Nik georgeblck

The repository for the assignment is public and Github does not allow the creation of private forks for public repositories.

The correct way of creating a private frok by duplicating the repo is documented here.

For this assignment the commands are:

Create a bare clone of the repository. (This is temporary and will be removed so just do it wherever.)

git clone --bare [email protected]:usi-systems/easytrace.git

R - Interactive Sessions and Command Line Interface

This is a template for R projects that should work both on the command line as well as in an interactive session.

The template is made up of three files:

install cuda-9.0 (https://developer.nvidia.com/cuda-toolkit-archive)
install cudnn-7 (https://developer.nvidia.com/cudnn)
install dependencies for caffe
- see the caffe installation guide [1] and wiki page [2]
install boost-1.65 or higher (http://www.boost.org/users/history/version_1_65_1.html) [3]
update caffe-fast-rcnn
- Easiest way is to use a rebased branch on BVLC/master. See the notes below if you would rather merge the changes yourself.
```
$ cd $FRCN_ROOT/caffe-fast-rcnn
```

	"""
	This is a batched LSTM forward and backward pass
	"""
	import numpy as np
	import code

	class LSTM:

	@staticmethod
	def init(input_size, hidden_size, fancy_forget_bias_init = 3):

	library(cdlTools)
	library(rgdal)
	library(raster)
	library(rgeos)


	# rasterize in the R 'raster' package is really slow, depending on your needs this may work better
	# Author: Jonathan Lisic
	# License BSD
	polyExtract <- function(x) {

	"""
	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))
	data_size, vocab_size = len(data), len(chars)

	# Tiny example of 3-layer nerual network with dropout in 2nd hidden layer
	# Output layer is linear with L2 cost (regression model)
	# Hidden layer activation is tanh

	import numpy as np

	n_epochs = 100
	n_samples = 100
	n_in = 10
	n_hidden = 5

	def multireplace(string, replacements, ignore_case=False):
	"""
	Given a string and a replacement map, it returns the replaced string.

	:param str string: string to execute replacements on
	:param dict replacements: replacement dictionary {value to find: value to replace}
	:param bool ignore_case: whether the match should be case insensitive
	:rtype: str

	"""

	## youtube video: https://youtu.be/AJDo9gpkEcg
	library("readr")
	library("ggplot2")

	## read.csv() <- from base R. DON'T USE!
	hw5 <- read_csv("homework_5.csv") # from readr

	hw5$A <- factor(hw5$A)
	hw5$B <- factor(hw5$B)
	hw5$C <- factor(hw5$C)

	using MXNet
	import MXNet.mx: _update_single_output, reset!, get

	using Distributions

	#####################################
	# Custom evaluation metric
	# It just summarize predictions, because in the case of custom
	# loss layer, ANN output equals to loss function itself