab.org/competitions/17119

需要看的論文

luckmoon

import torch
from torch import LongTensor
from torch.nn import Embedding, LSTM
from torch.autograd import Variable
from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence

## We want to run LSTM on a batch of 3 character sequences ['long_str', 'tiny', 'medium']
#
#     Step 1: Construct Vocabulary
#     Step 2: Load indexed data (list of instances, where each instance is list of character indices)

luckmoon

#!/usr/bin/env python
# -*- coding:UTF-8 -*-

import torch
import torch.nn as nn
import torch.nn.init as init


def weight_init(m):
    '''

luckmoon

# coding:utf-8

from elasticsearch import Elasticsearch
import json

# Define config
host = "127.0.0.1"
port = 9200
timeout = 1000
index = "index"