nishnik

// ==UserScript==
// @name         Screener Charts
// @namespace    http://tampermonkey.net/
// @version      0.1
// @description  Create Charts for Screener
// @author       You
// @match        https://www.screener.in/company/*
// @icon         https://www.google.com/s2/favicons?sz=64&domain=screener.in
// @grant        none
// ==/UserScript==

nishnik

name: training_internal
channels:
  - rapidsai-nightly
  - conda-forge
  - defaults
dependencies:
  - _libgcc_mutex=0.1=conda_forge
  - _openmp_mutex=4.5=1_llvm
  - abseil-cpp=20210324.2=h9c3ff4c_0
  - absl-py=1.0.0=pyhd8ed1ab_0

nishnik

// ==UserScript==
// @name         Change filename for arxiv downloads
// @namespace    https://arxiv.org/
// @version      1.0
// @description  Changes filename for the PDF link, so that once you open it in pdf js it downloads as "paper_name.pdf" instead of "year_month.identifier.pdf"
// @author       Nishant Nikhil
// @match        https://*.arxiv.org/abs/*
// @grant        none
// ==/UserScript==

nishnik

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

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

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

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

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

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

# 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