Ashwinkumar Ganesan codehacken

tmux shortcuts & cheatsheet

start new:

tmux

start new with session name:

tmux new -s myname

##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

	# Create a function to reshape a ndarray using a sliding window.
	# NOTE: The function uses numpy's internat as_strided function because looping in python is slow in comparison.

	# Adopted from http://www.rigtorp.se/2011/01/01/rolling-statistics-numpy.html
	import numpy as np

	# Reshape a numpy array 'a' of shape (n, x) to form shape((n - window_size), window_size, x))
	def rolling_window(a, window, step_size):
	shape = a.shape[:-1] + (a.shape[-1] - window + 1 - step_size + 1, window)
	strides = a.strides + (a.strides[-1] * step_size,)

	"""
	Hierarchial Clustering.
	The goal of gist is to show to use scikit-learn to perform agglomerative clustering when:
	1. There is a need for a custom distance metric (like levenshtein distance)
	2. Use the distance in sklearn's API.

	Adapted from: sklearn's FAQ.
	http://scikit-learn.org/stable/faq.html
	"""