RamonYeung

import re, collections

def get_stats(vocab):
   pairs = collections.defaultdict(int)
   for word, freq in vocab.items():
       symbols = word.split()
       for i in range(len(symbols)-1):
           pairs[symbols[i],symbols[i+1]] += freq
   return pairs

RamonYeung

from graphviz import Digraph
import torch
from torch.autograd import Variable, Function

def iter_graph(root, callback):
    queue = [root]
    seen = set()
    while queue:
        fn = queue.pop()
        if fn in seen:

RamonYeung

# encoding: utf-8
import os
import pygame

font_file = '/System/Library/Fonts/PingFang.ttc'

chinese_dir = 'chinese'
if not os.path.exists(chinese_dir):
    os.mkdir(chinese_dir)

RamonYeung

tmux cheatsheet

As configured in my dotfiles.

start new:

tmux

start new with session name:

RamonYeung

tmux shortcuts & cheatsheet

start new:

tmux

start new with session name:

tmux new -s myname

RamonYeung

import torch
import torch.nn as nn
from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence

seqs = ['gigantic_string','tiny_str','medium_str']

# make <pad> idx 0
vocab = ['<pad>'] + sorted(set(''.join(seqs)))

# make model

RamonYeung

''' Script for downloading all GLUE data.

Note: for legal reasons, we are unable to host MRPC.
You can either use the version hosted by the SentEval team, which is already tokenized, 
or you can download the original data from (https://download.microsoft.com/download/D/4/6/D46FF87A-F6B9-4252-AA8B-3604ED519838/MSRParaphraseCorpus.msi) and extract the data from it manually.
For Windows users, you can run the .msi file. For Mac and Linux users, consider an external library such as 'cabextract' (see below for an example).
You should then rename and place specific files in a folder (see below for an example).

mkdir MRPC
cabextract MSRParaphraseCorpus.msi -d MRPC

RamonYeung

# 1. Directly Load a Pre-trained Model
# https://github.com/pytorch/vision/tree/master/torchvision/models
import torchvision.models as models
resnet50 = models.resnet50(pretrained=True)
# or
model = models.resnet50(pretrained=False)

# Maybe you want to modify the last fc layer?
resnet.fc = nn.Linear(2048, 2) 

RamonYeung

# copy and paste two modules.
# https://raw.githubusercontent.com/skydark/nstools/master/zhtools/langconv.py
# https://raw.githubusercontent.com/skydark/nstools/master/zhtools/zh_wiki.py

from langconv import *

def Traditional2Simplified(sentence):
    sentence = Converter('zh-hans').convert(sentence)
    return sentence

RamonYeung

# coding: utf-8

import logging
import re
from collections import Counter

import numpy as np
import torch
from sklearn.datasets import fetch_20newsgroups
from torch.autograd import Variable