nishnik

#! /bin/bash
# DL, ML, NLP

sudo apt-get update

# scipy, matplotlib
sudo apt-get install python-dev python-pip python-matplotlib python-scipy
#tensorflow
sudo pip install https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.7.1-cp27-none-linux_x86_64.whl

nishnik

"""
Andrej Karpathy's code compatible in python3
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
BSD License
"""
import numpy as np

# data I/O
data = open('input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))

nishnik

def load_dataset():
    "Load the sample dataset. must be numbered from 1"
    return [[1, 3, 4], [2, 3, 5], [1, 2, 3, 5], [2, 5]]


def createC1(dataset):
    "Create a list of candidate item sets of size one."
    c1 = []
    for transaction in dataset:
        for item in transaction:

nishnik

# relu activation function
def relu(x):
    return T.switch(x<0, 0, x)


class VAE:
    """This class implements the Variational Auto Encoder"""
    def __init__(self, continuous, hu_encoder, hu_decoder, n_latent, x_train, b1=0.95, b2=0.999, batch_size=100, learning_rate=0.001, lam=0):
        # let us keep the discussion to not continuous

nishnik

from bs4 import BeautifulSoup
import requests

data_list = []
link = "https://wiki.metakgp.org/w/Special:ContributionScores"
response = requests.get(link)
html = response.content
source = BeautifulSoup(html, "lxml")
trs = source.findAll("tr")
run = False

nishnik

stride = 3
new_var = Variable(torch.zeros([x.shape[0], x.shape[1]//stride, x.shape[2]//stride]))
for dim1 in range(x.shape[0]):
    tmp = Variable(torch.zeros([x.shape[1]//stride, x.shape[2]//stride, 1]))
    for i in range(0, x.shape[1], stride):
        for j in range(0, x.shape[2], stride):
            tmp_max = x[dim1][i][j]
            for k in range(stride):
                for m in range(stride):
                    tmp_max = torch.max(tmp_max, x[dim1][i+k][j+m])

nishnik

import numpy as np
y = np.array([[1.0, 7.0, 1.0],[3.0, 4.0, 2], [1, 7, 1]])
x = torch.from_numpy(y)
x = Variable(x)
x = x.resize(1, 3, 3)
stride = 2
new_var = Variable(torch.zeros([x.shape[0], x.shape[1]//stride, x.shape[2]//stride]))
new_var2 = Variable(torch.zeros([x.shape[0], x.shape[1]//stride, x.shape[2]//stride]))
for dim1 in range(x.shape[0]):
    tmp = Variable(torch.zeros([x.shape[1]//stride, x.shape[2]//stride, 1]))

nishnik

from keras.preprocessing import sequence
from keras.models import Sequential
from keras.datasets import imdb

import torch
import torch.autograd as autograd
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

nishnik

var val = "3"
var radio_buttons = document.querySelectorAll('input[value="' + val +'"]');
var i = 0;
for (i=0; i<radio_buttons.length ; i++){
radio_buttons[i].checked = true;
}
var radio_buttons = document.querySelectorAll('input[value="5' + val +'"]');
var i = 0;
for (i=0; i<radio_buttons.length ; i++){
radio_buttons[i].checked = true;

nishnik

cat crowds_zara01_train.txt  | awk -F ' ' '{print $3}' | sort -n  | sed -n '1p;$p'