yenchenlin

import timeit
import numpy as np
from sklearn.cluster import KMeans

np.random.seed(5)
X = np.random.rand(200000, 20)
X = np.float32(X)
estimator = KMeans()

yenchenlin

Caffe Installation

Note on how to install caffe on Ubuntu. Sucessfully install using CPU, more information for GPU see this link

###Installation

• verify all the preinstallation according to CUDA guide e.g.

lspci | grep -i nvidia

yenchenlin

I've tried to make SequentialDataset support Cython fused types, but it seems really expensive. You can find the modified code in this branch.

tl;dr - seq_dataset.pyx is heavily bound with sag_fast.pyx, sgd_fast.pyx.

After I modified seq_dataset.pyx, this line in sag_fast.pyx requires to change as well since this pointer is passed into SequentialDataset's function. However, my past experience is that one can only declare local floating variable when at least one of the function's argument variable also belongs to floating type. Nonetheless, that's not the case here, unless we make this function's arguments

np.ndarray[double, ndim=2, mode='c'] weights_array
np.ndarray[double, ndim=1, mode='c'] intercept_array

yenchenlin

Merged Works

• #6593 Use fused types in sparse mean variance functions
• #6664 Make cython compiler directives global
• #6785 Make csr row norms support fused types
• #6846 Allows KMeans/MiniBatchKMeans to use float32 internally by using cython fused types
• #7053 Reduce duplicated code in _k_means.pyx
• #7170 Make Silhouette_score support sparse X
• #7184 Add whats_new about fixing example
• #7187 Rename CV params n_{folds,iter} to n_splits

yenchenlin

require 'torch'
require 'nn'
require 'optim'

-- to specify these at runtime, you can do, e.g.:
--    $ lr=0.001 th main.lua
opt = {
  dataset = 'video2',   -- indicates what dataset load to use (in data.lua)
  nThreads = 32,        -- how many threads to pre-fetch data
  batchSize = 64,      -- self-explanatory

yenchenlin

import tensorflow as tf
import numpy

from sklearn.datasets import fetch_mldata

FLAGS = tf.app.flags.FLAGS

tf.app.flags.DEFINE_integer('seed', 1, "initial random seed")

tf.app.flags.DEFINE_string('layer_sizes', '784-1200-600-300-150-10', "layer sizes")

yenchenlin

yenchenlin

Environment

First, make sure we have the right environment. Comment out the conda command in ~/.bashrc and run

source ~/.bashrc
conda activate corl

After that, comment out the conda command and open a new tab will get back to python 2.7 environment.

yenchenlin

Writing tips

The golden rule: do the most, with the least

General advice

11 rules

(1-4 and 11 adapted from George Orwell's six rules)

• Rule 1: Never use a metaphor, simile, or other figure of speech that you are used to seeing in print
• Rule 2: Never use jargon if you can think of an everyday English equivalent

yenchenlin

Figure tips

General advice

• Spend as much time on figures as you do on writing
• Use perceptual grouping to your advantage
• Never use default graphical styles; develop your own brand
• Minimize the data-ink ratio
• The figure should be understandable without reading the caption

Perceptual grouping