Dan Becker dansbecker

##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

	'''Train a simple deep CNN on the CIFAR10 small images dataset.

	GPU run command:
	THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python cifar10_cnn.py

	It gets down to 0.65 test logloss in 25 epochs, and down to 0.55 after 50 epochs.
	(it's still underfitting at that point, though).

	Note: the data was pickled with Python 2, and some encoding issues might prevent you
	from loading it in Python 3. You might have to load it in Python 2,

	import numpy as np
	from keras.models import Model
	from keras.layers import Input, Dense

	input_size = 1000
	n_obs = 200
	encoding_size = 50

	x = Input(shape=(input_size,))
	z = Dense(encoding_size, activation='sigmoid', name='z')(x)

	from keras.layers import Input, Dense, merge, Flatten
	from keras.layers.convolutional import Convolution2D
	from keras.models import Model, model_from_json
	from keras import backend as K

	def make_model(img_edge_size):

	img_shape = (3, img_edge_size, img_edge_size)
	mask_shape = (1, img_edge_size, img_edge_size)

	$ cat CMakeFiles/CMakeOutput.log
	The system is: CYGWIN - 2.6.0(0.304/5/3) - x86_64
	Compiling the C compiler identification source file "CMakeCCompilerId.c" succeeded.
	Compiler: /usr/bin/cc
	Build flags:
	Id flags:

	The output was:
	0

	Determining if the function dgettext exists failed with the following output:
	Change Dir: /home/powersju/Madeline_2.0_PDE/CMakeFiles/CMakeTmp

	Run Build Command:"/usr/bin/make.exe" "cmTC_872e9/fast"
	/usr/bin/make -f CMakeFiles/cmTC_872e9.dir/build.make CMakeFiles/cmTC_872e9.dir/build
	make[1]: Entering directory '/home/powersju/Madeline_2.0_PDE/CMakeFiles/CMakeTmp'
	Building C object CMakeFiles/cmTC_872e9.dir/CheckFunctionExists.c.o
	/usr/bin/cc -DCHECK_FUNCTION_EXISTS=dgettext -o CMakeFiles/cmTC_872e9.dir/CheckFunctionExists.c.o -c /usr/share/cmake-3.6.2/Modules/CheckFunctionExists.c
	<command-line>:0:23: warning: conflicting types for built-in function ‘dgettext’
	/usr/share/cmake-3.6.2/Modules/CheckFunctionExists.c:7:3: note: in expansion of macro ‘CHECK_FUNCTION_EXISTS’

	from keras.applications.resnet50 import ResNet50, preprocess_input
	from keras.preprocessing.image import load_img, img_to_array
	import numpy as np
	from os import listdir
	from os.path import join
	import pandas as pd


	def featurize(fpath, model, img_size):
	'''Use trained model to convert image to vector describing content

	from sklearn.datasets import fetch_20newsgroups
	from sklearn.feature_extraction.text import TfidfVectorizer

	from sklearn.linear_model import LogisticRegression
	# A pipeline "stitches together" the various steps of a modeling process into a single piece. You should either try to get a separate explanation of this, or try to do without it.
	# In general pipelines are pretty cool. But, one more thing to learn.
	from sklearn.pipeline import Pipeline
	import pandas as pd
	import numpy as np