kyubyong / tensorflow-exercises Goto Github PK

View Code? Open in Web Editor NEW

534.0 26.0 169.0 1.94 MB

TensorFlow Exercises - focusing on the comparison with NumPy.

License: Other

Python 100.00%

tensorflow tensorflow-exercises numpy

tensorflow-exercises's Introduction

TensorFlow Exercises

TensorFlow is arugably the most popular deep learning library as of 2017.

This is designed to help those who want to familiarize themselves with TensorFlow functions. Particulary, I focus on comparing TensorFlow functions with the equivalent functions in NumPy, the de facto standard numerical computation library. I hope this will help you get comfortable with TensorFlow quickly.

The basic outline will be as follows, though this is not 100% fixed.

Constants, Sequences, and Random Values (DONE)
Graphs (DONE)
Variables (DONE)
Reading Data (DONE)
Tensor Transformations (DONE)
Math Part 1 (DONE)
Math Part 2 (DONE)
Math Part 3 (DONE)
Strings (WIP)
Control Flow (DONE)
Images (WIP)
Sparse Tensors (DONE)
Neural Network Part 1 (DONE)
Neural Network Part 2 (DONE)
Neural Network Part 3 (WIP)
Seq2Seq (DONE)
Audio_Processing (DONE)

Enjoy!

tensorflow-exercises's People

Contributors

Stargazers

Watchers

Forkers

vyraun mjk276 wanjinchang qinpersevere zer0zh1 beckettman johndpope peratham limingdeng guoyinwhuthu yiweiyihang little1tow wujiahongpku sunnywanghj silverweihit jasonwuyun allensmile linyixiao shanlin-fighting ads97 irangaw yumoxu minya-wang jdc08161063 flying0er richasdy yang-xiaodong-ai thinkingslow danmartinez78 kekedan civis king-slayer sagaruprety kyocen menxia robustfengbin temcom svats2k xn0507 huklee deeplayer hanshiyi lanpay-lulu felixdae iuria21 mylearning2017 justttry zxsted jhy1993 csyanbin baojialiustc wzhihui slipwater snowman828 mrqjy kunimi00 scorpiodoctor kiramelody mlx0910 tangxinkevin samithaj gtbai wangxiaofei558 andyliu93 enggen huleg v97 hpham17 eherrerosj xerxes01 shivakrishna9 pushbound machine-learning-openprojects drxan dqwang122 pilotbear lcyyzy geeky-kakarot jianzhengming yashvijay leezqcst asurada2015 hyang428 locosoft1986 wathela nishantsbi frankfan007 marclachapelle tingxunshi vortexkd ajing strongwolf lifeiteng trunghieu4647 speedor aporia3517 watkyns fanbaoquan1025 github-allen lambdaofgod

tensorflow-exercises's Issues

W = tf.Variable(V.initialized_value() * 2.0) on Variables_Solutions.ipynb

V.initialized_value() is not a method, but it is a property.

When will you guys complete WIP?

I love your work. I am wondering when will you guys finish WIP in TF exercises.

reference

Could you list the references please? Thank you.

Error in Seq2Seq_solutions.ipynb

This line has error

loss = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=y)

It should be

loss=tf.nn.softmax_cross_entropy_with_logits(logits=logits,labels=dec_inputs)

Typo error. Please fix it in Tensor Transformation Solutions

X = tf.constant([[0, 5, 3], [4, 2, 1]])
out = tf.one_hot(x, 6)
print(out.eval())

X = tf.constant([[0, 5, 3], [4, 2, 1]])
out = tf.one_hot(X, 6)
print(out.eval())

Error in math1

Q8.

_x = np.array([1, 2, 3], np.int32)
_y = np.array([4, 5, 6], np.int32)
_z = np.array([7, 8, 9], np.int32)

should add up to [12, 15, 18], given: [9,12, 15]
Also
Q10.
_x = np.array([1, -1]) x = tf.convert_to_tensor(_x) out1 = tf.negative(x) out2 = -x print(out.eval())
should have print(out.eval()) replaced with print(out1.eval())
and the answer is correspondingly:
[-1, 1]

thanks for the great tutorial :)

kyubyong / tensorflow-exercises Goto Github PK

tensorflow-exercises's Introduction

TensorFlow Exercises

tensorflow-exercises's People

Contributors

Stargazers

Watchers

Forkers

tensorflow-exercises's Issues

W = tf.Variable(V.initialized_value() * 2.0) on Variables_Solutions.ipynb

When will you guys complete WIP?

reference

Error in Seq2Seq_solutions.ipynb

Typo error. Please fix it in Tensor Transformation Solutions

Error in math1

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent