jiqiujia

1. Clone your fork:

git clone git@github.com:YOUR-USERNAME/YOUR-FORKED-REPO.git

2. Add remote from original repository in your forked repository:

cd into/cloned/fork-repo
git remote add upstream git://github.com/ORIGINAL-DEV-USERNAME/REPO-YOU-FORKED-FROM.git
git fetch upstream

jiqiujia

{
  "mappings": {
    "docs": {
      "dynamic": true,
      "properties": {
        "time": {
          "type": "date",
          "format": "yyyyMMdd",
          "store": "true"
        },

jiqiujia

###byte pair encoding
###Neural Machine Translation of Rare Words with Subword Units
###from https://plmsmile.github.io/2017/10/19/subword-units/
import re
def process_raw_words(words, endtag='-'):
    '''把单词分割成最小的符号，并且加上结尾符号'''
    vocabs = {}
    for word, count in words.items():
        # 加上空格
        word = re.sub(r'([a-zA-Z])', r' \1', word)

jiqiujia

import argparse
import os
import shutil
import time

import torch
import torch.nn as nn
import torch.nn.parallel
import torch.backends.cudnn as cudnn
import torch.optim

jiqiujia

# This is an example for the CIFAR-10 dataset.
# There's a function for creating a train and validation iterator.
# There's also a function for creating a test iterator.
# Inspired by https://discuss.pytorch.org/t/feedback-on-pytorch-for-kaggle-competitions/2252/4

from utils import plot_images

def get_train_valid_loader(data_dir,
                           batch_size,
                           augment,

jiqiujia

#from https://rosettacode.org/wiki/LU_decomposition#Python
from pprint import pprint
 
def matrixMul(A, B):
    TB = zip(*B)
    return [[sum(ea*eb for ea,eb in zip(a,b)) for b in TB] for a in A]
 
def pivotize(m):
    """Creates the pivoting matrix for m."""
    n = len(m)

jiqiujia

### Adapted from TF repo

import tensorflow as tf
from tensorflow import gradients
from tensorflow.python.framework import ops
from tensorflow.python.ops import array_ops
from tensorflow.python.ops import math_ops


def hessian_vector_product(ys, xs, v):

jiqiujia

import numpy as np
import matplotlib.pyplot as plt
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.autograd import Variable
import torchvision
import torchvision.transforms as transforms
import numpy as np

jiqiujia

#plot tiled images
fig = plt.figure(figsize=(8,8))
#adjust the white space around the figure and each subplot
plt.subplots_adjust(wspace=0.01, hspace=0.01, left=0, right=1, bottom=0, top=1)
for i in range(63):
    ax = plt.subplot(8,8,i+1)
    plt.imshow(imgs[i])
    ax.axis('off') #no frame
    #ax.get_xaxis().set_visible(False)
    #ax.get_yaxis().set_visible(False)

jiqiujia

import numpy as np
from scipy.ndimage.interpolation import map_coordinates
from scipy.ndimage.filters import gaussian_filter

def elastic_transform(image, alpha, sigma, random_state=None):
    """Elastic deformation of images as described in [Simard2003]_.


    .. [Simard2003] Simard, Steinkraus and Platt, "Best Practices for
       Convolutional Neural Networks applied to Visual Document Analysis", in