thirdwing

# Make mouse useful
setw -g mouse on

# Allow xterm titles in terminal window, terminal scrolling with scrollbar, and setting overrides of C-Up, C-Down, C-Left, C-Right
# (commented out because it disables cursor navigation in vim)
#set -g terminal-overrides "xterm*:XT:smcup@:rmcup@:kUP5=\eOA:kDN5=\eOB:kLFT5=\eOD:kRIT5=\eOC"

# Scroll History
set -g history-limit 30000

thirdwing

CFLAGS +=             -O3 -Wall -pipe -pedantic
CXXFLAGS +=           -O3 -Wall -pipe -Wno-unused -pedantic
VER=-4.8
CCACHE=ccache
CC=$(CCACHE) gcc$(VER)
CXX=$(CCACHE) g++$(VER)
SHLIB_CXXLD=g++$(VER)
FC=ccache gfortran$(VER)
F77=$(CCACHE) gfortran$(VER)
MAKE=make -j8

thirdwing

find.funs <-function(pos = 1, ..., exclude.mcache = TRUE, mode = 'function') {
    findo <- function(pos2) {
      o <- named(lsall(pos = pos2, ...))
      
      if (!length(o))
        return(character(0))
      # keep if exists
      keep <- sapply(o, exists, where = pos2, mode = mode, inherits = FALSE)
      
      if (!any(keep))

thirdwing

// boost graph serialization example
// g++ boost_graph_serialize.cpp -lboost_serialization -o test


#include <iostream>
#include <string>
#include <iostream>
#include <fstream>
#include <set>

thirdwing

require(RCurl)
require(XML)
webpage <- getURL("https://en.wikipedia.org/wiki/N-gram")
webpage <- readLines(tc <- textConnection(webpage)); close(tc)
pagetree <- htmlTreeParse(webpage, error=function(...){}, useInternalNodes = TRUE)
x <- xpathSApply(pagetree, "//*/p", xmlValue)  
x <- unlist(strsplit(x, "\n"))
x <- gsub("\t","",x)
x <- sub("^[[:space:]]*(.*?)[[:space:]]*$", "\\1", x, perl=TRUE)
x <- x[!(x %in% c("", "|"))]

thirdwing

#!/bin/python
from collections import OrderedDict

def memo(f, k):
    cache = OrderedDict()
    def memoized(n):
        if n not in cache:
            cache[n] = f(n)
            if len(cache) > k:
                del cache[cache.keys()[0]]

thirdwing

Using Google Cloud Vision API's OCR to extract text from photos and scanned documents

Just a quickie test in Python 3 (using Requests) to see if Google Cloud Vision can be used to effectively OCR a scanned data table and preserve its structure, in the way that products such as ABBYY FineReader can OCR an image and provide Excel-ready output.

The short answer: No. While Cloud Vision provides bounding polygon coordinates in its output, it doesn't provide it at the word or region level, which would be needed to then calculate the data delimiters.

On the other hand, the OCR quality is pretty good, if you just need to identify text anywhere in an image, without regards to its physical coordinates. I've included two examples:

####### 1. A low-resolution photo of road signs

thirdwing

logger <- mx.metric.logger$new()

mx.callback.plot.train.metric <- function(period, logger=NULL) {
  function(iteration, nbatch, env, verbose=TRUE) {
    if (nbatch %% period == 0 && !is.null(env$metric)) {
      N = env$end.round
      result <- env$metric$get(env$train.metric)
      plot(c(0.5,1)~c(0,N), col=NA, ylab = paste0("Train-", result$name),xlab = "")
      logger$train <- c(logger$train, result$value)
      lines(logger$train, lwd = 3, col="red")

thirdwing

//java -Djava.awt.headless=true

import java.awt.image.BufferedImage;
import java.awt.image.DataBufferByte;
import java.io.File;
import java.io.IOException;
import javax.imageio.ImageIO;

public class Main {

thirdwing

MXNet R installation with GPU support on Windows

Clone the MXNet github repo

git clone --recursive https://github.com/dmlc/mxnet

The --recursive is to clone all the submodules used by MXNet.