fsodogandji

##VGG16 model for Keras

This is the Keras model of the 16-layer network used by the VGG team in the ILSVRC-2014 competition.

It has been obtained by directly converting the Caffe model provived by the authors.

Details about the network architecture can be found in the following arXiv paper:

Very Deep Convolutional Networks for Large-Scale Image Recognition

K. Simonyan, A. Zisserman

fsodogandji

import numpy as np
from scipy.ndimage.interpolation import map_coordinates
from scipy.ndimage.filters import gaussian_filter

def elastic_transform(image, alpha, sigma, random_state=None):
    """Elastic deformation of images as described in [Simard2003]_.


    .. [Simard2003] Simard, Steinkraus and Platt, "Best Practices for
       Convolutional Neural Networks applied to Visual Document Analysis", in

fsodogandji

fsodogandji

fsodogandji

fsodogandji

# This script installs everything you need on an EC2 GPU Instance
# Create an Ubuntu 12.04 GPU Instance with at least 16GB of free space

# Base packages
sudo apt-get update
sudo apt-get install build-essential
sudo apt-get install gcc git cmake

# CUDA/Nvidia installations
wget http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1204/x86_64/cuda-repo-ubuntu1204_6.0-37_amd64.deb

fsodogandji

import sys

from PIL import Image, ImageDraw

try:
    import cv
except ImportError:
    print 'Could not import cv, trying opencv'
    import opencv.cv as cv

fsodogandji

import numpy,math
import matplotlib.pyplot as plt
import random as random

random.seed(1)  # set random seed.

# Draw random samples from Salpeter IMF.
# N     ... number of samples.
# alpha ... power-law index.
# M_min ... lower bound of mass interval.

fsodogandji

TL;DR

sudo pg_dropcluster 9.4 main --stop
sudo pg_upgradecluster 9.3 main
sudo pg_dropcluster 9.3 main

---

fsodogandji