Roman Trusov Lextal

## test.prototxt
input: "data"
input_dim: 1
input_dim: 3
input_dim: 256
input_dim: 512
layer {
  name: "pool"
  type: "Pooling"
  bottom: "data"
  top: "pool"

## skimage_segment.py
from skimage.segmentation import slic
from skimage.segmentation import mark_boundaries
import matplotlib.pyplot as plt

segments = slic(img, n_segments = 500, sigma = 5)
plt.imshow(mark_boundaries(imgs, segments))

## skiing-agent-writeup
if step_to_the_left or step_to_the_right:
  rasstrel()

## gist:f9857e12beafecf361e9
from sklearn.ensemble import RandomForestRegressor
from sklearn.datasets import *
from sklearn.metrics import mean_absolute_error
from sklearn.cross_validation import train_test_split

data = load_boston()
X = data['data']
y = data['target']

train_x, test_x, train_y, test_y = train_test_split(X, y, test_size=0.2)

## gist:c5ce4fcf7e6199c1c4cd
synclient TouchpadOff=1
	input: "data"
	input_dim: 1
	input_dim: 3
	input_dim: 256
	input_dim: 512
	layer {
	name: "pool"
	type: "Pooling"
	bottom: "data"
	top: "pool"
	from skimage.segmentation import slic
	from skimage.segmentation import mark_boundaries
	import matplotlib.pyplot as plt

	segments = slic(img, n_segments = 500, sigma = 5)
	plt.imshow(mark_boundaries(imgs, segments))
	from sklearn.ensemble import RandomForestRegressor
	from sklearn.datasets import *
	from sklearn.metrics import mean_absolute_error
	from sklearn.cross_validation import train_test_split

	data = load_boston()
	X = data['data']
	y = data['target']

	train_x, test_x, train_y, test_y = train_test_split(X, y, test_size=0.2)