mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-06 15:22:21 +08:00
781 lines
56 KiB
HTML
781 lines
56 KiB
HTML
<!DOCTYPE html>
|
|
<html>
|
|
<head>
|
|
<meta http-equiv="content-type" content="text/html;charset=utf-8"/>
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
|
|
<meta name="description" content="A PyTorch implementation/tutorial of HyperLSTM introduced in paper HyperNetworks."/>
|
|
|
|
<meta name="twitter:card" content="summary"/>
|
|
<meta name="twitter:image:src" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
|
<meta name="twitter:title" content="HyperNetworks - HyperLSTM"/>
|
|
<meta name="twitter:description" content="A PyTorch implementation/tutorial of HyperLSTM introduced in paper HyperNetworks."/>
|
|
<meta name="twitter:site" content="@labmlai"/>
|
|
<meta name="twitter:creator" content="@labmlai"/>
|
|
|
|
<meta property="og:url" content="https://nn.labml.ai/hypernetworks/hyper_lstm.html"/>
|
|
<meta property="og:title" content="HyperNetworks - HyperLSTM"/>
|
|
<meta property="og:image" content="https://avatars1.githubusercontent.com/u/64068543?s=400&v=4"/>
|
|
<meta property="og:site_name" content="LabML Neural Networks"/>
|
|
<meta property="og:type" content="object"/>
|
|
<meta property="og:title" content="HyperNetworks - HyperLSTM"/>
|
|
<meta property="og:description" content="A PyTorch implementation/tutorial of HyperLSTM introduced in paper HyperNetworks."/>
|
|
|
|
<title>HyperNetworks - HyperLSTM</title>
|
|
<link rel="shortcut icon" href="/icon.png"/>
|
|
<link rel="stylesheet" href="../pylit.css">
|
|
<link rel="canonical" href="https://nn.labml.ai/hypernetworks/hyper_lstm.html"/>
|
|
<!-- Global site tag (gtag.js) - Google Analytics -->
|
|
<script async src="https://www.googletagmanager.com/gtag/js?id=G-4V3HC8HBLH"></script>
|
|
<script>
|
|
window.dataLayer = window.dataLayer || [];
|
|
|
|
function gtag() {
|
|
dataLayer.push(arguments);
|
|
}
|
|
|
|
gtag('js', new Date());
|
|
|
|
gtag('config', 'G-4V3HC8HBLH');
|
|
</script>
|
|
</head>
|
|
<body>
|
|
<div id='container'>
|
|
<div id="background"></div>
|
|
<div class='section'>
|
|
<div class='docs'>
|
|
<p>
|
|
<a class="parent" href="/">home</a>
|
|
<a class="parent" href="index.html">hypernetworks</a>
|
|
</p>
|
|
<p>
|
|
|
|
<a href="https://github.com/lab-ml/labml_nn/tree/master/labml_nn/hypernetworks/hyper_lstm.py">
|
|
<img alt="Github"
|
|
src="https://img.shields.io/github/stars/lab-ml/nn?style=social"
|
|
style="max-width:100%;"/></a>
|
|
<a href="https://twitter.com/labmlai"
|
|
rel="nofollow">
|
|
<img alt="Twitter"
|
|
src="https://img.shields.io/twitter/follow/labmlai?style=social"
|
|
style="max-width:100%;"/></a>
|
|
</p>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-0'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-0'>#</a>
|
|
</div>
|
|
<h1>HyperNetworks - HyperLSTM</h1>
|
|
<p>We have implemented HyperLSTM introduced in paper
|
|
<a href="https://arxiv.org/abs/1609.09106">HyperNetworks</a>, with annotations
|
|
using <a href="https://pytorch.org">PyTorch</a>.
|
|
<a href="https://blog.otoro.net/2016/09/28/hyper-networks/">This blog post</a>
|
|
by David Ha gives a good explanation of HyperNetworks.</p>
|
|
<p>We have an experiment that trains a HyperLSTM to predict text on Shakespeare dataset.
|
|
Here’s the link to code: <a href="experiment.html"><code>experiment.py</code></a></p>
|
|
<p><a href="https://colab.research.google.com/github/lab-ml/nn/blob/master/labml_nn/hypernetworks/experiment.ipynb"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg" /></a>
|
|
<a href="https://app.labml.ai/run/9e7f39e047e811ebbaff2b26e3148b3d"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen" /></a></p>
|
|
<p>HyperNetworks use a smaller network to generate weights of a larger network.
|
|
There are two variants: static hyper-networks and dynamic hyper-networks.
|
|
Static HyperNetworks have smaller networks that generate weights (kernels)
|
|
of a convolutional network. Dynamic HyperNetworks generate parameters of a
|
|
recurrent neural network
|
|
for each step. This is an implementation of the latter.</p>
|
|
<h2>Dynamic HyperNetworks</h2>
|
|
<p>In a RNN the parameters stay constant for each step.
|
|
Dynamic HyperNetworks generate different parameters for each step.
|
|
HyperLSTM has the structure of a LSTM but the parameters of
|
|
each step are changed by a smaller LSTM network.</p>
|
|
<p>In the basic form, a Dynamic HyperNetwork has a smaller recurrent network that generates
|
|
a feature vector corresponding to each parameter tensor of the larger recurrent network.
|
|
Let’s say the larger network has some parameter $\color{cyan}{W_h}$ the smaller network generates a feature
|
|
vector $z_h$ and we dynamically compute $\color{cyan}{W_h}$ as a linear transformation of $z_h$.
|
|
For instance $\color{cyan}{W_h} = \langle W_{hz}, z_h \rangle$ where
|
|
$W_{hz}$ is a 3-d tensor parameter and $\langle . \rangle$ is a tensor-vector multiplication.
|
|
$z_h$ is usually a linear transformation of the output of the smaller recurrent network.</p>
|
|
<h3>Weight scaling instead of computing</h3>
|
|
<p>Large recurrent networks have large dynamically computed parameters.
|
|
These are calculated using linear transformation of feature vector $z$.
|
|
And this transformation requires an even larger weight tensor.
|
|
That is, when $\color{cyan}{W_h}$ has shape $N_h \times N_h$,
|
|
$W_{hz}$ will be $N_h \times N_h \times N_z$.</p>
|
|
<p>To overcome this, we compute the weight parameters of the recurrent network by
|
|
dynamically scaling each row of a matrix of same size.
|
|
<script type="math/tex; mode=display">\begin{align}
|
|
d(z) = W_{hz} z_h \\
|
|
\\
|
|
\color{cyan}{W_h} =
|
|
\begin{pmatrix}
|
|
d_0(z) W_{hd_0} \\
|
|
d_1(z) W_{hd_1} \\
|
|
... \\
|
|
d_{N_h}(z) W_{hd_{N_h}} \\
|
|
\end{pmatrix}
|
|
\end{align}</script>
|
|
where $W_{hd}$ is a $N_h \times N_h$ parameter matrix.</p>
|
|
<p>We can further optimize this when we compute $\color{cyan}{W_h} h$,
|
|
as
|
|
<script type="math/tex; mode=display">\color{lightgreen}{d(z) \odot (W_{hd} h)}</script>
|
|
where $\odot$ stands for element-wise multiplication.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">71</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Optional</span><span class="p">,</span> <span class="n">Tuple</span>
|
|
<span class="lineno">72</span>
|
|
<span class="lineno">73</span><span class="kn">import</span> <span class="nn">torch</span>
|
|
<span class="lineno">74</span><span class="kn">from</span> <span class="nn">torch</span> <span class="kn">import</span> <span class="n">nn</span>
|
|
<span class="lineno">75</span>
|
|
<span class="lineno">76</span><span class="kn">from</span> <span class="nn">labml_helpers.module</span> <span class="kn">import</span> <span class="n">Module</span>
|
|
<span class="lineno">77</span><span class="kn">from</span> <span class="nn">labml_nn.lstm</span> <span class="kn">import</span> <span class="n">LSTMCell</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-1'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-1'>#</a>
|
|
</div>
|
|
<h2>HyperLSTM Cell</h2>
|
|
<p>For HyperLSTM the smaller network and the larger network both have the LSTM structure.
|
|
This is defined in Appendix A.2.2 in the paper.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">80</span><span class="k">class</span> <span class="nc">HyperLSTMCell</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-2'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-2'>#</a>
|
|
</div>
|
|
<p><code>input_size</code> is the size of the input $x_t$,
|
|
<code>hidden_size</code> is the size of the LSTM, and
|
|
<code>hyper_size</code> is the size of the smaller LSTM that alters the weights of the larger outer LSTM.
|
|
<code>n_z</code> is the size of the feature vectors used to alter the LSTM weights.</p>
|
|
<p>We use the output of the smaller LSTM to compute $z_h^{i,f,g,o}$, $z_x^{i,f,g,o}$ and
|
|
$z_b^{i,f,g,o}$ using linear transformations.
|
|
We calculate $d_h^{i,f,g,o}(z_h^{i,f,g,o})$, $d_x^{i,f,g,o}(z_x^{i,f,g,o})$, and
|
|
$d_b^{i,f,g,o}(z_b^{i,f,g,o})$ from these, using linear transformations again.
|
|
These are then used to scale the rows of weight and bias tensors of the main LSTM.</p>
|
|
<p>📝 Since the computation of $z$ and $d$ are two sequential linear transformations
|
|
these can be combined into a single linear transformation.
|
|
However we’ve implemented this separately so that it matches with the description
|
|
in the paper.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">88</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">hyper_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_z</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-3'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-3'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">106</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-4'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-4'>#</a>
|
|
</div>
|
|
<p>The input to the hyperLSTM is
|
|
<script type="math/tex; mode=display">
|
|
\hat{x}_t = \begin{pmatrix}
|
|
h_{t-1} \\
|
|
x_t
|
|
\end{pmatrix}
|
|
</script>
|
|
where $x_t$ is the input and $h_{t-1}$ is the output of the outer LSTM at previous step.
|
|
So the input size is <code>hidden_size + input_size</code>.</p>
|
|
<p>The output of hyperLSTM is $\hat{h}_t$ and $\hat{c}_t$.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">119</span> <span class="bp">self</span><span class="o">.</span><span class="n">hyper</span> <span class="o">=</span> <span class="n">LSTMCell</span><span class="p">(</span><span class="n">hidden_size</span> <span class="o">+</span> <span class="n">input_size</span><span class="p">,</span> <span class="n">hyper_size</span><span class="p">,</span> <span class="n">layer_norm</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-5'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-5'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">z_h^{i,f,g,o} = lin_{h}^{i,f,g,o}(\hat{h}_t)</script>
|
|
🤔 In the paper it was specified as
|
|
<script type="math/tex; mode=display">z_h^{i,f,g,o} = lin_{h}^{i,f,g,o}(\hat{h}_{\color{red}{t-1}})</script>
|
|
I feel that it’s a typo.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">125</span> <span class="bp">self</span><span class="o">.</span><span class="n">z_h</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">hyper_size</span><span class="p">,</span> <span class="mi">4</span> <span class="o">*</span> <span class="n">n_z</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-6'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-6'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">z_x^{i,f,g,o} = lin_x^{i,f,g,o}(\hat{h}_t)</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">127</span> <span class="bp">self</span><span class="o">.</span><span class="n">z_x</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">hyper_size</span><span class="p">,</span> <span class="mi">4</span> <span class="o">*</span> <span class="n">n_z</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-7'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-7'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">z_b^{i,f,g,o} = lin_b^{i,f,g,o}(\hat{h}_t)</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">129</span> <span class="bp">self</span><span class="o">.</span><span class="n">z_b</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">hyper_size</span><span class="p">,</span> <span class="mi">4</span> <span class="o">*</span> <span class="n">n_z</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-8'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-8'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">d_h^{i,f,g,o}(z_h^{i,f,g,o}) = lin_{dh}^{i,f,g,o}(z_h^{i,f,g,o})</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">132</span> <span class="n">d_h</span> <span class="o">=</span> <span class="p">[</span><span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">n_z</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">4</span><span class="p">)]</span>
|
|
<span class="lineno">133</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_h</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">(</span><span class="n">d_h</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-9'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-9'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">d_x^{i,f,g,o}(z_x^{i,f,g,o}) = lin_{dx}^{i,f,g,o}(z_x^{i,f,g,o})</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">135</span> <span class="n">d_x</span> <span class="o">=</span> <span class="p">[</span><span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">n_z</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">,</span> <span class="n">bias</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">4</span><span class="p">)]</span>
|
|
<span class="lineno">136</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_x</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">(</span><span class="n">d_x</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-10'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-10'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">d_b^{i,f,g,o}(z_b^{i,f,g,o}) = lin_{db}^{i,f,g,o}(z_b^{i,f,g,o})</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">138</span> <span class="n">d_b</span> <span class="o">=</span> <span class="p">[</span><span class="n">nn</span><span class="o">.</span><span class="n">Linear</span><span class="p">(</span><span class="n">n_z</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">4</span><span class="p">)]</span>
|
|
<span class="lineno">139</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_b</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">(</span><span class="n">d_b</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-11'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-11'>#</a>
|
|
</div>
|
|
<p>The weight matrices $W_h^{i,f,g,o}$</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">142</span> <span class="bp">self</span><span class="o">.</span><span class="n">w_h</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ParameterList</span><span class="p">([</span><span class="n">nn</span><span class="o">.</span><span class="n">Parameter</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">))</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">4</span><span class="p">)])</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-12'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-12'>#</a>
|
|
</div>
|
|
<p>The weight matrices $W_x^{i,f,g,o}$</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">144</span> <span class="bp">self</span><span class="o">.</span><span class="n">w_x</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ParameterList</span><span class="p">([</span><span class="n">nn</span><span class="o">.</span><span class="n">Parameter</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">,</span> <span class="n">input_size</span><span class="p">))</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">4</span><span class="p">)])</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-13'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-13'>#</a>
|
|
</div>
|
|
<p>Layer normalization</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">147</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer_norm</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">([</span><span class="n">nn</span><span class="o">.</span><span class="n">LayerNorm</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">4</span><span class="p">)])</span>
|
|
<span class="lineno">148</span> <span class="bp">self</span><span class="o">.</span><span class="n">layer_norm_c</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">LayerNorm</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-14'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-14'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">150</span> <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span>
|
|
<span class="lineno">151</span> <span class="n">h</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">c</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span>
|
|
<span class="lineno">152</span> <span class="n">h_hat</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">c_hat</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-15'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-15'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">
|
|
\hat{x}_t = \begin{pmatrix}
|
|
h_{t-1} \\
|
|
x_t
|
|
\end{pmatrix}
|
|
</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">159</span> <span class="n">x_hat</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">cat</span><span class="p">((</span><span class="n">h</span><span class="p">,</span> <span class="n">x</span><span class="p">),</span> <span class="n">dim</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-16'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-16'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">\hat{h}_t, \hat{c}_t = lstm(\hat{x}_t, \hat{h}_{t-1}, \hat{c}_{t-1})</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">161</span> <span class="n">h_hat</span><span class="p">,</span> <span class="n">c_hat</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">hyper</span><span class="p">(</span><span class="n">x_hat</span><span class="p">,</span> <span class="n">h_hat</span><span class="p">,</span> <span class="n">c_hat</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-17'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-17'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">z_h^{i,f,g,o} = lin_{h}^{i,f,g,o}(\hat{h}_t)</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">164</span> <span class="n">z_h</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">z_h</span><span class="p">(</span><span class="n">h_hat</span><span class="p">)</span><span class="o">.</span><span class="n">chunk</span><span class="p">(</span><span class="mi">4</span><span class="p">,</span> <span class="n">dim</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-18'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-18'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">z_x^{i,f,g,o} = lin_x^{i,f,g,o}(\hat{h}_t)</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">166</span> <span class="n">z_x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">z_x</span><span class="p">(</span><span class="n">h_hat</span><span class="p">)</span><span class="o">.</span><span class="n">chunk</span><span class="p">(</span><span class="mi">4</span><span class="p">,</span> <span class="n">dim</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-19'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-19'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">z_b^{i,f,g,o} = lin_b^{i,f,g,o}(\hat{h}_t)</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">168</span> <span class="n">z_b</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">z_b</span><span class="p">(</span><span class="n">h_hat</span><span class="p">)</span><span class="o">.</span><span class="n">chunk</span><span class="p">(</span><span class="mi">4</span><span class="p">,</span> <span class="n">dim</span><span class="o">=-</span><span class="mi">1</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-20'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-20'>#</a>
|
|
</div>
|
|
<p>We calculate $i$, $f$, $g$ and $o$ in a loop</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">171</span> <span class="n">ifgo</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="lineno">172</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">4</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-21'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-21'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">d_h^{i,f,g,o}(z_h^{i,f,g,o}) = lin_{dh}^{i,f,g,o}(z_h^{i,f,g,o})</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">174</span> <span class="n">d_h</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_h</span><span class="p">[</span><span class="n">i</span><span class="p">](</span><span class="n">z_h</span><span class="p">[</span><span class="n">i</span><span class="p">])</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-22'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-22'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">d_x^{i,f,g,o}(z_x^{i,f,g,o}) = lin_{dx}^{i,f,g,o}(z_x^{i,f,g,o})</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">176</span> <span class="n">d_x</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_x</span><span class="p">[</span><span class="n">i</span><span class="p">](</span><span class="n">z_x</span><span class="p">[</span><span class="n">i</span><span class="p">])</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-23'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-23'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">\begin{align}
|
|
{i,f,g,o} = LN(&\color{lightgreen}{d_h^{i,f,g,o}(z_h) \odot (W_h^{i,f,g,o} h_{t-1})} \\
|
|
+ &\color{lightgreen}{d_x^{i,f,g,o}(z_x) \odot (W_h^{i,f,g,o} x_t)} \\
|
|
+ &d_b^{i,f,g,o}(z_b))
|
|
\end{align}</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">183</span> <span class="n">y</span> <span class="o">=</span> <span class="n">d_h</span> <span class="o">*</span> <span class="n">torch</span><span class="o">.</span><span class="n">einsum</span><span class="p">(</span><span class="s1">'ij,bj->bi'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">w_h</span><span class="p">[</span><span class="n">i</span><span class="p">],</span> <span class="n">h</span><span class="p">)</span> <span class="o">+</span> \
|
|
<span class="lineno">184</span> <span class="n">d_x</span> <span class="o">*</span> <span class="n">torch</span><span class="o">.</span><span class="n">einsum</span><span class="p">(</span><span class="s1">'ij,bj->bi'</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">w_x</span><span class="p">[</span><span class="n">i</span><span class="p">],</span> <span class="n">x</span><span class="p">)</span> <span class="o">+</span> \
|
|
<span class="lineno">185</span> <span class="bp">self</span><span class="o">.</span><span class="n">d_b</span><span class="p">[</span><span class="n">i</span><span class="p">](</span><span class="n">z_b</span><span class="p">[</span><span class="n">i</span><span class="p">])</span>
|
|
<span class="lineno">186</span>
|
|
<span class="lineno">187</span> <span class="n">ifgo</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">layer_norm</span><span class="p">[</span><span class="n">i</span><span class="p">](</span><span class="n">y</span><span class="p">))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-24'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-24'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">i_t, f_t, g_t, o_t</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">190</span> <span class="n">i</span><span class="p">,</span> <span class="n">f</span><span class="p">,</span> <span class="n">g</span><span class="p">,</span> <span class="n">o</span> <span class="o">=</span> <span class="n">ifgo</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-25'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-25'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">c_t = \sigma(f_t) \odot c_{t-1} + \sigma(i_t) \odot \tanh(g_t) </script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">193</span> <span class="n">c_next</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">sigmoid</span><span class="p">(</span><span class="n">f</span><span class="p">)</span> <span class="o">*</span> <span class="n">c</span> <span class="o">+</span> <span class="n">torch</span><span class="o">.</span><span class="n">sigmoid</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="o">*</span> <span class="n">torch</span><span class="o">.</span><span class="n">tanh</span><span class="p">(</span><span class="n">g</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-26'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-26'>#</a>
|
|
</div>
|
|
<p>
|
|
<script type="math/tex; mode=display">h_t = \sigma(o_t) \odot \tanh(LN(c_t))</script>
|
|
</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">196</span> <span class="n">h_next</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">sigmoid</span><span class="p">(</span><span class="n">o</span><span class="p">)</span> <span class="o">*</span> <span class="n">torch</span><span class="o">.</span><span class="n">tanh</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">layer_norm_c</span><span class="p">(</span><span class="n">c_next</span><span class="p">))</span>
|
|
<span class="lineno">197</span>
|
|
<span class="lineno">198</span> <span class="k">return</span> <span class="n">h_next</span><span class="p">,</span> <span class="n">c_next</span><span class="p">,</span> <span class="n">h_hat</span><span class="p">,</span> <span class="n">c_hat</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-27'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-27'>#</a>
|
|
</div>
|
|
<h1>HyperLSTM module</h1>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">201</span><span class="k">class</span> <span class="nc">HyperLSTM</span><span class="p">(</span><span class="n">Module</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-28'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-28'>#</a>
|
|
</div>
|
|
<p>Create a network of <code>n_layers</code> of HyperLSTM.</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">205</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">hyper_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_z</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">n_layers</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-29'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-29'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">210</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-30'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-30'>#</a>
|
|
</div>
|
|
<p>Store sizes to initialize state</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">213</span> <span class="bp">self</span><span class="o">.</span><span class="n">n_layers</span> <span class="o">=</span> <span class="n">n_layers</span>
|
|
<span class="lineno">214</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</span> <span class="o">=</span> <span class="n">hidden_size</span>
|
|
<span class="lineno">215</span> <span class="bp">self</span><span class="o">.</span><span class="n">hyper_size</span> <span class="o">=</span> <span class="n">hyper_size</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-31'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-31'>#</a>
|
|
</div>
|
|
<p>Create cells for each layer. Note that only the first layer gets the input directly.
|
|
Rest of the layers get the input from the layer below</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">219</span> <span class="bp">self</span><span class="o">.</span><span class="n">cells</span> <span class="o">=</span> <span class="n">nn</span><span class="o">.</span><span class="n">ModuleList</span><span class="p">([</span><span class="n">HyperLSTMCell</span><span class="p">(</span><span class="n">input_size</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">,</span> <span class="n">hyper_size</span><span class="p">,</span> <span class="n">n_z</span><span class="p">)]</span> <span class="o">+</span>
|
|
<span class="lineno">220</span> <span class="p">[</span><span class="n">HyperLSTMCell</span><span class="p">(</span><span class="n">hidden_size</span><span class="p">,</span> <span class="n">hidden_size</span><span class="p">,</span> <span class="n">hyper_size</span><span class="p">,</span> <span class="n">n_z</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span>
|
|
<span class="lineno">221</span> <span class="nb">range</span><span class="p">(</span><span class="n">n_layers</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)])</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-32'>
|
|
<div class='docs doc-strings'>
|
|
<div class='section-link'>
|
|
<a href='#section-32'>#</a>
|
|
</div>
|
|
<ul>
|
|
<li><code>x</code> has shape <code>[n_steps, batch_size, input_size]</code> and</li>
|
|
<li><code>state</code> is a tuple of $h, c, \hat{h}, \hat{c}$.
|
|
$h, c$ have shape <code>[batch_size, hidden_size]</code> and
|
|
$\hat{h}, \hat{c}$ have shape <code>[batch_size, hyper_size]</code>.</li>
|
|
</ul>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">223</span> <span class="k">def</span> <span class="fm">__call__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">:</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span>
|
|
<span class="lineno">224</span> <span class="n">state</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">torch</span><span class="o">.</span><span class="n">Tensor</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-33'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-33'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">231</span> <span class="n">n_steps</span><span class="p">,</span> <span class="n">batch_size</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">shape</span><span class="p">[:</span><span class="mi">2</span><span class="p">]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-34'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-34'>#</a>
|
|
</div>
|
|
<p>Initialize the state with zeros if <code>None</code></p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">234</span> <span class="k">if</span> <span class="n">state</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="lineno">235</span> <span class="n">h</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">new_zeros</span><span class="p">(</span><span class="n">batch_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">n_layers</span><span class="p">)]</span>
|
|
<span class="lineno">236</span> <span class="n">c</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">new_zeros</span><span class="p">(</span><span class="n">batch_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_size</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">n_layers</span><span class="p">)]</span>
|
|
<span class="lineno">237</span> <span class="n">h_hat</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">new_zeros</span><span class="p">(</span><span class="n">batch_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hyper_size</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">n_layers</span><span class="p">)]</span>
|
|
<span class="lineno">238</span> <span class="n">c_hat</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">new_zeros</span><span class="p">(</span><span class="n">batch_size</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hyper_size</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">n_layers</span><span class="p">)]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-35'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-35'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">240</span> <span class="k">else</span><span class="p">:</span>
|
|
<span class="lineno">241</span> <span class="p">(</span><span class="n">h</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h_hat</span><span class="p">,</span> <span class="n">c_hat</span><span class="p">)</span> <span class="o">=</span> <span class="n">state</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-36'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-36'>#</a>
|
|
</div>
|
|
<p>Reverse stack the tensors to get the states of each layer</p>
|
|
<p>📝 You can just work with the tensor itself but this is easier to debug</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">245</span> <span class="n">h</span><span class="p">,</span> <span class="n">c</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">unbind</span><span class="p">(</span><span class="n">h</span><span class="p">)),</span> <span class="nb">list</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">unbind</span><span class="p">(</span><span class="n">c</span><span class="p">))</span>
|
|
<span class="lineno">246</span> <span class="n">h_hat</span><span class="p">,</span> <span class="n">c_hat</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">unbind</span><span class="p">(</span><span class="n">h_hat</span><span class="p">)),</span> <span class="nb">list</span><span class="p">(</span><span class="n">torch</span><span class="o">.</span><span class="n">unbind</span><span class="p">(</span><span class="n">c_hat</span><span class="p">))</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-37'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-37'>#</a>
|
|
</div>
|
|
<p>Collect the outputs of the final layer at each step</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">249</span> <span class="n">out</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="lineno">250</span> <span class="k">for</span> <span class="n">t</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">n_steps</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-38'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-38'>#</a>
|
|
</div>
|
|
<p>Input to the first layer is the input itself</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">252</span> <span class="n">inp</span> <span class="o">=</span> <span class="n">x</span><span class="p">[</span><span class="n">t</span><span class="p">]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-39'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-39'>#</a>
|
|
</div>
|
|
<p>Loop through the layers</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">254</span> <span class="k">for</span> <span class="n">layer</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">n_layers</span><span class="p">):</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-40'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-40'>#</a>
|
|
</div>
|
|
<p>Get the state of the layer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">256</span> <span class="n">h</span><span class="p">[</span><span class="n">layer</span><span class="p">],</span> <span class="n">c</span><span class="p">[</span><span class="n">layer</span><span class="p">],</span> <span class="n">h_hat</span><span class="p">[</span><span class="n">layer</span><span class="p">],</span> <span class="n">c_hat</span><span class="p">[</span><span class="n">layer</span><span class="p">]</span> <span class="o">=</span> \
|
|
<span class="lineno">257</span> <span class="bp">self</span><span class="o">.</span><span class="n">cells</span><span class="p">[</span><span class="n">layer</span><span class="p">](</span><span class="n">inp</span><span class="p">,</span> <span class="n">h</span><span class="p">[</span><span class="n">layer</span><span class="p">],</span> <span class="n">c</span><span class="p">[</span><span class="n">layer</span><span class="p">],</span> <span class="n">h_hat</span><span class="p">[</span><span class="n">layer</span><span class="p">],</span> <span class="n">c_hat</span><span class="p">[</span><span class="n">layer</span><span class="p">])</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-41'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-41'>#</a>
|
|
</div>
|
|
<p>Input to the next layer is the state of this layer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">259</span> <span class="n">inp</span> <span class="o">=</span> <span class="n">h</span><span class="p">[</span><span class="n">layer</span><span class="p">]</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-42'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-42'>#</a>
|
|
</div>
|
|
<p>Collect the output $h$ of the final layer</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">261</span> <span class="n">out</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">h</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-43'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-43'>#</a>
|
|
</div>
|
|
<p>Stack the outputs and states</p>
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">264</span> <span class="n">out</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="n">out</span><span class="p">)</span>
|
|
<span class="lineno">265</span> <span class="n">h</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="n">h</span><span class="p">)</span>
|
|
<span class="lineno">266</span> <span class="n">c</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="n">c</span><span class="p">)</span>
|
|
<span class="lineno">267</span> <span class="n">h_hat</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="n">h_hat</span><span class="p">)</span>
|
|
<span class="lineno">268</span> <span class="n">c_hat</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="n">c_hat</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
<div class='section' id='section-44'>
|
|
<div class='docs'>
|
|
<div class='section-link'>
|
|
<a href='#section-44'>#</a>
|
|
</div>
|
|
|
|
</div>
|
|
<div class='code'>
|
|
<div class="highlight"><pre><span class="lineno">271</span> <span class="k">return</span> <span class="n">out</span><span class="p">,</span> <span class="p">(</span><span class="n">h</span><span class="p">,</span> <span class="n">c</span><span class="p">,</span> <span class="n">h_hat</span><span class="p">,</span> <span class="n">c_hat</span><span class="p">)</span></pre></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.4/MathJax.js?config=TeX-AMS_HTML">
|
|
</script>
|
|
<!-- MathJax configuration -->
|
|
<script type="text/x-mathjax-config">
|
|
MathJax.Hub.Config({
|
|
tex2jax: {
|
|
inlineMath: [ ['$','$'] ],
|
|
displayMath: [ ['$$','$$'] ],
|
|
processEscapes: true,
|
|
processEnvironments: true
|
|
},
|
|
// Center justify equations in code and markdown cells. Elsewhere
|
|
// we use CSS to left justify single line equations in code cells.
|
|
displayAlign: 'center',
|
|
"HTML-CSS": { fonts: ["TeX"] }
|
|
});
|
|
</script>
|
|
<script>
|
|
function handleImages() {
|
|
var images = document.querySelectorAll('p>img')
|
|
|
|
console.log(images);
|
|
for (var i = 0; i < images.length; ++i) {
|
|
handleImage(images[i])
|
|
}
|
|
}
|
|
|
|
function handleImage(img) {
|
|
img.parentElement.style.textAlign = 'center'
|
|
|
|
var modal = document.createElement('div')
|
|
modal.id = 'modal'
|
|
|
|
var modalContent = document.createElement('div')
|
|
modal.appendChild(modalContent)
|
|
|
|
var modalImage = document.createElement('img')
|
|
modalContent.appendChild(modalImage)
|
|
|
|
var span = document.createElement('span')
|
|
span.classList.add('close')
|
|
span.textContent = 'x'
|
|
modal.appendChild(span)
|
|
|
|
img.onclick = function () {
|
|
console.log('clicked')
|
|
document.body.appendChild(modal)
|
|
modalImage.src = img.src
|
|
}
|
|
|
|
span.onclick = function () {
|
|
document.body.removeChild(modal)
|
|
}
|
|
}
|
|
|
|
handleImages()
|
|
</script>
|
|
</body>
|
|
</html> |