mhjensen
343 lines
14 KiB
HTML
343 lines
14 KiB
HTML
<!--
|
||
Automatically generated HTML file from DocOnce source
|
||
(https://github.com/hplgit/doconce/)
|
||
-->
|
||
<html>
|
||
<head>
|
||
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
||
<meta name="generator" content="DocOnce: https://github.com/hplgit/doconce/" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||
<meta name="description" content="Convolutional Neural Networks">
|
||
|
||
<title>Convolutional Neural Networks</title>
|
||
|
||
<!-- Bootstrap style: bootstrap -->
|
||
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
|
||
<!-- not necessary
|
||
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
|
||
-->
|
||
|
||
<style type="text/css">
|
||
|
||
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
|
||
.dropdown-menu {
|
||
height: auto;
|
||
max-height: 400px;
|
||
overflow-x: hidden;
|
||
}
|
||
|
||
/* Adds an invisible element before each target to offset for the navigation
|
||
bar */
|
||
.anchor::before {
|
||
content:"";
|
||
display:block;
|
||
height:50px; /* fixed header height for style bootstrap */
|
||
margin:-50px 0 0; /* negative fixed header height */
|
||
}
|
||
</style>
|
||
|
||
|
||
</head>
|
||
|
||
<!-- tocinfo
|
||
{'highest level': 2,
|
||
'sections': [('Convolutional Neural Networks (recognizing images)',
|
||
2,
|
||
None,
|
||
'___sec0'),
|
||
('Regular NNs don’t scale well to full images',
|
||
2,
|
||
None,
|
||
'___sec1'),
|
||
('3D volumes of neurons', 2, None, '___sec2'),
|
||
('Layers used to build CNNs', 2, None, '___sec3'),
|
||
('Transforming images', 2, None, '___sec4'),
|
||
('CNNs in brief', 2, None, '___sec5'),
|
||
('CNNs in more detail, building convolutional neural networks in '
|
||
'Tensorflow and Keras',
|
||
2,
|
||
None,
|
||
'___sec6'),
|
||
('Setting it up', 2, None, '___sec7'),
|
||
('The MNIST dataset again', 2, None, '___sec8'),
|
||
('Strong correlations', 2, None, '___sec9'),
|
||
('Layers of a CNN', 2, None, '___sec10'),
|
||
('Systematic reduction', 2, None, '___sec11'),
|
||
('Prerequisites: Collect and pre-process data',
|
||
2,
|
||
None,
|
||
'___sec12'),
|
||
('Importing Keras and Tensorflow', 2, None, '___sec13'),
|
||
('Using TensorFlow backend', 2, None, '___sec14'),
|
||
('Train the model', 2, None, '___sec15'),
|
||
('Visualizing the results', 2, None, '___sec16'),
|
||
('Running with Keras', 2, None, '___sec17'),
|
||
('Final part', 2, None, '___sec18'),
|
||
('Final visualization', 2, None, '___sec19'),
|
||
('Fun links', 2, None, '___sec20')]}
|
||
end of tocinfo -->
|
||
|
||
<body>
|
||
|
||
|
||
|
||
<script type="text/x-mathjax-config">
|
||
MathJax.Hub.Config({
|
||
TeX: {
|
||
equationNumbers: { autoNumber: "none" },
|
||
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
|
||
}
|
||
});
|
||
</script>
|
||
<script type="text/javascript" async
|
||
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
|
||
</script>
|
||
|
||
|
||
|
||
|
||
<!-- Bootstrap navigation bar -->
|
||
<div class="navbar navbar-default navbar-fixed-top">
|
||
<div class="navbar-header">
|
||
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
|
||
<span class="icon-bar"></span>
|
||
<span class="icon-bar"></span>
|
||
<span class="icon-bar"></span>
|
||
</button>
|
||
<a class="navbar-brand" href="cnn-bs.html">Convolutional Neural Networks</a>
|
||
</div>
|
||
|
||
<div class="navbar-collapse collapse navbar-responsive-collapse">
|
||
<ul class="nav navbar-nav navbar-right">
|
||
<li class="dropdown">
|
||
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
|
||
<ul class="dropdown-menu">
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs001.html#___sec0" style="font-size: 80%;">Convolutional Neural Networks (recognizing images)</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs002.html#___sec1" style="font-size: 80%;">Regular NNs don’t scale well to full images</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs003.html#___sec2" style="font-size: 80%;">3D volumes of neurons</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs004.html#___sec3" style="font-size: 80%;">Layers used to build CNNs</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs005.html#___sec4" style="font-size: 80%;">Transforming images</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs006.html#___sec5" style="font-size: 80%;">CNNs in brief</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs007.html#___sec6" style="font-size: 80%;">CNNs in more detail, building convolutional neural networks in Tensorflow and Keras</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs008.html#___sec7" style="font-size: 80%;">Setting it up</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs009.html#___sec8" style="font-size: 80%;">The MNIST dataset again</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs010.html#___sec9" style="font-size: 80%;">Strong correlations</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs011.html#___sec10" style="font-size: 80%;">Layers of a CNN</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs012.html#___sec11" style="font-size: 80%;">Systematic reduction</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs013.html#___sec12" style="font-size: 80%;">Prerequisites: Collect and pre-process data</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs014.html#___sec13" style="font-size: 80%;">Importing Keras and Tensorflow</a></li>
|
||
<!-- navigation toc: --> <li><a href="#___sec14" style="font-size: 80%;">Using TensorFlow backend</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs016.html#___sec15" style="font-size: 80%;">Train the model</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs017.html#___sec16" style="font-size: 80%;">Visualizing the results</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs018.html#___sec17" style="font-size: 80%;">Running with Keras</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs019.html#___sec18" style="font-size: 80%;">Final part</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs020.html#___sec19" style="font-size: 80%;">Final visualization</a></li>
|
||
<!-- navigation toc: --> <li><a href="._cnn-bs021.html#___sec20" style="font-size: 80%;">Fun links</a></li>
|
||
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</div>
|
||
</div>
|
||
</div> <!-- end of navigation bar -->
|
||
|
||
<div class="container">
|
||
|
||
<p> </p><p> </p><p> </p> <!-- add vertical space -->
|
||
|
||
<a name="part0015"></a>
|
||
<!-- !split -->
|
||
|
||
<h2 id="___sec14" class="anchor">Using TensorFlow backend </h2>
|
||
|
||
<p>
|
||
We need to define model and architecture and choose cost function and optmizer.
|
||
<p>
|
||
|
||
<!-- code=text (!bc pycid) typeset with pygments style "default" -->
|
||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span>import tensorflow as tf
|
||
|
||
class ConvolutionalNeuralNetworkTensorflow:
|
||
def __init__(
|
||
self,
|
||
X_train,
|
||
Y_train,
|
||
X_test,
|
||
Y_test,
|
||
n_filters=10,
|
||
n_neurons_connected=50,
|
||
n_categories=10,
|
||
receptive_field=3,
|
||
stride=1,
|
||
padding=1,
|
||
epochs=10,
|
||
batch_size=100,
|
||
eta=0.1,
|
||
lmbd=0.0):
|
||
|
||
self.global_step = tf.Variable(0, dtype=tf.int32, trainable=False, name='global_step')
|
||
|
||
self.X_train = X_train
|
||
self.Y_train = Y_train
|
||
self.X_test = X_test
|
||
self.Y_test = Y_test
|
||
|
||
self.n_inputs, self.input_width, self.input_height, self.depth = X_train.shape
|
||
|
||
self.n_filters = n_filters
|
||
self.n_downsampled = int(self.input_width*self.input_height*n_filters / 4)
|
||
self.n_neurons_connected = n_neurons_connected
|
||
self.n_categories = n_categories
|
||
|
||
self.receptive_field = receptive_field
|
||
self.stride = stride
|
||
self.strides = [stride, stride, stride, stride]
|
||
self.padding = padding
|
||
|
||
self.epochs = epochs
|
||
self.batch_size = batch_size
|
||
self.iterations = self.n_inputs // self.batch_size
|
||
self.eta = eta
|
||
self.lmbd = lmbd
|
||
|
||
self.create_placeholders()
|
||
self.create_CNN()
|
||
self.create_loss()
|
||
self.create_optimiser()
|
||
self.create_accuracy()
|
||
|
||
def create_placeholders(self):
|
||
with tf.name_scope('data'):
|
||
self.X = tf.placeholder(tf.float32, shape=(None, self.input_width, self.input_height, self.depth), name='X_data')
|
||
self.Y = tf.placeholder(tf.float32, shape=(None, self.n_categories), name='Y_data')
|
||
|
||
def create_CNN(self):
|
||
with tf.name_scope('CNN'):
|
||
|
||
# Convolutional layer
|
||
self.W_conv = self.weight_variable([self.receptive_field, self.receptive_field, self.depth, self.n_filters], name='conv', dtype=tf.float32)
|
||
b_conv = self.weight_variable([self.n_filters], name='conv', dtype=tf.float32)
|
||
z_conv = tf.nn.conv2d(self.X, self.W_conv, self.strides, padding='SAME', name='conv') + b_conv
|
||
a_conv = tf.nn.relu(z_conv)
|
||
|
||
# 2x2 max pooling
|
||
a_pool = tf.nn.max_pool(a_conv, [1, 2, 2, 1], [1, 2, 2, 1], padding='SAME', name='pool')
|
||
|
||
# Fully connected layer
|
||
a_pool_flat = tf.reshape(a_pool, [-1, self.n_downsampled])
|
||
self.W_fc = self.weight_variable([self.n_downsampled, self.n_neurons_connected], name='fc', dtype=tf.float32)
|
||
b_fc = self.bias_variable([self.n_neurons_connected], name='fc', dtype=tf.float32)
|
||
a_fc = tf.nn.relu(tf.matmul(a_pool_flat, self.W_fc) + b_fc)
|
||
|
||
# Output layer
|
||
self.W_out = self.weight_variable([self.n_neurons_connected, self.n_categories], name='out', dtype=tf.float32)
|
||
b_out = self.bias_variable([self.n_categories], name='out', dtype=tf.float32)
|
||
self.z_out = tf.matmul(a_fc, self.W_out) + b_out
|
||
|
||
def create_loss(self):
|
||
with tf.name_scope('loss'):
|
||
softmax_loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=self.Y, logits=self.z_out))
|
||
|
||
regularizer_loss_conv = tf.nn.l2_loss(self.W_conv)
|
||
regularizer_loss_fc = tf.nn.l2_loss(self.W_fc)
|
||
regularizer_loss_out = tf.nn.l2_loss(self.W_out)
|
||
regularizer_loss = self.lmbd*(regularizer_loss_conv + regularizer_loss_fc + regularizer_loss_out)
|
||
|
||
self.loss = softmax_loss + regularizer_loss
|
||
|
||
def create_accuracy(self):
|
||
with tf.name_scope('accuracy'):
|
||
probabilities = tf.nn.softmax(self.z_out)
|
||
predictions = tf.argmax(probabilities, 1)
|
||
labels = tf.argmax(self.Y, 1)
|
||
|
||
correct_predictions = tf.equal(predictions, labels)
|
||
correct_predictions = tf.cast(correct_predictions, tf.float32)
|
||
self.accuracy = tf.reduce_mean(correct_predictions)
|
||
|
||
def create_optimiser(self):
|
||
with tf.name_scope('optimizer'):
|
||
self.optimizer = tf.train.GradientDescentOptimizer(learning_rate=self.eta).minimize(self.loss, global_step=self.global_step)
|
||
|
||
def weight_variable(self, shape, name='', dtype=tf.float32):
|
||
initial = tf.truncated_normal(shape, stddev=0.1)
|
||
return tf.Variable(initial, name=name, dtype=dtype)
|
||
|
||
def bias_variable(self, shape, name='', dtype=tf.float32):
|
||
initial = tf.constant(0.1, shape=shape)
|
||
return tf.Variable(initial, name=name, dtype=dtype)
|
||
|
||
def fit(self):
|
||
data_indices = np.arange(self.n_inputs)
|
||
|
||
with tf.Session() as sess:
|
||
sess.run(tf.global_variables_initializer())
|
||
for i in range(self.epochs):
|
||
for j in range(self.iterations):
|
||
chosen_datapoints = np.random.choice(data_indices, size=self.batch_size, replace=False)
|
||
batch_X, batch_Y = self.X_train[chosen_datapoints], self.Y_train[chosen_datapoints]
|
||
|
||
sess.run([CNN.loss, CNN.optimizer],
|
||
feed_dict={CNN.X: batch_X,
|
||
CNN.Y: batch_Y})
|
||
accuracy = sess.run(CNN.accuracy,
|
||
feed_dict={CNN.X: batch_X,
|
||
CNN.Y: batch_Y})
|
||
step = sess.run(CNN.global_step)
|
||
|
||
self.train_loss, self.train_accuracy = sess.run([CNN.loss, CNN.accuracy],
|
||
feed_dict={CNN.X: self.X_train,
|
||
CNN.Y: self.Y_train})
|
||
|
||
self.test_loss, self.test_accuracy = sess.run([CNN.loss, CNN.accuracy],
|
||
feed_dict={CNN.X: self.X_test,
|
||
CNN.Y: self.Y_test})
|
||
</pre></div>
|
||
<p>
|
||
<p>
|
||
<!-- navigation buttons at the bottom of the page -->
|
||
<ul class="pagination">
|
||
<li><a href="._cnn-bs014.html">«</a></li>
|
||
<li><a href="._cnn-bs000.html">1</a></li>
|
||
<li><a href="">...</a></li>
|
||
<li><a href="._cnn-bs007.html">8</a></li>
|
||
<li><a href="._cnn-bs008.html">9</a></li>
|
||
<li><a href="._cnn-bs009.html">10</a></li>
|
||
<li><a href="._cnn-bs010.html">11</a></li>
|
||
<li><a href="._cnn-bs011.html">12</a></li>
|
||
<li><a href="._cnn-bs012.html">13</a></li>
|
||
<li><a href="._cnn-bs013.html">14</a></li>
|
||
<li><a href="._cnn-bs014.html">15</a></li>
|
||
<li class="active"><a href="._cnn-bs015.html">16</a></li>
|
||
<li><a href="._cnn-bs016.html">17</a></li>
|
||
<li><a href="._cnn-bs017.html">18</a></li>
|
||
<li><a href="._cnn-bs018.html">19</a></li>
|
||
<li><a href="._cnn-bs019.html">20</a></li>
|
||
<li><a href="._cnn-bs020.html">21</a></li>
|
||
<li><a href="._cnn-bs021.html">22</a></li>
|
||
<li><a href="._cnn-bs016.html">»</a></li>
|
||
</ul>
|
||
<!-- ------------------- end of main content --------------- -->
|
||
|
||
</div> <!-- end container -->
|
||
<!-- include javascript, jQuery *first* -->
|
||
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
|
||
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
|
||
|
||
<!-- Bootstrap footer
|
||
<footer>
|
||
<a href="http://..."><img width="250" align=right src="http://..."></a>
|
||
</footer>
|
||
-->
|
||
|
||
|
||
<center style="font-size:80%">
|
||
<!-- copyright only on the titlepage -->
|
||
</center>
|
||
|
||
|
||
</body>
|
||
</html>
|
||
|
||
|