skyer9

#!/bin/sh
# ------------------------------------------------------------------------------ 
# SOME INFOS : fairly standard (debian) init script.
#                 Note that node doesn't create a PID file (hence --make-pidfile) 
#                 has to be run in the background (hence --background)
#                 and NOT as root (hence --chuid)
#
# MORE INFOS :  INIT SCRIPT       http://www.debian.org/doc/debian-policy/ch-opersys.html#s-sysvinit
#               INIT-INFO RULES   http://wiki.debian.org/LSBInitScripts
#               INSTALL/REMOVE    http://www.debian-administration.org/articles/28

skyer9

'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.

It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data

In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/

skyer9

# -*- coding: utf-8 -*-
"""Sequence-to-sequence model with an attention mechanism."""

# original code
# https://gist.github.com/pannous/b3f8ab944a85b33e694de21c6ded029e

# see https://www.tensorflow.org/versions/r0.10/tutorials/seq2seq/index.html
# compare https://github.com/tflearn/tflearn/blob/master/examples/nlp/seq2seq_example.py
from __future__ import print_function
import numpy as np

skyer9

{
  "AWSTemplateFormatVersion" : "2010-09-09",

  "Description" : "ElasticSearch Cluster.",

  "Parameters" : {

    "KeyName": {
      "Description" : "The name of an existing key pair to enable SSH access to Amazon EC2 instances",
      "Type": "String",