9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

ADVENTURES IN MACHINE LEARNING

LEARN AND EXPLORE MACHINE LEARNING

ABOUT CONTACT

Python TensorFlow
POPULAR TUTORIALS

Tutorial Build a Neural Neural Networks Tutorial A

Pathway to Deep Learning

Network Python TensorFlow Tutorial

Build a Neural Network
April 8, 2017 Andy Deep learning, Neural networks, Convolutional Neural Networks
TensorFlow 12 Tutorial in TensorFlow
Keras tutorial build a
convolutional neural network in
11 lines
Word2Vec word embedding
tutorial in Python and
TensorFlow

CATEGORIES

CNTK

Convolutional Neural Networks

The TensorFlow logo Deep learning

gensim
Googles
TensorFlow Keras
hasbeen a
Neural networks
hottopic in
deep learning NLP
recently.The
Optimisation
open source
software, TensorFlow
designed to
Word2Vec
Machine Learning Course allow e cient
computation
Learn to make
of data ow
Predictive Models
graphs, is

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 1/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

especially suited to deep learning tasks. It is designed to be

executed on single or multiple CPUs and GPUs, making it a good
option for complex deep learning tasks. In its most recent
incarnation version 1.0 it can even be run on certain mobile
operating systems. This introductory tutorial to TensorFlow will
givean overview ofsome of the basic concepts of TensorFlow in
Python. These will be a good stepping stone to building more
complexdeep learningnetworks, such as Convolution Neural
Networks, natural language models and Recurrent Neural
Networks in the package. Well be creating a simple three-layer
neural network to classify the MNIST dataset. This tutorial
assumes that you are familiar with the basics of neural networks,
which you can get up to scratch with in the neural networks
tutorial if required. Toinstall TensorFlow, follow the instructions
here. The code for this tutorial can be found in this sites GitHub
repository. Once youre done, you also might want to check out a
higher level deep learning library that sits on top of TensorFlow
called Keras see my Keras tutorial.

Recommended online course: Once youve read this post, and

youd like to learn more in a video course, Id recommend the
following inexpensive Udemy course: Data Science: Practical Deep
Learning in Theano + TensorFlow

First, lets have a look at the main ideas of TensorFlow.

1.0TensorFlow graphs NEWSLETTER + FREE

EBOOK
TensorFlow is based on graph based computation what on earth
is that?, you might say. Its an alternative way ofconceptualising Email address:
mathematical calculations. Consider the following expression Your email address
a = (b + c) (c + 2) . We can break this function down into the
SIGN UP
following components:

d = b + c FIND US ON FACEBOOK
e = c + 2

a = d e
Adventures in Machine L
Now we can represent these operations graphically as: Liked 2.1K likes

You like this

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 2/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

Simple computational graph

This may seem like a silly example but notice a powerful idea in
expressing the equation this way: two of the computations (
d = b + c and e = c + 2 ) can be performed in parallel. By
splitting up these calculations across CPUs or GPUs, this can give
us signi cant gains in computational times.Thesegains are a must
for big data applications and deep learning especially for
complicated neural network architectures such as Convolutional
Neural Networks (CNNs) and Recurrent Neural Networks (RNNs).
The idea behind TensorFlow is to ability to create these
computational graphs in code and allow signi cant performance
improvements via parallel operations and other e ciency gains.

We can look at a similar graph in TensorFlow below, which shows

the computational graph of a three-layer neural network.

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 3/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

TensorFlow data ow graph

The animated data ows between di erent nodes in the graph are
tensors which are multi-dimensional data arrays. For instance, the
input data tensor may be 5000 x 64 x 1, which represents a 64
node input layer with 5000 training samples. After the input layer
there is a hidden layer with recti ed linear units as the activation
function. There is a nal output layer (called a logit layer in the
above graph) which uses cross entropy as a cost/loss function. At
each point we see therelevant tensors owing to the Gradients
block which nally ow to the Stochastic Gradient Descent
optimiser which performs the back-propagation and gradient
descent.

Here we can see how computational graphs can be used to

represent the calculations in neural networks, and this, of course,
is what TensorFlow excels at. Lets see how to perform some basic
mathematical operations in TensorFlow to get a feel for how it all
works.

2.0 A Simple TensorFlow

example
Lets rst make TensorFlow perform our littleexample
calculationabove a = (b + c) (c + 2) . First we need to

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 4/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

introduce ourselves to TensorFlow variables and constants. Lets

declare some then Ill explain the syntax:

import tensorflow as tf

# first, create a TensorFlow constant

const = tf.constant(2.0, name="const")

# create TensorFlow variables

b = tf.Variable(2.0, name='b')
c = tf.Variable(1.0, name='c')

As can be observed above, TensorFlow constants can be declared

using the tf.constant function, and variables with the tf.Variable
function. The rst element in both is the value to be assigned the
constant / variable when it is initialised. The second is an optional
name string which can be used to label the constant / variable
this is handy for when you want to do visualisations (as will be
discussed brie y later). TensorFlow will infer the type of the
constant / variable from the initialised value, but it can also be set
explicitly using the optional dtype argument. TensorFlow has many
of its own types like tf. oat32, tf.int32 etc. see them all here.

Its important to note that, as the Python code runs through these
commands, the variables havent actually been declared as they
would have been if you just had a standard Python declaration (i.e.
b= 2.0). Instead, all the constants, variables, operationsand the
computational graph are only created when the initialisation
commands are run.

Next, we create the TensorFlow operations:

# now create some operations

d = tf.add(b, c, name='d')
e = tf.add(c, const, name='e')
a = tf.multiply(d, e, name='a')

TensorFlow has a wealth of operations available to perform all

sorts of interactions between variables, some of which well get to
later in the tutorial. The operations above are pretty obvious, and
they instantiate the operations b + c, c + 2.0 and d e.

The next step is to setup an object to initialise the variables and the
graph structure:

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 5/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

# setup the variable initialisation

init_op = tf.global_variables_initializer()

Ok, so now we are all set to go. To run the operations between the
variables, we need to start a TensorFlow session tf.Session. The
TensorFlow session is an object where all operations are run.
Using the with Python syntax, we can run the graph with the
following code:

# start the session

with tf.Session() as sess:
# initialise the variables
sess.run(init_op)
# compute the output of the graph
a_out = sess.run(a)
print("Variable a is {}".format(a_out))

The rst command within the with block is the initialisation, which
is run with the, well, run command. Next we want to gure out
what the variable a should be. All we have to do is run the
operation which calculates a i.e. a = tf.multiply(d, e, name=a). Note
that a is an operation, not a variable and therefore it can be run.
We do just that with the sess.run(a) command and assign the
output to a_out, the value of which we then print out.

Note something cool we de ned operations d and e which need

to be calculated before we can gure out what a is.However, we
dont have to explicitly run those operations, as TensorFlow knows
what other operations and variables the operation a depends on,
and therefore runs the necessary operations on its own. It does
this through its data ow graph which shows it all the required
dependencies. Using the TensorBoard functionality, we can see the
graph that TensorFlow created in this little program:

Simple TensorFlow graph

Now thats obviouslya trivial example what if we had an array of

b values that we wanted to calculate the value of a over?

2.1 The TensorFlow placeholder

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 6/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

2.1 The TensorFlow placeholder

Lets also say that we didnt know what the value of the array b
would be during the declaration phase of the TensorFlow problem
(i.e. before the with tf.Session() as sess) stage. In this case,
TensorFlow requires us to declare the basic structure of the data
by using the tf.placeholder variable declaration. Lets use it for b:

# create TensorFlow variables

b = tf.placeholder(tf.float32, [None, 1], name='b')

Because we arent providing an initialisation in this declaration, we

need to tell TensorFlow what data type each element within the
tensor is going to be. In this case, we want to use tf. oat32. The
second argument is the shape of the data that will be injected
into this variable. In this case, we want to use a (? x 1) sized array
because we are being cagey about how much data we are
supplying to this variable (hence the ?), the placeholder is willing
to accept a None argument in the size declaration. Now we can
inject as much 1-dimensional data that we want into the b variable.

The only other change we need to make to our program is in the

sess.run(a,) command:

a_out = sess.run(a, feed_dict={b: np.arange(0, 10)[:,

np.newaxis]})

Note that we have added the feed_dict argument to the sess.run(a,

) command. Here we remove the mystery and specify exactly
what the variable b is to be a one-dimensionalrange from 0 to
10. As suggested by the argument name, feed_dict, the input to be
supplied is a Python dictionary, with each key being the name of
the placeholder that we are lling.

When we run the program again this time we get:

Variable a is [[ 3.]
[ 6.]
[ 9.]
[ 12.]
[ 15.]
[ 18.]
[ 21.]
[ 24.]

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 7/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

[ 27.]
[ 30.]]

Notice how TensorFlow adapts naturally from a scalar output (i.e. a

singular output when a=9.0) to a tensor (i.e. an array/matrix)? This
isbased on its understanding of how the data will ow through the
graph.

Now we are ready to build a basic MNIST predicting neural

network.

3.0A Neural Network

Example
Now well go through an example in TensorFlow of creating a
simple three layer neural network. In future articles, well show
how to build more complicated neural network structures such as
convolution neural networks and recurrent neural networks. For
this example though, well keep it simple. If you need to scrub up
on your neural network basics, check out my popular tutorial on
the subject. In this example, well be using the MNIST dataset (and
its associated loader) that the TensorFlow package provides. This
MNIST dataset is a set of 2828 pixel grayscale images which
represent hand-written digits. It has 55,000 training rows, 10,000
testing rows and 5,000 validation rows.

We can load the data by running:

from tensorflow.examples.tutorials.mnist import

input_data
mnist = input_data.read_data_sets("MNIST_data/",
one_hot=True)

The one_hot=True argument speci es that instead of the labels

associated witheach image being the digit itselfi.e. 4, it is a
vector with one hot node and all the other nodes being zero i.e.
[0,0, 0,0, 1, 0, 0, 0, 0, 0]. This lets us easily feed it into the output
layer of our neural network.

3.1 Setting things up

Next, we can set-up the placeholder variables forthe training data
(and some training parameters):

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 8/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

# Python optimisation variables

learning_rate = 0.5
epochs = 10
batch_size = 100

# declare the training data placeholders

# input x - for 28 x 28 pixels = 784
x = tf.placeholder(tf.float32, [None, 784])
# now declare the output data placeholder - 10 digits
y = tf.placeholder(tf.float32, [None, 10])

Notice the x input layer is 784 nodes corresponding to the 28 x 28

(=784) pixels, and the y output layer is 10 nodes corresponding to
the 10 possible digits. Again, the size of x is (?x 784), where the ?
stands for an as yet unspeci ed number of samples to be input
this is the function of the placeholder variable.

Now we need to setup the weight and bias variables for the three
layer neural network. There are always L-1 number of weights/bias
tensors, where L is the number of layers. Soin this case, we need
975
to setup two tensors for each:
Shares

# now declare the weights connecting the input to the

793hidden layer
W1 = tf.Variable(tf.random_normal([784, 300],
161stddev=0.03), name='W1')
b1 = tf.Variable(tf.random_normal([300]), name='b1')
# and the weights connecting the hidden layer to the
output layer
W2 = tf.Variable(tf.random_normal([300, 10],
stddev=0.03), name='W2')
b2 = tf.Variable(tf.random_normal([10]), name='b2')

Ok, so lets unpack the above code a little. First, we declare some
variables for W1 and b1, the weights and bias for the connections
between the input and hidden layer. This neural network will have
300 nodes in the hidden layer, so the size of the weight tensor W1
is [784, 300]. We initialise the values of the weights using a random
normal distribution with a mean of zero and a standard deviation
of 0.03. TensorFlow has a replicated version of the numpy
random normal function, which allows you to create a matrix of a
given size populated with random samples drawn from a given
distribution. Likewise, we create W2 and b2 variables to connect
the hidden layer to the output layer of the neural network.

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 9/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

Next, we have to setup node inputs and activation functions of the

hidden layer nodes:

# calculate the output of the hidden layer

hidden_out = tf.add(tf.matmul(x, W1), b1)
hidden_out = tf.nn.relu(hidden_out)

In the rst line, we execute the standard matrix multiplication of

the weights (W1)by the input vector x and we add the bias b1. The
matrix multiplication is executed using the tf.matmul operation.
Next, we nalise the hidden_out operation by applying a recti ed
linear unit activation function to the matrixmultiplication plus
bias. Note that TensorFlow has arecti ed linear unit activation
already setup for us, tf.nn.relu.

This is to execute the following equations, as detailed in the neural

networks tutorial:

(l+1) (l) (l)

z = W x + b

(l+1) (l+1)
h = f (z )

Now, lets setup the output layer, y_:

# now calculate the hidden layer output - in this

case, let's use a softmax activated
# output layer
y_ = tf.nn.softmax(tf.add(tf.matmul(hidden_out, W2),
b2))

Again we perform the weight multiplication with the output from

the hidden layer (hidden_out) and add the bias, b2. In this case, we
are going to use a softmax activation for the output layer we can
use theincluded TensorFlowsoftmax function tf.nn.softmax.

We also have to include a cost or loss function for the

optimisation/ backpropagationto work on.Here well use the
cross entropy cost function, represented by:

m n
1 (i) (i)
(i) (i)
J = y log(y j _ ) + (1 y )log(1 y j _ )
j j
m
i=1 j=1

Where y j is the ith training label for output node j, y j _(i) is the
(i)

ith predicted label for output node j, m is the number of training /

batch samples and n is the number . There are two operations
occurring in the above equation. The rst is the summation of the
logarithmic products and additions across all the output nodes. The
http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 10/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

second is taking a mean of this summation across all the training

samples. We can implement this crossentropy cost function
inTensorFlow with the following code:

y_clipped = tf.clip_by_value(y_, 1e-10, 0.9999999)

cross_entropy = -tf.reduce_mean(tf.reduce_sum(y *
tf.log(y_clipped)
+ (1 - y) * tf.log(1 -
y_clipped), axis=1))

Some explanation is required. The rst line is an operation

converting the output y_ to a clipped version, limited between 1e-
10 to 0.999999. This is to make sure that we never get acase were
we havea log(0) operation occurring during training this would
return NaN and break the training process. The second line is the
cross entropy calculation.

To perform this calculation, rst we use TensorFlows tf.reduce_sum

function this function basically takes the sum of a given axis of
the tensor you supply. In this case, the tensor that is supplied is
the element-wise cross-entropy calculation for a single node and
training sample i.e.: y j .
(i) (i) (i) (i)
log(y j _ ) + (1 y )log(1 y j _ )
j

Remember that y and y_clipped in the above calculation are (mx 10)
tensors therefore we need to perform the rst sum over the
second axis. This is speci ed using the axis=1 argument, where 1
actually refers to the second axis when we have a zero-based
indices system like Python.

After this operation, we have an (m x 1) tensor. To take the mean

of this tensorand complete our cross entropy cost calculation (i.e.
execute this part ), we use TensorFlows tf.reduce_mean
1 m

m i=1

function. This function simply takes the mean of whatever tensor

you provide it. So now we have a cost function that we can use in
the training process.

Lets setup the optimiser in TensorFlow:

# add an optimiser
optimiser =
tf.train.GradientDescentOptimizer(learning_rate=learni
ng_rate).minimize(cross_entropy)

Here we are just using the gradient descent optimiser provided by

TensorFlow. We initialize it with a learning rate, then specify what
we want it to do i.e. minimise the cross entropy cost operationwe
created. This function will then perform the gradient descent (for
http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 11/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

more details on gradient descent see here and here) and the
backpropagationfor you. How easy is that? TensorFlow has a
library of popular neural networktraining optimisers, see here.

Finally, before we move on to the main show, were we actually run

the operations, lets setup the variable initialisation operation and
an operation to measure the accuracy of our predictions:

# finally setup the initialisation operator

init_op = tf.global_variables_initializer()

# define an accuracy assessment operation

correct_prediction = tf.equal(tf.argmax(y, 1),
tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,
tf.float32))

The correct prediction operation correct_prediction makes use of

the TensorFlow tf.equal function which returns True or False
depending on whether to arguments supplied to it are equal. The
tf.argmax function is the same as the numpy argmax function,
which returns the index of the maximum value in a vector / tensor.
Therefore, the correct_prediction operation returns a tensor of
size(m x 1) of True and False values designating whether the neural
network has correctly predicted the digit. We then want to
calculate the mean accuracyfrom this tensor rst we have to cast
the type of the correct_prediction operation from a Boolean to a
TensorFlow oat in order toperform thereduce_mean operation.
Once weve done that, we now have an accuracy operation ready to
assess the performance of our neural network.

3.2 Setting up the training

Wenow have everything we need to setup the trainingprocess of
our neural network. Im going to show the full code below, then
talk through it:

# start the session

with tf.Session() as sess:
# initialise the variables
sess.run(init_op)
total_batch = int(len(mnist.train.labels) /
batch_size)
for epoch in range(epochs):
avg_cost = 0
for i in range(total_batch):

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 12/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

batch_x, batch_y =
mnist.train.next_batch(batch_size=batch_size)
_, c = sess.run([optimiser,
cross_entropy],
feed_dict={x: batch_x, y:
batch_y})
avg_cost += c / total_batch
print("Epoch:", (epoch + 1), "cost =", "
{:.3f}".format(avg_cost))
print(sess.run(accuracy, feed_dict={x:
mnist.test.images, y: mnist.test.labels}))

Stepping through the lines above, the rst couple relate to setting
up the with statement and running the initialisation operation. The
third line relates to our mini-batch training scheme that we are
going to run for this neural network. If you want to know about
mini-batch gradient descent, check out this post. In the third line,
we are calculating the number of batches to run through in each
training epoch. After that, we loop through each training epoch
and initialise an avg_cost variable to keep track of the average cross
entropy cost for each epoch. The next line is where we extract a
randomised batch of samples, batch_xand batch_y, from the MNIST
training dataset. The TensorFlow provided MNIST dataset has a
handy utility function, next_batch,that makes it easy to extract
batches of data for training.

The following line is where we run two operations. Notice that

sess.run is capable of taking a list of operations to run as its rst
argument. In this case, supplying [optimiser, cross_entropy] as the
list means that both these operations will be performed. As such,
we get two outputs, which we have assigned to the variables _ and
c. We dont really care too much about the output from the
optimiser operation but we want to know the output from the
cross_entropy operation which we have assigned to the variable c.
Note, we run the optimiser (and cross_entropy) operation on the
batch samples. In the following line, we use c to calculate the
average cost for the epoch.

Finally, we print out our progress in the average cost, and after the
training is complete, we run the accuracy operation to print out the
accuracy of our trained network on the test set. Running this
program produces the following output:

Epoch: 1 cost = 0.586

Epoch: 2 cost = 0.213
Epoch: 3 cost = 0.150
Epoch: 4 cost = 0.113
http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 13/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

Epoch: 5 cost = 0.094

Epoch: 6 cost = 0.073
Epoch: 7 cost = 0.058
Epoch: 8 cost = 0.045
Epoch: 9 cost = 0.036
Epoch: 10 cost = 0.027

Training complete!
0.9787

There we go approximately 98% accuracy on the test set, not

bad. We could do a number of things to improve the model, such
as regularisation (see this tips and tricks post), but here we are
just interested in exploring TensorFlow. You can also use
TensorBoard visualisation to look at things like the increase in
accuracyover the epochs:

TensorBoard plot of the increase in accuracy over 10 epochs

In a future article, Ill introduce you to TensorBoard visualisation,

which is a really nice feature of TensorFlow. For now, I hope this
tutorial was instructive and helps get you going on the TensorFlow
journey. Just a reminder, you can check out the code for this post
here. Ive also written an article that shows you how to build more
complex neural networks such as convolution neural networks
and Word2Vec natural language models in TensorFlow. You also
might want to check out a higher level deep learning library that
sits on top of TensorFlow called Keras see my Keras tutorial. Ill
also be writting a new article on recurrent neural networks and
LSTMs soon.So stay tuned.

Have fun!

Recommended online course: If youd like to dive a little deeper

Id recommend the following inexpensive Udemy video course:
Data Science: Practical Deep Learning in Theano + TensorFlow

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 14/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

PREVIOUS NEXT
Stochastic Gradient Convolutional
Descent Mini- Neural Networks
batch and more Tutorial in
TensorFlow

12 COMMENTS

tomas
APRIL 14, 2017 AT 8:28 AM

hi, Iike the idea of explaining using the simple equation, great idea.
I didnt get the tensor/array output could you past all the code. Also
the code for the tensorboard visualization would be nice (I know
you are planning to go into that in more detail in another tutorial,
but would be great to take a look at now.

REPLY

Andy
APRIL 15, 2017 AT 5:51 AM

Hi Tomas no problems, you can nd the code here :

https://github.com/adventuresinML/adventures-in-ml-code.
Ive put another link to this repository in the article to make it
clearer. Thanks for the feedback

REPLY

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 15/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

Bablo l
APRIL 19, 2017 AT 3:19 AM

Thanks, great article.

REPLY

Lwebzem
MAY 5, 2017 AT 1:16 AM

I used the code from this post and it worked instantly. This is a
great article and great code so I added the link to the collection of
neural networks with python.

REPLY

dtdzung
JULY 17, 2017 AT 1:02 PM

great article. Thank you

REPLY

xxx
JULY 21, 2017 AT 10:21 AM

Asking uetions are really fastdious thing if you are not

understandng anything completely, but this piece of riting
presents nice understanding et.

REPLY

Lucian
JULY 28, 2017 AT 11:10 AM

Hi

Great tutorial, one of the (few..) best explained on the web.

I have a question: it is possible to give an image path to the model

so it can recognize the content of the image (a number in this case)
and print accuracy ?
http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 16/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

I alredy have a Tensor ow model which predict given numbers

(based on MNIST) but it fails a bit. I would like to print the accuracy
or, better, use a model like this with TF deeply integrated to predict
these numbers.

Thank you

REPLY

Andy
JULY 28, 2017 AT 7:44 PM

Hi Lucian, thanks for the comment. Im sorry, Im not quite sure

what you mean by image path? The code given here does
predict the MNIST numbers and prints the accuracy. Are you
asking whether there is a more accurate deep learning model
to predict numbers and other image content? If so, there is a
convolutional neural network. Check out this post to learn how
to implement in TensorFlow: Convolutional Neural Networks
Tutorial in TensorFlow

I hope this helps

REPLY

John McDonald
AUGUST 10, 2017 AT 10:38 PM

Shouldnt
a=d*e in the 1st paragraph breakdown? Not a=d*c

REPLY

Andy
AUGUST 11, 2017 AT 7:22 PM

Hi John, yes it should thanks for picking this up. Ive xed it

REPLY

John McDonald
AUGUST 12, 2017 AT 12:58 PM

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 17/18
9/28/2017 Python TensorFlow Tutorial - Build a Neural Network - Adventures in Machine Learning

No problem I initially thought I might have missed a new

way to break down functions!!

REPLY

Pasindu Tennage
AUGUST 17, 2017 AT 5:17 PM

Thank you very much for posting this. Very informative. Keep up
the good work

REPLY

Leave a Reply
Your email address will not be published.

Comment

Name*

Email*

Website

POST COMMENT

Note: some posts

contain Udemy a liate
links

Copyright 2017 | WordPress Theme by MH Themes

http://adventuresinmachinelearning.com/python-tensorflow-tutorial/ 18/18