Arash Archor arasharchor

Updated 4/11/2018

Here's my experience of installing the NVIDIA CUDA kit 9.0 on a fresh install of Ubuntu Desktop 16.04.4 LTS.

Deep Learning for Face Recognition (May 2016)

Popular architectures

FaceNet (Google)
- They use a triplet loss with the goal of keeping the L2 intra-class distances low and inter-class distances high
DeepID (Hong Kong University)
- They use verification and identification signals to train the network. Afer each convolutional layer there is an identity layer connected to the supervisory signals in order to train each layer closely (on top of normal backprop)
DeepFace (Facebook)
- Convs followed by locally connected, followed by fully connected

MapRoulette Challenge Tutorial (ßeta)

You have played MapRoulette. You have seen some of the fun challenges. If you are reading this, you are probably thinking: 'I have a great idea for the next MapRoulette challenge!'

Great! That is exactly what I am here to explain step by step. So let's get started!

Step 1 - The Idea

Storytelling from Space: Tools/Resources

This list of resources is all about acquring and processing aerial imagery. It's generally broken up in three ways: how to go about this in Photoshop/GIMP, using command-line tools, or in GIS software, depending what's most comfortable to you. Often these tools can be used in conjunction with each other.

Acquiring Landsat & MODIS

Web Interface

USGS Earth Explorer - Browser and data access (create a login)
http://earthexplorer.usgs.gov/

Landsat archive

	import matplotlib.pyplot as plt

	def draw_neural_net(ax, left, right, bottom, top, layer_sizes):
	'''
	Draw a neural network cartoon using matplotilb.

	:usage:
	>>> fig = plt.figure(figsize=(12, 12))
	>>> draw_neural_net(fig.gca(), .1, .9, .1, .9, [4, 7, 2])

	#include <opencv2/core/core.hpp>
	#include <opencv2/opencv.hpp>
	#include <opencv2/highgui/highgui.hpp>
	#include <iostream>
	#include <fcntl.h>
	#include <unistd.h>
	#include <termios.h>

	using namespace std;
	using namespace cv;

	#include <Servo.h>

	#define MIN_Y 90
	#define MAX_Y 180

	#define MIN_X 0
	#define MAX_X 180

	Servo tilt;
	Servo pan;

	'''
	This is how to track a white ball example using SimpleCV

	The parameters may need to be adjusted to match the RGB color
	of your object.

	The demo video can be found at:
	http://www.youtube.com/watch?v=jihxqg3kr-g
	'''
	print __doc__

	# "Colorizing B/W Movies with Neural Nets",
	# Network/Code Created by Ryan Dahl, hacked by samim.io to work with movies
	# BACKGROUND: http://tinyclouds.org/colorize/
	# DEMO: https://www.youtube.com/watch?v=_MJU8VK2PI4
	# USAGE:
	# 1. Download TensorFlow model from: http://tinyclouds.org/colorize/
	# 2. Use FFMPEG or such to extract frames from video.
	# 3. Make sure your images are 224x224 pixels dimension. You can use imagemagicks "mogrify", here some useful commands:
	# mogrify -resize 224x224 *.jpg
	# mogrify -gravity center -background black -extent 224x224 *.jpg