abulka

#!/usr/bin/env python
__author__ = 'Kevin Warrick'
__email__ = 'kwarrick@uga.edu, abulka@gmail.com'
__version__ = '2.0.0'

import pickle
from collections import namedtuple
from functools import wraps
import inspect
from icecream import ic

julio-kim

const source = 'http://ncov.mohw.go.kr'
let webView = new WebView()
await webView.loadURL(source)

let covid = await webView.evaluateJavaScript(`
    const baseSelector = 'div.mainlive_container div.liveboard_layout '
    let date = document.querySelector(baseSelector + 'h2 span.livedate').innerText
    let domestic = document.querySelector(baseSelector + 'div.liveNum_today_new ul li:nth-child(1) span.data').innerText
    let overseas = document.querySelector(baseSelector + 'div.liveNum_today_new ul li:nth-child(2) span.data').innerText
    

SuperShinyEyes

def f1_loss(y_true:torch.Tensor, y_pred:torch.Tensor, is_training=False) -> torch.Tensor:
    '''Calculate F1 score. Can work with gpu tensors
    
    The original implmentation is written by Michal Haltuf on Kaggle.
    
    Returns
    -------
    torch.Tensor
        `ndim` == 1. 0 <= val <= 1
    

XinDongol

Inside profiler

import torch
import torchvision.models as models

model = models.densenet121(pretrained=True)
x = torch.randn((1, 3, 224, 224), requires_grad=True)

with torch.autograd.profiler.profile(use_cuda=True) as prof:
    model(x)

shagunsodhani

Curriculum Learning

Introduction

• Curriculum Learning - When training machine learning models, start with easier subtasks and gradually increase the difficulty level of the tasks.
• Motivation comes from the observation that humans and animals seem to learn better when trained with a curriculum like a strategy.
• Link to the paper.

Contributions of the paper

mitmul

#! /bin/bash
sudo aptitude update
sudo aptitude full-upgrade -y
sudo reboot

wget http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1404/x86_64/cuda-repo-ubuntu1404_6.5-14_amd64.deb
sudo dpkg -i cuda-repo-ubuntu1404_6.5-14_amd64.deb 
sudo aptitude update
sudo aptitude install -y linux-image-extra-virtual
sudo aptitude install -y cuda

gschizas

r = requests.get(file_url)
size = int(r.headers['Content-Length'].strip())
self.bytes = 0
widgets = [name, ": ", Bar(marker="|", left="[", right=" "),
    Percentage(), " ",  FileTransferSpeed(), "] ",
    self,
    " of {0}MB".format(str(round(size / 1024 / 1024, 2))[:4])]
pbar = ProgressBar(widgets=widgets, maxval=size).start()
file = []
for buf in r.iter_content(1024):