BigsnarfDude bigsnarfdude

## gist:dbf7064fa9ed08fd9f22

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                bigsnarfdude
                / gist:dbf7064fa9ed08fd9f22
            
            
              Last active
              November 26, 2015 23:34
                — forked from debasishg/gist:8172796
            
              
                A collection of links for streaming algorithms and data structures
              
          
General Background and Overview


Probabilistic Data Structures for Web Analytics and Data Mining : A great overview of the space of probabilistic data structures and how they are used in approximation algorithm implementation.
Models and Issues in Data Stream Systems
Philippe Flajolet’s contribution to streaming algorithms : A presentation by Jérémie Lumbroso that visits some of the hostorical perspectives and how it all began with Flajolet
Approximate Frequency Counts over Data Streams by Gurmeet Singh Manku & Rajeev Motwani : One of the early papers on the subject.
[Methods for Finding Frequent Items in Data Streams](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.187.9800&amp;rep


## classifier_from_little_data_script_1.py
"""
ubuntu@red:~/dev/catDogs$ THEANO_FLAGS=device=gpu,floatX=float32 python script_1.py
"""

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Convolution2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense


## classifier_from_little_data_script_2.py
"""
ubuntu@red:~/dev/catDogs$ THEANO_FLAGS=device=gpu,floatX=float32 python script_2.py
"""


import os
import h5py
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential

## classifier_from_little_data_script_3.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/

## deep_drive_model.prototxt
name: "GTANet"

# Can be used with pretrained Caffenet (AlexNet architecture).
# Layers with names containing 'gtanet' are not transferred from Caffenet.

layer {
  name: "gta_frames_input_layer"
  type: "HDF5Data"
  top: "images"
  top: "targets"

## kitti_lidar.py
"""
VISUALISE THE LIDAR DATA FROM THE KITTI DATASET

Based on the sample code from
    https://github.com/utiasSTARS/pykitti/blob/master/demos/demo_raw.py
And:
    http://stackoverflow.com/a/37863912

Contains two methods of visualizing lidar data interactively.
 - Matplotlib - very slow, and likely to crash, so only 1 out of every 100
	"""
	ubuntu@red:~/dev/catDogs$ THEANO_FLAGS=device=gpu,floatX=float32 python script_1.py
	"""

	from keras.preprocessing.image import ImageDataGenerator
	from keras.models import Sequential
	from keras.layers import Convolution2D, MaxPooling2D
	from keras.layers import Activation, Dropout, Flatten, Dense
	"""
	ubuntu@red:~/dev/catDogs$ THEANO_FLAGS=device=gpu,floatX=float32 python script_2.py
	"""


	import os
	import h5py
	import numpy as np
	from keras.preprocessing.image import ImageDataGenerator
	from keras.models import Sequential
	'''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/
	name: "GTANet"

	# Can be used with pretrained Caffenet (AlexNet architecture).
	# Layers with names containing 'gtanet' are not transferred from Caffenet.

	layer {
	name: "gta_frames_input_layer"
	type: "HDF5Data"
	top: "images"
	top: "targets"
	"""
	VISUALISE THE LIDAR DATA FROM THE KITTI DATASET

	Based on the sample code from
	https://github.com/utiasSTARS/pykitti/blob/master/demos/demo_raw.py
	And:
	http://stackoverflow.com/a/37863912

	Contains two methods of visualizing lidar data interactively.
	- Matplotlib - very slow, and likely to crash, so only 1 out of every 100