Ekon22 tensorflow machinelearning2

Machine Learning
with TensorFlow
Max Kleiner 10.2018

2
TensorFlow Agenda
2https://www.esecurityplanet.com/views/article.php/1501001/Security-Threat-Correlation-The-Next-Battlefield.htm
 3 Cases
– XOR, MNIST, Image Cluster with QT 5
Sacred Experiment Log Recorder
Most experiments score with metrics as confusion matrix
 What's behind TF ? (pattern recognition)
 Cluster & Classify with different inputs, params, config
Define label or topic ratings, hyper-parameters,
– assumed/implicit labels, predict versus target
 Conclusions/ ML Data-mining Summary/

CASSANDRASystem
3
What is TensorFlow?
Intro Link to EuroPython
 Probabilistic (NB, MNB, PD,
BN, BC, PLSA, LDA, ...)
 Independence assumptions
made
 Stochastic or Distance-based
(SVM, matching, VSIM, k-
NN,CR, PageRank,Kmeans)
 Features used
 Structures exploited
 Model-based (rules, BC, BN,
boosting)
 Social media driven

4
4
https://www.springboard.com/blog/data-mining-python-tutorial/
Baseline Perceptron (MLP) with XOR
C:maXboxBASTA2018xor_perceptron.py
http://playground.tensorflow.org_maXbox1
http://playground.tensorflow.org_maXbox2

5
5
https://www.springboard.com/blog/data-mining-python-tutorial/
MNIST Classify Task
https://datascienceplus.com/mnist-for-machine-learning-beginners-with-softmax-regression/

CASSANDRASystem
7
from keras.datasets import mnist
0 1 2 3 4
5 6 7 8 9
 76 english, 38 content="voa,
 36 美国之音 " 74 special hand written
 44 Modified National Institute of Standards and
Technology database)
 36 голос 36 америки
The MNIST dataset is comprised of 70,000 handwritten numeric
digit images and their respective labels 0..9.
2. Main: C:maXboxmX46210DataScienceplot_confusion_matrix_vectormachine.py
3. Second C:maXboxmX46210DataScienceconfusionlistmnist_softmax21.py
https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/4_Utils/tensorboard_basic.ipynb
There are 60,000 training images and 10,000 test images, all of
which are 28 pixels by 28 pixels.

CASSANDRASystem
8
QT from keras import backend as K
@ex.automain
def define_and_train(batch_size, epochs,
convolution_layers, maxpooling_pool_size, maxpooling_dropout,
dense_layers, dense_dropout, final_dropout,_run):
from keras.models import Sequential #convolution
from keras.layers import Dense, Dropout, Flatten, Conv2D,
from keras.utils import to_categorical
from keras.losses import categorical_crossentropy
from keras.optimizers import Adadelta
from keras import backend as K
from keras.callbacks import ModelCheckpoint, Callback
4. C:maXboxmX46210ntwdblib.dllUnsharpDetector-masterUnsharpDetector-masterinference_gui.py

CASSANDRASystem
9
MongoDB/Sacred module import class
0 1 2 3 4
5 6 7 8 9
from __future__ import division, print_function,
unicode_literals
from sacred import Experiment
from sacred.observers import MongoObserver
from sacred.utils import apply_backspaces_and_linefeeds
import pymongo, pickle, os
import pydot as pdot
import numpy as np
import tensorflow as tf
5. C:maXboxmX46210DataScienceconfusionlisttrain_convnet_tf.py

CASSANDRASystem
10
MongoDB
 Start the shell process mongod from
 Call from script or start mongod: C:Program
FilesMongoDBServer3.6bin>mongod

CASSANDRASystem
11
MongoDB My Cluster sacred.runs & completed

12
12
MNIST Sacred Training & Test

15
15
Task III
https://pythonexample.com/search/mnist%20tensorboard%20demo/8

16
16
What's behind test ? (backend pattern, crossentropy)
60000/60000 [==============================] - 426s 7ms/step - loss: 0.4982 - acc: 0.8510 -
val_loss: 0.0788 - val_acc: 0.9749
Using TensorFlow backend.
INFO - MNIST-Convnet4 - Result: 0.9749
INFO - MNIST-Convnet4 - Completed after 0:07:27
Test loss: 0.0788029053777
Test accuracy: 0.9749
 59392/60000 [============================>.] - ETA: 5s - loss: 0.0571 - acc: 0.9829
 59520/60000 [============================>.] - ETA: 3s - loss: 0.0572 - acc: 0.9829
 59648/60000 [============================>.] - ETA: 2s - loss: 0.0572 - acc: 0.9829
 59776/60000 [============================>.] - ETA: 1s - loss: 0.0572 - acc: 0.9829
 59904/60000 [============================>.] - ETA: 0s - loss: 0.0573 - acc: 0.9829
 60000/60000 [==============================] - 513s 9ms/step - loss: 0.0573 - acc:
0.9829 - val_loss: 0.0312 - val_acc: 0.9891
 Using TensorFlow backend.
 INFO - MNIST-Convnet4 - Result: 0.9891
 INFO - MNIST-Convnet4 - Completed after 0:33:28
 Test loss: 0.0311644290059
 Test accuracy: 0.9891


17
17
What's behind code ? (keras, pymongo, pydot, graphviz)
db = pymongo.MongoClient('mongodb://localhost:27017/').sacred
print(tf.__version__)
os.environ["PATH"] += os.pathsep +
'C:/Program Files (x86)/Graphviz2.38/bin/'
from tensorflow.examples.tutorials.mnist import input_data
ex = Experiment("MNIST-Convnet4")
ex.observers.append(MongoObserver.create())
ex.captured_out_filter = apply_backspaces_and_linefeeds
https://www.programcreek.com/python/example/103267/keras.datasets.mnist.load_data

18
18https://github.com/pinae/Sacred-MNIST/blob/master/train_convnet.py
Whats behind 64-bit Python: PIP3 Install
pip3 install sacred
Collecting sacred
Downloading
https://files.pythonhosted.org/packages/2d/86/7be3af
a4d4c1c0c76a5de03e5ff779797ab2654e377685255c11c13c0e
a5/sacred-0.7.3-py2.py3-none-any.whl (82kB)
Collecting pymongo
Downloading
https://files.pythonhosted.org/packages/46/39/b9bb7fed3e3a0ea621a1
512a938c105cd996320d7d9894d8239ca9093340/pymongo-3.6.1-cp36-cp36m-
win_amd64.whl (291kB)
100% |¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦¦| 296kB 728kB/s
Installing collected packages: pymongo
Successfully installed pymongo-3.6.1

19
19
Machine Learning Jokes ;-)
1. There are two kinds of data scientists:
1) Those who can extrapolate from
incomplete data.
2. In data science, 80 percent of time
spent is preparing data, 20 percent of
time is spent complaining about the need
to prepare data.
https://maxbox4.wordpress.com/
http://www.softwareschule.ch/examples/machinelearning.jpg

CASSANDRASystem
20
https://www.kaggle.com/
similarity of doc a to doc b =
''
)',(
),(
)',(
),(
),(
word
'
2
'
2
BA
jbv
jbv
jav
jav
basim
i
jj

 


21
SUMMARY & QUESTIONS
21
https://maxbox4.wordpress.com/

Ekon22 tensorflow machinelearning2

More Related Content

Similar to Ekon22 tensorflow machinelearning2 (20)

More from Max Kleiner (20)

Recently uploaded (20)

Ekon22 tensorflow machinelearning2