s4nyam s4nyam

Deep Learning for Face Recognition (May 2016)

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

	import numpy as np
	import matplotlib.pyplot as plt
	from mpl_toolkits.mplot3d import Axes3D
	from matplotlib.animation import FuncAnimation

	def ackley(x, y):
	a = 20
	b = 0.2
	c = 2 * np.pi
	term1 = -a * np.exp(-b * np.sqrt((x2 + y2) / 2))

	import numpy as np
	import matplotlib.pyplot as plt
	from matplotlib.animation import FuncAnimation

	def fitness(x, y):
	return np.sin(x) * np.cos(y)

	mutation_range = 0.02

	population = np.array([[np.random.uniform(-5, 5), np.random.uniform(-5, 5)]])

	import numpy as np
	import matplotlib.pyplot as plt
	from matplotlib.animation import FuncAnimation
	from matplotlib.animation import PillowWriter

	# Define the initial state of the grid
	grid = np.zeros((100, 100))
	grid[1, 2] = 1
	grid[2, 3] = 1
	grid[3, 1:4] = 1

	import pygame
	import random

	# Set up the Pygame window
	pygame.init()
	screen = pygame.display.set_mode((800, 600))
	pygame.display.set_caption("Northern Lights")

	# Define some colors
	black = (0, 0, 0)

	# import the necessary packages
	import argparse
	import datetime
	import imutils
	import time
	import cv2
	from facerec.feature import Fisherfaces
	from facerec.classifier import NearestNeighbor
	from facerec.model import PredictableModel