Programing with Deep Neural Networks dneuraln

## classifier_from_little_data_script_2.py
'''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/

## min-char-rnn.py
"""
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)

## elastic_transform.py
import numpy
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

## minibatch version of KL and JS divergences.ipynb

      
              1 file
            
          
              0 forks
            
          
                0 comments
              
            
              0 stars
            
          
                dneuraln
                / minibatch version of KL and JS divergences.ipynb
            
            
              Created
              August 4, 2016 10:32
                — forked from fhuszar/minibatch version of KL and JS divergences.ipynb
            
          
      Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## gputest.lua
-- Max Jaderberg 4/9/13
-- GPU Effectiveness test

require 'torch'
require 'sys'
require 'nn'
require 'xlua'

cmd = torch.CmdLine()
cmd:text()

## conv_deconv_variational_autoencoder.py
import theano
import theano.tensor as T
from theano.sandbox.rng_mrg import MRG_RandomStreams as RandomStreams
from theano.tensor.signal.downsample import max_pool_2d
from theano.tensor.extra_ops import repeat
from theano.sandbox.cuda.dnn import dnn_conv

from time import time
import numpy as np
from matplotlib import pyplot as plt

## conv_deconv_vae.py
# Alec Radford, Indico, Kyle Kastner
# License: MIT
"""
Convolutional VAE in a single file.
Bringing in code from IndicoDataSolutions and Alec Radford (NewMu)
Additionally converted to use default conv2d interface instead of explicit cuDNN
"""
import theano
import theano.tensor as T
from theano.compat.python2x import OrderedDict

## mdn_demo_theano.py
# -*- coding: utf-8 -*-
"""
Created on Mon Aug 22 00:36:48 2016

@author: park
"""

#%% train

import theano

## train_imagenet_32x32_gan.py
import sys
sys.path.append('..')

import os
import json
from time import time
import numpy as np
from tqdm import tqdm
from matplotlib import pyplot as plt
from sklearn.externals import joblib

## blog_tensorflow_variable_sequence_labelling.py
# Working example for my blog post at:
# http://danijar.com/variable-sequence-lengths-in-tensorflow/
import functools
import sets
import tensorflow as tf
from tensorflow.models.rnn import rnn_cell
from tensorflow.models.rnn import rnn


def lazy_property(function):
	'''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/
	"""
	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)
	import numpy
	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
	-- Max Jaderberg 4/9/13
	-- GPU Effectiveness test

	require 'torch'
	require 'sys'
	require 'nn'
	require 'xlua'

	cmd = torch.CmdLine()
	cmd:text()
	import theano
	import theano.tensor as T
	from theano.sandbox.rng_mrg import MRG_RandomStreams as RandomStreams
	from theano.tensor.signal.downsample import max_pool_2d
	from theano.tensor.extra_ops import repeat
	from theano.sandbox.cuda.dnn import dnn_conv

	from time import time
	import numpy as np
	from matplotlib import pyplot as plt
	# Alec Radford, Indico, Kyle Kastner
	# License: MIT
	"""
	Convolutional VAE in a single file.
	Bringing in code from IndicoDataSolutions and Alec Radford (NewMu)
	Additionally converted to use default conv2d interface instead of explicit cuDNN
	"""
	import theano
	import theano.tensor as T
	from theano.compat.python2x import OrderedDict
	# -- coding: utf-8 --
	"""
	Created on Mon Aug 22 00:36:48 2016

	@author: park
	"""

	#%% train

	import theano
	import sys
	sys.path.append('..')

	import os
	import json
	from time import time
	import numpy as np
	from tqdm import tqdm
	from matplotlib import pyplot as plt
	from sklearn.externals import joblib
	# Working example for my blog post at:
	# http://danijar.com/variable-sequence-lengths-in-tensorflow/
	import functools
	import sets
	import tensorflow as tf
	from tensorflow.models.rnn import rnn_cell
	from tensorflow.models.rnn import rnn


	def lazy_property(function):