Naimish Agarwal agarwalnaimish

Using Torch in Atom

Install Atom from https://atom.io or with brew cask install atom

Then install packages (example apm install hydrogen, apm is a package manager for atom):

Theano requires its compiler.

Just download GUI installer from NVIDIA and install it.

After installation you might want to try out some examples.

They are typically in C:\ProgramData\NVIDIA Corporation\CUDASamples\Vx.x\Bin\win64\Release\

##VGG19 model for Keras

This is the Keras model of the 19-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

	"""

	Example to create a neural network with one hidden layer for solving the classical XOR problem.

	Based on the lua code at
	https://github.com/torch/nn/blob/master/doc/training.md

	@author: Naimish Agarwal

	@dependencies: python 2.7, torch 7

	from keras.models import Sequential
	from keras.layers.core import Dense, Dropout, Activation, Flatten
	from keras.layers.convolutional import Convolution2D, MaxPooling2D
	from keras.layers.normalization import BatchNormalization

	#AlexNet with batch normalization in Keras
	#input image is 224x224

	model = Sequential()
	model.add(Convolution2D(64, 3, 11, 11, border_mode='full'))