pbamotra

from os import listdir
from os.path import isfile, join

images_directory = './flower_data/flower_data_flat'
# read names of all image files
image_files = [f for f in listdir(image_dir) if isfile(join(image_dir, f))]

# we create a data frame with the image names and dummy labels - label_1, label_2
data = pd.DataFrame(list(zip(image_files, 
                            list(range(len(image_files))), 

pbamotra

$ wget -cq https://s3.amazonaws.com/content.udacity-data.com/courses/nd188/flower_data.zip \
  && unzip -qq flower_data.zip \
  && mkdir -p ./flower_data/flower_data_flat \
  && find ./flower_data/train -mindepth 2 -type f -exec mv -t ./flower_data/flower_data_flat -i '{}' +

pbamotra

# Find out the cuda version so that we install appropriate DALI binaries
# Find installation instructions at 
# https://github.com/NVIDIA/DALI#installing-prebuilt-dali-packages

$ nvcc --version

# sample output
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2018 NVIDIA Corporation
Built on Sat_Aug_25_21:08:01_CDT_2018

pbamotra

from torchvision import transforms

def get_image_transforms() -> transforms.Compose:
    """
    These transformations meant for data augmentation are a bottleneck
    since all the operations are done on CPU and then the tensors are
    copied to the GPU device.
    """
    return transforms.Compose([
        transforms.RandomSizedCrop(224),

pbamotra

def logsigsoftmax(logits):
    """
    Computes sigsoftmax from the paper - https://arxiv.org/pdf/1805.10829.pdf
    """
    max_values = torch.max(logits, 1, keepdim = True)[0]
    exp_logits_sigmoided = torch.exp(logits - max_values) * torch.sigmoid(logits)
    sum_exp_logits_sigmoided = exp_logits_sigmoided.sum(1, keepdim = True)
    log_probs = logits - max_values + torch.log(torch.sigmoid(logits)) - torch.log(sum_exp_logits_sigmoided)
    return log_probs

pbamotra

#!/bin/bash

# Mac instructions: -
# 0. Install brew -- https://brew.sh/
#    ```/usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"```
# 1. Install pup -- https://github.com/ericchiang/pup
#    ```$ brew install https://raw.githubusercontent.com/EricChiang/pup/master/pup.rb```
# 2. Install jq -- https://stedolan.github.io/jq/
#    ```$ brew install jq```

pbamotra

In this article, I will share some of my experience on installing NVIDIA driver and CUDA on Linux OS. Here I mainly use Ubuntu as example. Comments for CentOS/Fedora are also provided as much as I can.

Table of Contents

• Install NVIDIA Graphics Driver via apt-get
• Install NVIDIA Graphics Driver via runfile
  • Remove Previous Installations (Important)
  • Download the Driver
  • Install Dependencies
  • Creat Blacklist for Nouveau Driver

• Stop lightdm/gdm/kdm

pbamotra

brew install jq && curl -sS 'https://trends.google.com/trends/api/stories/latest?hl=en-US&tz=480&cat=b&fi=15&fs=15&geo=US&ri=300&rs=15&sort=0' -H 'dnt: 1' -H 'accept-encoding: gzip, deflate, br' -H 'accept-language: en-US,en;q=0.9'  -H 'accept: application/json, text/plain, */*' -H 'referer: https://trends.google.com/trends/home/b/US' -H 'authority: trends.google.com' --compressed > out.json && sed '1d' out.json > out2.json && jq '.storySummaries.trendingStories[].entityNames | join(", ")' out2.json | grep 'NYSE\|NASDAQ' | jq "."

pbamotra

# -*- coding: utf-8 -*-

import os
import sys
import grequests
import numpy as np
import pandas as pd
from lxml import html
from time import sleep
from datetime import date, timedelta

pbamotra

# requirements: curl, jq, python, pandas

# brew install jq
# pip install pandas

# prints top 50 papers

curl -sS "https://openreview.net/notes?invitation=ICLR.cc%2F2018%2FConference%2F-%2FBlind_Submission&offset=0&limit=5000" | jq -r '.notes[] | .content.title + "\t" + (.replyCount|tostring)' > subset.tsv && python -c 'from pprint import pprint; import pandas as pd; d=pd.read_csv("subset.tsv", header=None, delimiter="\t"); d.columns=["title", "replies"]; pprint(d.sort_values(by="replies", ascending=False).head(50).title.tolist());' && rm -f subset.tsv

# number of papers in top 50 on adversarial networks