small update on neural networks
This commit is contained in:
mhjensen
@@ -92,54 +92,55 @@ Automatically generated HTML file from DocOnce source
|
||||
'___sec30'),
|
||||
('Defining the cost function', 2, None, '___sec31'),
|
||||
('Example: binary classification problem', 2, None, '___sec32'),
|
||||
('The Softmax function', 2, None, '___sec33'),
|
||||
('Developing a code for doing neural networks with back '
|
||||
'propagation',
|
||||
2,
|
||||
None,
|
||||
'___sec33'),
|
||||
('Collect and pre-process data', 2, None, '___sec34'),
|
||||
('Train and test datasets', 2, None, '___sec35'),
|
||||
('Define model and architecture', 2, None, '___sec36'),
|
||||
('Layers', 2, None, '___sec37'),
|
||||
('Weights and biases', 2, None, '___sec38'),
|
||||
('Feed-forward pass', 2, None, '___sec39'),
|
||||
('Matrix multiplications', 2, None, '___sec40'),
|
||||
('Choose cost function and optimizer', 2, None, '___sec41'),
|
||||
('Optimizing the cost function', 2, None, '___sec42'),
|
||||
('Regularization', 2, None, '___sec43'),
|
||||
('Matrix multiplication', 2, None, '___sec44'),
|
||||
('Improving performance', 2, None, '___sec45'),
|
||||
('Full object-oriented implementation', 2, None, '___sec46'),
|
||||
('Evaluate model performance on test data', 2, None, '___sec47'),
|
||||
('Adjust hyperparameters', 2, None, '___sec48'),
|
||||
('Visualization', 2, None, '___sec49'),
|
||||
('scikit-learn implementation', 2, None, '___sec50'),
|
||||
('Visualization', 2, None, '___sec51'),
|
||||
'___sec34'),
|
||||
('Collect and pre-process data', 2, None, '___sec35'),
|
||||
('Train and test datasets', 2, None, '___sec36'),
|
||||
('Define model and architecture', 2, None, '___sec37'),
|
||||
('Layers', 2, None, '___sec38'),
|
||||
('Weights and biases', 2, None, '___sec39'),
|
||||
('Feed-forward pass', 2, None, '___sec40'),
|
||||
('Matrix multiplications', 2, None, '___sec41'),
|
||||
('Choose cost function and optimizer', 2, None, '___sec42'),
|
||||
('Optimizing the cost function', 2, None, '___sec43'),
|
||||
('Regularization', 2, None, '___sec44'),
|
||||
('Matrix multiplication', 2, None, '___sec45'),
|
||||
('Improving performance', 2, None, '___sec46'),
|
||||
('Full object-oriented implementation', 2, None, '___sec47'),
|
||||
('Evaluate model performance on test data', 2, None, '___sec48'),
|
||||
('Adjust hyperparameters', 2, None, '___sec49'),
|
||||
('Visualization', 2, None, '___sec50'),
|
||||
('scikit-learn implementation', 2, None, '___sec51'),
|
||||
('Visualization', 2, None, '___sec52'),
|
||||
('Building neural networks in Tensorflow and Keras',
|
||||
2,
|
||||
None,
|
||||
'___sec52'),
|
||||
('Tensorflow', 2, None, '___sec53'),
|
||||
('Collect and pre-process data', 2, None, '___sec54'),
|
||||
('Using TensorFlow backend', 2, None, '___sec55'),
|
||||
('Optimizing and using gradient descent', 2, None, '___sec56'),
|
||||
('Using Keras', 2, None, '___sec57'),
|
||||
('Which activation function should I use?', 2, None, '___sec58'),
|
||||
'___sec53'),
|
||||
('Tensorflow', 2, None, '___sec54'),
|
||||
('Collect and pre-process data', 2, None, '___sec55'),
|
||||
('Using TensorFlow backend', 2, None, '___sec56'),
|
||||
('Optimizing and using gradient descent', 2, None, '___sec57'),
|
||||
('Using Keras', 2, None, '___sec58'),
|
||||
('Which activation function should I use?', 2, None, '___sec59'),
|
||||
('Is the Logistic activation function (Sigmoid) our choice?',
|
||||
2,
|
||||
None,
|
||||
'___sec59'),
|
||||
('The derivative of the Logistic funtion', 2, None, '___sec60'),
|
||||
('The RELU function family', 2, None, '___sec61'),
|
||||
('Which activation function should we use?', 2, None, '___sec62'),
|
||||
'___sec60'),
|
||||
('The derivative of the Logistic funtion', 2, None, '___sec61'),
|
||||
('The RELU function family', 2, None, '___sec62'),
|
||||
('Which activation function should we use?', 2, None, '___sec63'),
|
||||
('A top-down perspective on Neural networks',
|
||||
2,
|
||||
None,
|
||||
'___sec63'),
|
||||
'___sec64'),
|
||||
('Limitations of supervised learning with deep networks',
|
||||
2,
|
||||
None,
|
||||
'___sec64')]}
|
||||
'___sec65')]}
|
||||
end of tocinfo -->
|
||||
|
||||
<body>
|
||||
@@ -210,38 +211,39 @@ MathJax.Hub.Config({
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs031.html#___sec30" style="font-size: 80%;"><b>Setting up a Multi-layer perceptron model for classification</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs032.html#___sec31" style="font-size: 80%;"><b>Defining the cost function</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs033.html#___sec32" style="font-size: 80%;"><b>Example: binary classification problem</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs034.html#___sec33" style="font-size: 80%;"><b>Developing a code for doing neural networks with back propagation</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs035.html#___sec34" style="font-size: 80%;"><b>Collect and pre-process data</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs036.html#___sec35" style="font-size: 80%;"><b>Train and test datasets</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs037.html#___sec36" style="font-size: 80%;"><b>Define model and architecture</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs038.html#___sec37" style="font-size: 80%;"><b>Layers</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs039.html#___sec38" style="font-size: 80%;"><b>Weights and biases</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs040.html#___sec39" style="font-size: 80%;"><b>Feed-forward pass</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs041.html#___sec40" style="font-size: 80%;"><b>Matrix multiplications</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs042.html#___sec41" style="font-size: 80%;"><b>Choose cost function and optimizer</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs043.html#___sec42" style="font-size: 80%;"><b>Optimizing the cost function</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs044.html#___sec43" style="font-size: 80%;"><b>Regularization</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs045.html#___sec44" style="font-size: 80%;"><b>Matrix multiplication</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs046.html#___sec45" style="font-size: 80%;"><b>Improving performance</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs047.html#___sec46" style="font-size: 80%;"><b>Full object-oriented implementation</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs048.html#___sec47" style="font-size: 80%;"><b>Evaluate model performance on test data</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs049.html#___sec48" style="font-size: 80%;"><b>Adjust hyperparameters</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs050.html#___sec49" style="font-size: 80%;"><b>Visualization</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs051.html#___sec50" style="font-size: 80%;"><b>scikit-learn implementation</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs052.html#___sec51" style="font-size: 80%;"><b>Visualization</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs053.html#___sec52" style="font-size: 80%;"><b>Building neural networks in Tensorflow and Keras</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs054.html#___sec53" style="font-size: 80%;"><b>Tensorflow</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs055.html#___sec54" style="font-size: 80%;"><b>Collect and pre-process data</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs056.html#___sec55" style="font-size: 80%;"><b>Using TensorFlow backend</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec56" style="font-size: 80%;"><b>Optimizing and using gradient descent</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs058.html#___sec57" style="font-size: 80%;"><b>Using Keras</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs059.html#___sec58" style="font-size: 80%;"><b>Which activation function should I use?</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs060.html#___sec59" style="font-size: 80%;"><b>Is the Logistic activation function (Sigmoid) our choice?</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs061.html#___sec60" style="font-size: 80%;"><b>The derivative of the Logistic funtion</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs062.html#___sec61" style="font-size: 80%;"><b>The RELU function family</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs063.html#___sec62" style="font-size: 80%;"><b>Which activation function should we use?</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs064.html#___sec63" style="font-size: 80%;"><b>A top-down perspective on Neural networks</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs065.html#___sec64" style="font-size: 80%;"><b>Limitations of supervised learning with deep networks</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs034.html#___sec33" style="font-size: 80%;"><b>The Softmax function</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs035.html#___sec34" style="font-size: 80%;"><b>Developing a code for doing neural networks with back propagation</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs036.html#___sec35" style="font-size: 80%;"><b>Collect and pre-process data</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs037.html#___sec36" style="font-size: 80%;"><b>Train and test datasets</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs038.html#___sec37" style="font-size: 80%;"><b>Define model and architecture</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs039.html#___sec38" style="font-size: 80%;"><b>Layers</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs040.html#___sec39" style="font-size: 80%;"><b>Weights and biases</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs041.html#___sec40" style="font-size: 80%;"><b>Feed-forward pass</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs042.html#___sec41" style="font-size: 80%;"><b>Matrix multiplications</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs043.html#___sec42" style="font-size: 80%;"><b>Choose cost function and optimizer</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs044.html#___sec43" style="font-size: 80%;"><b>Optimizing the cost function</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs045.html#___sec44" style="font-size: 80%;"><b>Regularization</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs046.html#___sec45" style="font-size: 80%;"><b>Matrix multiplication</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs047.html#___sec46" style="font-size: 80%;"><b>Improving performance</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs048.html#___sec47" style="font-size: 80%;"><b>Full object-oriented implementation</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs049.html#___sec48" style="font-size: 80%;"><b>Evaluate model performance on test data</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs050.html#___sec49" style="font-size: 80%;"><b>Adjust hyperparameters</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs051.html#___sec50" style="font-size: 80%;"><b>Visualization</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs052.html#___sec51" style="font-size: 80%;"><b>scikit-learn implementation</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs053.html#___sec52" style="font-size: 80%;"><b>Visualization</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs054.html#___sec53" style="font-size: 80%;"><b>Building neural networks in Tensorflow and Keras</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs055.html#___sec54" style="font-size: 80%;"><b>Tensorflow</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs056.html#___sec55" style="font-size: 80%;"><b>Collect and pre-process data</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="#___sec56" style="font-size: 80%;"><b>Using TensorFlow backend</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs058.html#___sec57" style="font-size: 80%;"><b>Optimizing and using gradient descent</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs059.html#___sec58" style="font-size: 80%;"><b>Using Keras</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs060.html#___sec59" style="font-size: 80%;"><b>Which activation function should I use?</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs061.html#___sec60" style="font-size: 80%;"><b>Is the Logistic activation function (Sigmoid) our choice?</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs062.html#___sec61" style="font-size: 80%;"><b>The derivative of the Logistic funtion</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs063.html#___sec62" style="font-size: 80%;"><b>The RELU function family</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs064.html#___sec63" style="font-size: 80%;"><b>Which activation function should we use?</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs065.html#___sec64" style="font-size: 80%;"><b>A top-down perspective on Neural networks</b></a></li>
|
||||
<!-- navigation toc: --> <li><a href="._NeuralNet-bs066.html#___sec65" style="font-size: 80%;"><b>Limitations of supervised learning with deep networks</b></a></li>
|
||||
|
||||
</ul>
|
||||
</li>
|
||||
@@ -257,80 +259,147 @@ MathJax.Hub.Config({
|
||||
<a name="part0057"></a>
|
||||
<!-- !split -->
|
||||
|
||||
<h2 id="___sec56" class="anchor">Optimizing and using gradient descent </h2>
|
||||
<h2 id="___sec56" class="anchor">Using TensorFlow backend </h2>
|
||||
|
||||
<ol>
|
||||
<li> Define model and architecture</li>
|
||||
<li> Choose cost function and optimizer</li>
|
||||
</ol>
|
||||
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span>epochs <span style="color: #666666">=</span> <span style="color: #666666">100</span>
|
||||
batch_size <span style="color: #666666">=</span> <span style="color: #666666">100</span>
|
||||
n_neurons_layer1 <span style="color: #666666">=</span> <span style="color: #666666">100</span>
|
||||
n_neurons_layer2 <span style="color: #666666">=</span> <span style="color: #666666">50</span>
|
||||
n_categories <span style="color: #666666">=</span> <span style="color: #666666">10</span>
|
||||
eta_vals <span style="color: #666666">=</span> np<span style="color: #666666">.</span>logspace(<span style="color: #666666">-5</span>, <span style="color: #666666">1</span>, <span style="color: #666666">7</span>)
|
||||
lmbd_vals <span style="color: #666666">=</span> np<span style="color: #666666">.</span>logspace(<span style="color: #666666">-5</span>, <span style="color: #666666">1</span>, <span style="color: #666666">7</span>)
|
||||
</pre></div>
|
||||
<p>
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">tensorflow</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">tf</span>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span>DNN_tf <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((<span style="color: #008000">len</span>(eta_vals), <span style="color: #008000">len</span>(lmbd_vals)), dtype<span style="color: #666666">=</span><span style="color: #008000">object</span>)
|
||||
<span style="color: #008000; font-weight: bold">class</span> <span style="color: #0000FF; font-weight: bold">NeuralNetworkTensorflow</span>:
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">__init__</span>(
|
||||
<span style="color: #008000">self</span>,
|
||||
X_train,
|
||||
Y_train,
|
||||
X_test,
|
||||
Y_test,
|
||||
n_neurons_layer1<span style="color: #666666">=100</span>,
|
||||
n_neurons_layer2<span style="color: #666666">=50</span>,
|
||||
n_categories<span style="color: #666666">=2</span>,
|
||||
epochs<span style="color: #666666">=10</span>,
|
||||
batch_size<span style="color: #666666">=100</span>,
|
||||
eta<span style="color: #666666">=0.1</span>,
|
||||
lmbd<span style="color: #666666">=0.0</span>,
|
||||
):
|
||||
|
||||
<span style="color: #008000; font-weight: bold">for</span> i, eta <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">enumerate</span>(eta_vals):
|
||||
<span style="color: #008000; font-weight: bold">for</span> j, lmbd <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">enumerate</span>(lmbd_vals):
|
||||
DNN <span style="color: #666666">=</span> NeuralNetworkTensorflow(X_train, Y_train, X_test, Y_test,
|
||||
n_neurons_layer1, n_neurons_layer2, n_categories,
|
||||
epochs<span style="color: #666666">=</span>epochs, batch_size<span style="color: #666666">=</span>batch_size, eta<span style="color: #666666">=</span>eta, lmbd<span style="color: #666666">=</span>lmbd)
|
||||
DNN<span style="color: #666666">.</span>fit()
|
||||
<span style="color: #408080; font-style: italic"># keep track of number of steps</span>
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>global_step <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>Variable(<span style="color: #666666">0</span>, dtype<span style="color: #666666">=</span>tf<span style="color: #666666">.</span>int32, trainable<span style="color: #666666">=</span><span style="color: #008000">False</span>, name<span style="color: #666666">=</span><span style="color: #BA2121">'global_step'</span>)
|
||||
|
||||
DNN_tf[i][j] <span style="color: #666666">=</span> DNN
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>X_train <span style="color: #666666">=</span> X_train
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>Y_train <span style="color: #666666">=</span> Y_train
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>X_test <span style="color: #666666">=</span> X_test
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>Y_test <span style="color: #666666">=</span> Y_test
|
||||
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Learning rate = "</span>, eta)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Lambda = "</span>, lmbd)
|
||||
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">"Test accuracy: </span><span style="color: #BB6688; font-weight: bold">%.3f</span><span style="color: #BA2121">"</span> <span style="color: #666666">%</span> DNN<span style="color: #666666">.</span>test_accuracy)
|
||||
<span style="color: #008000; font-weight: bold">print</span>()
|
||||
</pre></div>
|
||||
<p>
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># optional</span>
|
||||
<span style="color: #408080; font-style: italic"># visual representation of grid search</span>
|
||||
<span style="color: #408080; font-style: italic"># uses seaborn heatmap, could probably do this in matplotlib</span>
|
||||
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">seaborn</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">sns</span>
|
||||
|
||||
sns<span style="color: #666666">.</span>set()
|
||||
|
||||
train_accuracy <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((<span style="color: #008000">len</span>(eta_vals), <span style="color: #008000">len</span>(lmbd_vals)))
|
||||
test_accuracy <span style="color: #666666">=</span> np<span style="color: #666666">.</span>zeros((<span style="color: #008000">len</span>(eta_vals), <span style="color: #008000">len</span>(lmbd_vals)))
|
||||
|
||||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(<span style="color: #008000">len</span>(eta_vals)):
|
||||
<span style="color: #008000; font-weight: bold">for</span> j <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(<span style="color: #008000">len</span>(lmbd_vals)):
|
||||
DNN <span style="color: #666666">=</span> DNN_tf[i][j]
|
||||
|
||||
train_accuracy[i][j] <span style="color: #666666">=</span> DNN<span style="color: #666666">.</span>train_accuracy
|
||||
test_accuracy[i][j] <span style="color: #666666">=</span> DNN<span style="color: #666666">.</span>test_accuracy
|
||||
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>n_inputs <span style="color: #666666">=</span> X_train<span style="color: #666666">.</span>shape[<span style="color: #666666">0</span>]
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>n_features <span style="color: #666666">=</span> X_train<span style="color: #666666">.</span>shape[<span style="color: #666666">1</span>]
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>n_neurons_layer1 <span style="color: #666666">=</span> n_neurons_layer1
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>n_neurons_layer2 <span style="color: #666666">=</span> n_neurons_layer2
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>n_categories <span style="color: #666666">=</span> n_categories
|
||||
|
||||
fig, ax <span style="color: #666666">=</span> plt<span style="color: #666666">.</span>subplots(figsize <span style="color: #666666">=</span> (<span style="color: #666666">10</span>, <span style="color: #666666">10</span>))
|
||||
sns<span style="color: #666666">.</span>heatmap(train_accuracy, annot<span style="color: #666666">=</span><span style="color: #008000">True</span>, ax<span style="color: #666666">=</span>ax, cmap<span style="color: #666666">=</span><span style="color: #BA2121">"viridis"</span>)
|
||||
ax<span style="color: #666666">.</span>set_title(<span style="color: #BA2121">"Training Accuracy"</span>)
|
||||
ax<span style="color: #666666">.</span>set_ylabel(<span style="color: #BA2121">"$\eta$"</span>)
|
||||
ax<span style="color: #666666">.</span>set_xlabel(<span style="color: #BA2121">"$\lambda$"</span>)
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>epochs <span style="color: #666666">=</span> epochs
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>batch_size <span style="color: #666666">=</span> batch_size
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>iterations <span style="color: #666666">=</span> <span style="color: #008000">self</span><span style="color: #666666">.</span>n_inputs <span style="color: #666666">//</span> <span style="color: #008000">self</span><span style="color: #666666">.</span>batch_size
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>eta <span style="color: #666666">=</span> eta
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>lmbd <span style="color: #666666">=</span> lmbd
|
||||
|
||||
<span style="color: #408080; font-style: italic"># build network piece by piece</span>
|
||||
<span style="color: #408080; font-style: italic"># name scopes (with) are used to enforce creation of new variables</span>
|
||||
<span style="color: #408080; font-style: italic"># https://www.tensorflow.org/guide/variables</span>
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>create_placeholders()
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>create_DNN()
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>create_loss()
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>create_optimiser()
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>create_accuracy()
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">create_placeholders</span>(<span style="color: #008000">self</span>):
|
||||
<span style="color: #408080; font-style: italic"># placeholders are fine here, but "Datasets" are the preferred method</span>
|
||||
<span style="color: #408080; font-style: italic"># of streaming data into a model</span>
|
||||
<span style="color: #008000; font-weight: bold">with</span> tf<span style="color: #666666">.</span>name_scope(<span style="color: #BA2121">'data'</span>):
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>X <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>placeholder(tf<span style="color: #666666">.</span>float32, shape<span style="color: #666666">=</span>(<span style="color: #008000">None</span>, <span style="color: #008000">self</span><span style="color: #666666">.</span>n_features), name<span style="color: #666666">=</span><span style="color: #BA2121">'X_data'</span>)
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>Y <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>placeholder(tf<span style="color: #666666">.</span>float32, shape<span style="color: #666666">=</span>(<span style="color: #008000">None</span>, <span style="color: #008000">self</span><span style="color: #666666">.</span>n_categories), name<span style="color: #666666">=</span><span style="color: #BA2121">'Y_data'</span>)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">create_DNN</span>(<span style="color: #008000">self</span>):
|
||||
<span style="color: #008000; font-weight: bold">with</span> tf<span style="color: #666666">.</span>name_scope(<span style="color: #BA2121">'DNN'</span>):
|
||||
<span style="color: #408080; font-style: italic"># the weights are stored to calculate regularization loss later</span>
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Fully connected layer 1</span>
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>W_fc1 <span style="color: #666666">=</span> <span style="color: #008000">self</span><span style="color: #666666">.</span>weight_variable([<span style="color: #008000">self</span><span style="color: #666666">.</span>n_features, <span style="color: #008000">self</span><span style="color: #666666">.</span>n_neurons_layer1], name<span style="color: #666666">=</span><span style="color: #BA2121">'fc1'</span>, dtype<span style="color: #666666">=</span>tf<span style="color: #666666">.</span>float32)
|
||||
b_fc1 <span style="color: #666666">=</span> <span style="color: #008000">self</span><span style="color: #666666">.</span>bias_variable([<span style="color: #008000">self</span><span style="color: #666666">.</span>n_neurons_layer1], name<span style="color: #666666">=</span><span style="color: #BA2121">'fc1'</span>, dtype<span style="color: #666666">=</span>tf<span style="color: #666666">.</span>float32)
|
||||
a_fc1 <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>nn<span style="color: #666666">.</span>sigmoid(tf<span style="color: #666666">.</span>matmul(<span style="color: #008000">self</span><span style="color: #666666">.</span>X, <span style="color: #008000">self</span><span style="color: #666666">.</span>W_fc1) <span style="color: #666666">+</span> b_fc1)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Fully connected layer 2</span>
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>W_fc2 <span style="color: #666666">=</span> <span style="color: #008000">self</span><span style="color: #666666">.</span>weight_variable([<span style="color: #008000">self</span><span style="color: #666666">.</span>n_neurons_layer1, <span style="color: #008000">self</span><span style="color: #666666">.</span>n_neurons_layer2], name<span style="color: #666666">=</span><span style="color: #BA2121">'fc2'</span>, dtype<span style="color: #666666">=</span>tf<span style="color: #666666">.</span>float32)
|
||||
b_fc2 <span style="color: #666666">=</span> <span style="color: #008000">self</span><span style="color: #666666">.</span>bias_variable([<span style="color: #008000">self</span><span style="color: #666666">.</span>n_neurons_layer2], name<span style="color: #666666">=</span><span style="color: #BA2121">'fc2'</span>, dtype<span style="color: #666666">=</span>tf<span style="color: #666666">.</span>float32)
|
||||
a_fc2 <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>nn<span style="color: #666666">.</span>sigmoid(tf<span style="color: #666666">.</span>matmul(a_fc1, <span style="color: #008000">self</span><span style="color: #666666">.</span>W_fc2) <span style="color: #666666">+</span> b_fc2)
|
||||
|
||||
<span style="color: #408080; font-style: italic"># Output layer</span>
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>W_out <span style="color: #666666">=</span> <span style="color: #008000">self</span><span style="color: #666666">.</span>weight_variable([<span style="color: #008000">self</span><span style="color: #666666">.</span>n_neurons_layer2, <span style="color: #008000">self</span><span style="color: #666666">.</span>n_categories], name<span style="color: #666666">=</span><span style="color: #BA2121">'out'</span>, dtype<span style="color: #666666">=</span>tf<span style="color: #666666">.</span>float32)
|
||||
b_out <span style="color: #666666">=</span> <span style="color: #008000">self</span><span style="color: #666666">.</span>bias_variable([<span style="color: #008000">self</span><span style="color: #666666">.</span>n_categories], name<span style="color: #666666">=</span><span style="color: #BA2121">'out'</span>, dtype<span style="color: #666666">=</span>tf<span style="color: #666666">.</span>float32)
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>z_out <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>matmul(a_fc2, <span style="color: #008000">self</span><span style="color: #666666">.</span>W_out) <span style="color: #666666">+</span> b_out
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">create_loss</span>(<span style="color: #008000">self</span>):
|
||||
<span style="color: #008000; font-weight: bold">with</span> tf<span style="color: #666666">.</span>name_scope(<span style="color: #BA2121">'loss'</span>):
|
||||
softmax_loss <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>reduce_mean(tf<span style="color: #666666">.</span>nn<span style="color: #666666">.</span>softmax_cross_entropy_with_logits_v2(labels<span style="color: #666666">=</span><span style="color: #008000">self</span><span style="color: #666666">.</span>Y, logits<span style="color: #666666">=</span><span style="color: #008000">self</span><span style="color: #666666">.</span>z_out))
|
||||
|
||||
regularizer_loss_fc1 <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>nn<span style="color: #666666">.</span>l2_loss(<span style="color: #008000">self</span><span style="color: #666666">.</span>W_fc1)
|
||||
regularizer_loss_fc2 <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>nn<span style="color: #666666">.</span>l2_loss(<span style="color: #008000">self</span><span style="color: #666666">.</span>W_fc2)
|
||||
regularizer_loss_out <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>nn<span style="color: #666666">.</span>l2_loss(<span style="color: #008000">self</span><span style="color: #666666">.</span>W_out)
|
||||
regularizer_loss <span style="color: #666666">=</span> <span style="color: #008000">self</span><span style="color: #666666">.</span>lmbd<span style="color: #666666">*</span>(regularizer_loss_fc1 <span style="color: #666666">+</span> regularizer_loss_fc2 <span style="color: #666666">+</span> regularizer_loss_out)
|
||||
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>loss <span style="color: #666666">=</span> softmax_loss <span style="color: #666666">+</span> regularizer_loss
|
||||
|
||||
fig, ax <span style="color: #666666">=</span> plt<span style="color: #666666">.</span>subplots(figsize <span style="color: #666666">=</span> (<span style="color: #666666">10</span>, <span style="color: #666666">10</span>))
|
||||
sns<span style="color: #666666">.</span>heatmap(test_accuracy, annot<span style="color: #666666">=</span><span style="color: #008000">True</span>, ax<span style="color: #666666">=</span>ax, cmap<span style="color: #666666">=</span><span style="color: #BA2121">"viridis"</span>)
|
||||
ax<span style="color: #666666">.</span>set_title(<span style="color: #BA2121">"Test Accuracy"</span>)
|
||||
ax<span style="color: #666666">.</span>set_ylabel(<span style="color: #BA2121">"$\eta$"</span>)
|
||||
ax<span style="color: #666666">.</span>set_xlabel(<span style="color: #BA2121">"$\lambda$"</span>)
|
||||
plt<span style="color: #666666">.</span>show()
|
||||
</pre></div>
|
||||
<p>
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">create_accuracy</span>(<span style="color: #008000">self</span>):
|
||||
<span style="color: #008000; font-weight: bold">with</span> tf<span style="color: #666666">.</span>name_scope(<span style="color: #BA2121">'accuracy'</span>):
|
||||
probabilities <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>nn<span style="color: #666666">.</span>softmax(<span style="color: #008000">self</span><span style="color: #666666">.</span>z_out)
|
||||
predictions <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>argmax(probabilities, axis<span style="color: #666666">=1</span>)
|
||||
labels <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>argmax(<span style="color: #008000">self</span><span style="color: #666666">.</span>Y, axis<span style="color: #666666">=1</span>)
|
||||
|
||||
correct_predictions <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>equal(predictions, labels)
|
||||
correct_predictions <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>cast(correct_predictions, tf<span style="color: #666666">.</span>float32)
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>accuracy <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>reduce_mean(correct_predictions)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">create_optimiser</span>(<span style="color: #008000">self</span>):
|
||||
<span style="color: #008000; font-weight: bold">with</span> tf<span style="color: #666666">.</span>name_scope(<span style="color: #BA2121">'optimizer'</span>):
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>optimizer <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>train<span style="color: #666666">.</span>GradientDescentOptimizer(learning_rate<span style="color: #666666">=</span><span style="color: #008000">self</span><span style="color: #666666">.</span>eta)<span style="color: #666666">.</span>minimize(<span style="color: #008000">self</span><span style="color: #666666">.</span>loss, global_step<span style="color: #666666">=</span><span style="color: #008000">self</span><span style="color: #666666">.</span>global_step)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">weight_variable</span>(<span style="color: #008000">self</span>, shape, name<span style="color: #666666">=</span><span style="color: #BA2121">''</span>, dtype<span style="color: #666666">=</span>tf<span style="color: #666666">.</span>float32):
|
||||
initial <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>truncated_normal(shape, stddev<span style="color: #666666">=0.1</span>)
|
||||
<span style="color: #008000; font-weight: bold">return</span> tf<span style="color: #666666">.</span>Variable(initial, name<span style="color: #666666">=</span>name, dtype<span style="color: #666666">=</span>dtype)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">bias_variable</span>(<span style="color: #008000">self</span>, shape, name<span style="color: #666666">=</span><span style="color: #BA2121">''</span>, dtype<span style="color: #666666">=</span>tf<span style="color: #666666">.</span>float32):
|
||||
initial <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>constant(<span style="color: #666666">0.1</span>, shape<span style="color: #666666">=</span>shape)
|
||||
<span style="color: #008000; font-weight: bold">return</span> tf<span style="color: #666666">.</span>Variable(initial, name<span style="color: #666666">=</span>name, dtype<span style="color: #666666">=</span>dtype)
|
||||
|
||||
<span style="color: #008000; font-weight: bold">def</span> <span style="color: #0000FF">fit</span>(<span style="color: #008000">self</span>):
|
||||
data_indices <span style="color: #666666">=</span> np<span style="color: #666666">.</span>arange(<span style="color: #008000">self</span><span style="color: #666666">.</span>n_inputs)
|
||||
|
||||
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
|
||||
<div class="highlight" style="background: #f8f8f8"><pre style="line-height: 125%"><span></span><span style="color: #408080; font-style: italic"># optional</span>
|
||||
<span style="color: #408080; font-style: italic"># we can use log files to visualize our graph in Tensorboard</span>
|
||||
writer <span style="color: #666666">=</span> tf<span style="color: #666666">.</span>summary<span style="color: #666666">.</span>FileWriter(<span style="color: #BA2121">'logs/'</span>)
|
||||
writer<span style="color: #666666">.</span>add_graph(tf<span style="color: #666666">.</span>get_default_graph())
|
||||
<span style="color: #008000; font-weight: bold">with</span> tf<span style="color: #666666">.</span>Session() <span style="color: #008000; font-weight: bold">as</span> sess:
|
||||
sess<span style="color: #666666">.</span>run(tf<span style="color: #666666">.</span>global_variables_initializer())
|
||||
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(<span style="color: #008000">self</span><span style="color: #666666">.</span>epochs):
|
||||
<span style="color: #008000; font-weight: bold">for</span> j <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(<span style="color: #008000">self</span><span style="color: #666666">.</span>iterations):
|
||||
chosen_datapoints <span style="color: #666666">=</span> np<span style="color: #666666">.</span>random<span style="color: #666666">.</span>choice(data_indices, size<span style="color: #666666">=</span><span style="color: #008000">self</span><span style="color: #666666">.</span>batch_size, replace<span style="color: #666666">=</span><span style="color: #008000">False</span>)
|
||||
batch_X, batch_Y <span style="color: #666666">=</span> <span style="color: #008000">self</span><span style="color: #666666">.</span>X_train[chosen_datapoints], <span style="color: #008000">self</span><span style="color: #666666">.</span>Y_train[chosen_datapoints]
|
||||
|
||||
sess<span style="color: #666666">.</span>run([DNN<span style="color: #666666">.</span>loss, DNN<span style="color: #666666">.</span>optimizer],
|
||||
feed_dict<span style="color: #666666">=</span>{DNN<span style="color: #666666">.</span>X: batch_X,
|
||||
DNN<span style="color: #666666">.</span>Y: batch_Y})
|
||||
accuracy <span style="color: #666666">=</span> sess<span style="color: #666666">.</span>run(DNN<span style="color: #666666">.</span>accuracy,
|
||||
feed_dict<span style="color: #666666">=</span>{DNN<span style="color: #666666">.</span>X: batch_X,
|
||||
DNN<span style="color: #666666">.</span>Y: batch_Y})
|
||||
step <span style="color: #666666">=</span> sess<span style="color: #666666">.</span>run(DNN<span style="color: #666666">.</span>global_step)
|
||||
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>train_loss, <span style="color: #008000">self</span><span style="color: #666666">.</span>train_accuracy <span style="color: #666666">=</span> sess<span style="color: #666666">.</span>run([DNN<span style="color: #666666">.</span>loss, DNN<span style="color: #666666">.</span>accuracy],
|
||||
feed_dict<span style="color: #666666">=</span>{DNN<span style="color: #666666">.</span>X: <span style="color: #008000">self</span><span style="color: #666666">.</span>X_train,
|
||||
DNN<span style="color: #666666">.</span>Y: <span style="color: #008000">self</span><span style="color: #666666">.</span>Y_train})
|
||||
|
||||
<span style="color: #008000">self</span><span style="color: #666666">.</span>test_loss, <span style="color: #008000">self</span><span style="color: #666666">.</span>test_accuracy <span style="color: #666666">=</span> sess<span style="color: #666666">.</span>run([DNN<span style="color: #666666">.</span>loss, DNN<span style="color: #666666">.</span>accuracy],
|
||||
feed_dict<span style="color: #666666">=</span>{DNN<span style="color: #666666">.</span>X: <span style="color: #008000">self</span><span style="color: #666666">.</span>X_test,
|
||||
DNN<span style="color: #666666">.</span>Y: <span style="color: #008000">self</span><span style="color: #666666">.</span>Y_test})
|
||||
</pre></div>
|
||||
<p>
|
||||
<p>
|
||||
@@ -356,6 +425,7 @@ writer<span style="color: #666666">.</span>add_graph(tf<span style="color: #6666
|
||||
<li><a href="._NeuralNet-bs063.html">64</a></li>
|
||||
<li><a href="._NeuralNet-bs064.html">65</a></li>
|
||||
<li><a href="._NeuralNet-bs065.html">66</a></li>
|
||||
<li><a href="._NeuralNet-bs066.html">67</a></li>
|
||||
<li><a href="._NeuralNet-bs058.html">»</a></li>
|
||||
</ul>
|
||||
<!-- ------------------- end of main content --------------- -->
|
||||
|
||||
Reference in New Issue
Block a user