Deep Learning: Difference between revisions

From Edgar BV Wiki
Jump to navigation Jump to search
 
(5 intermediate revisions by the same user not shown)
Line 51: Line 51:
Then delete the space at the end of the file
Then delete the space at the end of the file


To explore the categories
OR
<pre>
head -n 10 Kickstarter_2017-10-15T10_20_38_271Z.json | awk '{print "["} BEGIN {RS=""}{ gsub(/\n/,", &") ; print } END{print "]"}'
awk '{print "["} BEGIN {RS=""}{ gsub(/\n/,", \n") ; print } {print "]"}'
</pre>
 
To explore the category
<pre>
<pre>
jq '.[].data.category.name' Kickstarter_2017-09-15T22_20_48_432Z.json | sort -u > categorylist09
jq '.[].data.category.name' Kickstarter_2017-09-15T22_20_48_432Z.json | sort -u > categorylist09
Line 59: Line 65:
cat categorylist08 categorylist09 | sort -u > categorylist
cat categorylist08 categorylist09 | sort -u > categorylist
</pre>
</pre>
NB using uniq here won't work as this only looks for the first occurence


[https://webrobots.io/indiegogo-dataset/ Indigogo dataset]
[https://webrobots.io/indiegogo-dataset/ Indigogo dataset]

Latest revision as of 10:03, 17 November 2017

Books

Deep learning primer (video)

AI Playbook by Andreessen Horowitz

Deep Learning

An MIT Press book

Ian Goodfellow and Yoshua Bengio and Aaron Courville

Sutton & Barto 2nd edition

File:Bookdraft2016sep.pdf

Understanding Machine Learning: From Theory to Algorithms

File:Understanding-machine-learning-theory-algorithms.pdf

Presentations

Learn TensorFlow and deep learning, without a Ph.D.

Practice

Khan Academy Linear Algebra

OpenAI Gym

Script to figure out what an space_action is doing

action = 0  # modify this!
o = env.reset()
for i in xrange(5): # repeat one action for five times
    o = env.step(action)[0]
IPython.display.display(
    Image.fromarray(
        o[:,140:142]  # extract your bat
    ).resize((300, 300))  # bigger image, easy for visualization
)

From here

Datasets

Kickstarter dataset

in vim the following:

:%s/\n/,\r/g

Then delete the space at the end of the file

OR

head -n 10 Kickstarter_2017-10-15T10_20_38_271Z.json | awk '{print "["} BEGIN {RS=""}{ gsub(/\n/,", &") ; print } END{print "]"}'
awk '{print "["} BEGIN {RS=""}{ gsub(/\n/,", \n") ; print } {print "]"}'

To explore the category

jq '.[].data.category.name' Kickstarter_2017-09-15T22_20_48_432Z.json | sort -u > categorylist09

jq '.[].data.category.name' Kickstarter_2017-08-15T22_20_51_958Z.json | sort -u > categorylist08

cat categorylist08 categorylist09 | sort -u > categorylist

NB using uniq here won't work as this only looks for the first occurence

Indigogo dataset

Useful file manipulation

jq . filename (for jason queries) (see also Jq json file manipulation)

wc -l filename (counts amount of lines)

head -n 10 filename > filename2 (sends top 10 lines of code to filename2)

NB. sed can't find and replace newlines as it encapsulates the file being streamed and gets rid of the newlines.