build based on ab46da1
This commit is contained in:
parent
55553fd2be
commit
dfdaed5ad5
@ -11,34 +11,34 @@ m(5) == 26
|
||||
|
||||
m = Chain(Dense(10, 5), Dense(5, 2))
|
||||
x = rand(10)
|
||||
m(x) == m[2](m[1](x))</code></pre><p><code>Chain</code> also supports indexing and slicing, e.g. <code>m[2]</code> or <code>m[1:end-1]</code>. <code>m[1:3](x)</code> will calculate the output of the first three layers.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/basic.jl#L1-L18">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Dense" href="#Flux.Dense"><code>Flux.Dense</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Dense(in::Integer, out::Integer, σ = identity)</code></pre><p>Creates a traditional <code>Dense</code> layer with parameters <code>W</code> and <code>b</code>.</p><pre><code class="language-none">y = σ.(W * x .+ b)</code></pre><p>The input <code>x</code> must be a vector of length <code>in</code>, or a batch of vectors represented as an <code>in × N</code> matrix. The out <code>y</code> will be a vector or batch of length <code>out</code>.</p><pre><code class="language-julia">julia> d = Dense(5, 2)
|
||||
m(x) == m[2](m[1](x))</code></pre><p><code>Chain</code> also supports indexing and slicing, e.g. <code>m[2]</code> or <code>m[1:end-1]</code>. <code>m[1:3](x)</code> will calculate the output of the first three layers.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/basic.jl#L1-L18">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Dense" href="#Flux.Dense"><code>Flux.Dense</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Dense(in::Integer, out::Integer, σ = identity)</code></pre><p>Creates a traditional <code>Dense</code> layer with parameters <code>W</code> and <code>b</code>.</p><pre><code class="language-none">y = σ.(W * x .+ b)</code></pre><p>The input <code>x</code> must be a vector of length <code>in</code>, or a batch of vectors represented as an <code>in × N</code> matrix. The out <code>y</code> will be a vector or batch of length <code>out</code>.</p><pre><code class="language-julia">julia> d = Dense(5, 2)
|
||||
Dense(5, 2)
|
||||
|
||||
julia> d(rand(5))
|
||||
Tracked 2-element Array{Float64,1}:
|
||||
0.00257447
|
||||
-0.00449443</code></pre></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/basic.jl#L45-L64">source</a></section><h2><a class="nav-anchor" id="Convolution-and-Pooling-Layers-1" href="#Convolution-and-Pooling-Layers-1">Convolution and Pooling Layers</a></h2><p>These layers are used to build convolutional neural networks (CNNs).</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Conv" href="#Flux.Conv"><code>Flux.Conv</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Conv(size, in=>out)
|
||||
-0.00449443</code></pre></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/basic.jl#L45-L64">source</a></section><h2><a class="nav-anchor" id="Convolution-and-Pooling-Layers-1" href="#Convolution-and-Pooling-Layers-1">Convolution and Pooling Layers</a></h2><p>These layers are used to build convolutional neural networks (CNNs).</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Conv" href="#Flux.Conv"><code>Flux.Conv</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Conv(size, in=>out)
|
||||
Conv(size, in=>out, relu)</code></pre><p>Standard convolutional layer. <code>size</code> should be a tuple like <code>(2, 2)</code>. <code>in</code> and <code>out</code> specify the number of input and output channels respectively.</p><p>Example: Applying Conv layer to a 1-channel input using a 2x2 window size, giving us a 16-channel output. Output is activated with ReLU.</p><pre><code class="language-none">size = (2,2)
|
||||
in = 1
|
||||
out = 16
|
||||
Conv((2, 2), 1=>16, relu)</code></pre><p>Data should be stored in WHCN order (width, height, # channels, # batches). In other words, a 100×100 RGB image would be a <code>100×100×3×1</code> array, and a batch of 50 would be a <code>100×100×3×50</code> array.</p><p>Takes the keyword arguments <code>pad</code>, <code>stride</code> and <code>dilation</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/conv.jl#L8-L28">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.MaxPool" href="#Flux.MaxPool"><code>Flux.MaxPool</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">MaxPool(k)</code></pre><p>Max pooling layer. <code>k</code> stands for the size of the window for each dimension of the input.</p><p>Takes the keyword arguments <code>pad</code> and <code>stride</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/conv.jl#L168-L174">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.MeanPool" href="#Flux.MeanPool"><code>Flux.MeanPool</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">MeanPool(k)</code></pre><p>Mean pooling layer. <code>k</code> stands for the size of the window for each dimension of the input.</p><p>Takes the keyword arguments <code>pad</code> and <code>stride</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/conv.jl#L190-L196">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.DepthwiseConv" href="#Flux.DepthwiseConv"><code>Flux.DepthwiseConv</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">DepthwiseConv(size, in)
|
||||
Conv((2, 2), 1=>16, relu)</code></pre><p>Data should be stored in WHCN order (width, height, # channels, # batches). In other words, a 100×100 RGB image would be a <code>100×100×3×1</code> array, and a batch of 50 would be a <code>100×100×3×50</code> array.</p><p>Takes the keyword arguments <code>pad</code>, <code>stride</code> and <code>dilation</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/conv.jl#L8-L28">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.MaxPool" href="#Flux.MaxPool"><code>Flux.MaxPool</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">MaxPool(k)</code></pre><p>Max pooling layer. <code>k</code> stands for the size of the window for each dimension of the input.</p><p>Takes the keyword arguments <code>pad</code> and <code>stride</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/conv.jl#L168-L174">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.MeanPool" href="#Flux.MeanPool"><code>Flux.MeanPool</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">MeanPool(k)</code></pre><p>Mean pooling layer. <code>k</code> stands for the size of the window for each dimension of the input.</p><p>Takes the keyword arguments <code>pad</code> and <code>stride</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/conv.jl#L190-L196">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.DepthwiseConv" href="#Flux.DepthwiseConv"><code>Flux.DepthwiseConv</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">DepthwiseConv(size, in)
|
||||
DepthwiseConv(size, in=>mul)
|
||||
DepthwiseConv(size, in=>mul, relu)</code></pre><p>Depthwise convolutional layer. <code>size</code> should be a tuple like <code>(2, 2)</code>. <code>in</code> and <code>mul</code> specify the number of input channels and channel multiplier respectively. In case the <code>mul</code> is not specified it is taken as 1.</p><p>Data should be stored in WHCN order. In other words, a 100×100 RGB image would be a <code>100×100×3</code> array, and a batch of 50 would be a <code>100×100×3×50</code> array.</p><p>Takes the keyword arguments <code>pad</code> and <code>stride</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/conv.jl#L117-L130">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.ConvTranspose" href="#Flux.ConvTranspose"><code>Flux.ConvTranspose</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">ConvTranspose(size, in=>out)
|
||||
ConvTranspose(size, in=>out, relu)</code></pre><p>Standard convolutional transpose layer. <code>size</code> should be a tuple like <code>(2, 2)</code>. <code>in</code> and <code>out</code> specify the number of input and output channels respectively. Data should be stored in WHCN order. In other words, a 100×100 RGB image would be a <code>100×100×3</code> array, and a batch of 50 would be a <code>100×100×3×50</code> array. Takes the keyword arguments <code>pad</code>, <code>stride</code> and <code>dilation</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/conv.jl#L69-L78">source</a></section><h2><a class="nav-anchor" id="Recurrent-Layers-1" href="#Recurrent-Layers-1">Recurrent Layers</a></h2><p>Much like the core layers above, but can be used to process sequence data (as well as other kinds of structured data).</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.RNN" href="#Flux.RNN"><code>Flux.RNN</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">RNN(in::Integer, out::Integer, σ = tanh)</code></pre><p>The most basic recurrent layer; essentially acts as a <code>Dense</code> layer, but with the output fed back into the input each time step.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/recurrent.jl#L105-L110">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.LSTM" href="#Flux.LSTM"><code>Flux.LSTM</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">LSTM(in::Integer, out::Integer)</code></pre><p>Long Short Term Memory recurrent layer. Behaves like an RNN but generally exhibits a longer memory span over sequences.</p><p>See <a href="http://colah.github.io/posts/2015-08-Understanding-LSTMs/">this article</a> for a good overview of the internals.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/recurrent.jl#L150-L158">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.GRU" href="#Flux.GRU"><code>Flux.GRU</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">GRU(in::Integer, out::Integer)</code></pre><p>Gated Recurrent Unit layer. Behaves like an RNN but generally exhibits a longer memory span over sequences.</p><p>See <a href="http://colah.github.io/posts/2015-08-Understanding-LSTMs/">this article</a> for a good overview of the internals.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/recurrent.jl#L191-L199">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Recur" href="#Flux.Recur"><code>Flux.Recur</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Recur(cell)</code></pre><p><code>Recur</code> takes a recurrent cell and makes it stateful, managing the hidden state in the background. <code>cell</code> should be a model of the form:</p><pre><code class="language-none">h, y = cell(h, x...)</code></pre><p>For example, here's a recurrent network that keeps a running total of its inputs.</p><pre><code class="language-julia">accum(h, x) = (h+x, x)
|
||||
DepthwiseConv(size, in=>mul, relu)</code></pre><p>Depthwise convolutional layer. <code>size</code> should be a tuple like <code>(2, 2)</code>. <code>in</code> and <code>mul</code> specify the number of input channels and channel multiplier respectively. In case the <code>mul</code> is not specified it is taken as 1.</p><p>Data should be stored in WHCN order. In other words, a 100×100 RGB image would be a <code>100×100×3</code> array, and a batch of 50 would be a <code>100×100×3×50</code> array.</p><p>Takes the keyword arguments <code>pad</code> and <code>stride</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/conv.jl#L117-L130">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.ConvTranspose" href="#Flux.ConvTranspose"><code>Flux.ConvTranspose</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">ConvTranspose(size, in=>out)
|
||||
ConvTranspose(size, in=>out, relu)</code></pre><p>Standard convolutional transpose layer. <code>size</code> should be a tuple like <code>(2, 2)</code>. <code>in</code> and <code>out</code> specify the number of input and output channels respectively. Data should be stored in WHCN order. In other words, a 100×100 RGB image would be a <code>100×100×3</code> array, and a batch of 50 would be a <code>100×100×3×50</code> array. Takes the keyword arguments <code>pad</code>, <code>stride</code> and <code>dilation</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/conv.jl#L69-L78">source</a></section><h2><a class="nav-anchor" id="Recurrent-Layers-1" href="#Recurrent-Layers-1">Recurrent Layers</a></h2><p>Much like the core layers above, but can be used to process sequence data (as well as other kinds of structured data).</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.RNN" href="#Flux.RNN"><code>Flux.RNN</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">RNN(in::Integer, out::Integer, σ = tanh)</code></pre><p>The most basic recurrent layer; essentially acts as a <code>Dense</code> layer, but with the output fed back into the input each time step.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/recurrent.jl#L105-L110">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.LSTM" href="#Flux.LSTM"><code>Flux.LSTM</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">LSTM(in::Integer, out::Integer)</code></pre><p>Long Short Term Memory recurrent layer. Behaves like an RNN but generally exhibits a longer memory span over sequences.</p><p>See <a href="http://colah.github.io/posts/2015-08-Understanding-LSTMs/">this article</a> for a good overview of the internals.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/recurrent.jl#L150-L158">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.GRU" href="#Flux.GRU"><code>Flux.GRU</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">GRU(in::Integer, out::Integer)</code></pre><p>Gated Recurrent Unit layer. Behaves like an RNN but generally exhibits a longer memory span over sequences.</p><p>See <a href="http://colah.github.io/posts/2015-08-Understanding-LSTMs/">this article</a> for a good overview of the internals.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/recurrent.jl#L191-L199">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Recur" href="#Flux.Recur"><code>Flux.Recur</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Recur(cell)</code></pre><p><code>Recur</code> takes a recurrent cell and makes it stateful, managing the hidden state in the background. <code>cell</code> should be a model of the form:</p><pre><code class="language-none">h, y = cell(h, x...)</code></pre><p>For example, here's a recurrent network that keeps a running total of its inputs.</p><pre><code class="language-julia">accum(h, x) = (h+x, x)
|
||||
rnn = Flux.Recur(accum, 0)
|
||||
rnn(2) # 2
|
||||
rnn(3) # 3
|
||||
rnn.state # 5
|
||||
rnn.(1:10) # apply to a sequence
|
||||
rnn.state # 60</code></pre></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/recurrent.jl#L7-L26">source</a></section><h2><a class="nav-anchor" id="Other-General-Purpose-Layers-1" href="#Other-General-Purpose-Layers-1">Other General Purpose Layers</a></h2><p>These are marginally more obscure than the Basic Layers. But in contrast to the layers described in the other sections are not readily grouped around a particular purpose (e.g. CNNs or RNNs).</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Maxout" href="#Flux.Maxout"><code>Flux.Maxout</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Maxout(over)</code></pre><p><code>Maxout</code> is a neural network layer, which has a number of internal layers, which all have the same input, and the maxout returns the elementwise maximium of the internal layers' outputs.</p><p>Maxout over linear dense layers satisfies the univeral approximation theorem.</p><p>Reference: Ian J. Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron Courville, and Yoshua Bengio.</p><ol><li>Maxout networks.</li></ol><p>In Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28 (ICML'13), Sanjoy Dasgupta and David McAllester (Eds.), Vol. 28. JMLR.org III-1319-III-1327. https://arxiv.org/pdf/1302.4389.pdf</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/basic.jl#L129-L144">source</a></section><h1><a class="nav-anchor" id="Normalisation-and-Regularisation-1" href="#Normalisation-and-Regularisation-1">Normalisation & Regularisation</a></h1><p>These layers don't affect the structure of the network but may improve training times or reduce overfitting.</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.testmode!" href="#Flux.testmode!"><code>Flux.testmode!</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">testmode!(m)
|
||||
testmode!(m, false)</code></pre><p>Put layers like <a href="#Flux.Dropout"><code>Dropout</code></a> and <a href="#Flux.BatchNorm"><code>BatchNorm</code></a> into testing mode (or back to training mode with <code>false</code>).</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/normalise.jl#L1-L7">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.BatchNorm" href="#Flux.BatchNorm"><code>Flux.BatchNorm</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">BatchNorm(channels::Integer, σ = identity;
|
||||
rnn.state # 60</code></pre></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/recurrent.jl#L7-L26">source</a></section><h2><a class="nav-anchor" id="Other-General-Purpose-Layers-1" href="#Other-General-Purpose-Layers-1">Other General Purpose Layers</a></h2><p>These are marginally more obscure than the Basic Layers. But in contrast to the layers described in the other sections are not readily grouped around a particular purpose (e.g. CNNs or RNNs).</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Maxout" href="#Flux.Maxout"><code>Flux.Maxout</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Maxout(over)</code></pre><p><code>Maxout</code> is a neural network layer, which has a number of internal layers, which all have the same input, and the maxout returns the elementwise maximium of the internal layers' outputs.</p><p>Maxout over linear dense layers satisfies the univeral approximation theorem.</p><p>Reference: Ian J. Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron Courville, and Yoshua Bengio.</p><ol><li>Maxout networks.</li></ol><p>In Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28 (ICML'13), Sanjoy Dasgupta and David McAllester (Eds.), Vol. 28. JMLR.org III-1319-III-1327. https://arxiv.org/pdf/1302.4389.pdf</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/basic.jl#L129-L144">source</a></section><h1><a class="nav-anchor" id="Normalisation-and-Regularisation-1" href="#Normalisation-and-Regularisation-1">Normalisation & Regularisation</a></h1><p>These layers don't affect the structure of the network but may improve training times or reduce overfitting.</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.testmode!" href="#Flux.testmode!"><code>Flux.testmode!</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">testmode!(m)
|
||||
testmode!(m, false)</code></pre><p>Put layers like <a href="#Flux.Dropout"><code>Dropout</code></a> and <a href="#Flux.BatchNorm"><code>BatchNorm</code></a> into testing mode (or back to training mode with <code>false</code>).</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/normalise.jl#L1-L7">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.BatchNorm" href="#Flux.BatchNorm"><code>Flux.BatchNorm</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">BatchNorm(channels::Integer, σ = identity;
|
||||
initβ = zeros, initγ = ones,
|
||||
ϵ = 1e-8, momentum = .1)</code></pre><p>Batch Normalization layer. The <code>channels</code> input should be the size of the channel dimension in your data (see below).</p><p>Given an array with <code>N</code> dimensions, call the <code>N-1</code>th the channel dimension. (For a batch of feature vectors this is just the data dimension, for <code>WHCN</code> images it's the usual channel dimension.)</p><p><code>BatchNorm</code> computes the mean and variance for each each <code>W×H×1×N</code> slice and shifts them to have a new mean and variance (corresponding to the learnable, per-channel <code>bias</code> and <code>scale</code> parameters).</p><p>See <a href="https://arxiv.org/pdf/1502.03167.pdf">Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift</a>.</p><p>Example:</p><pre><code class="language-julia">m = Chain(
|
||||
Dense(28^2, 64),
|
||||
BatchNorm(64, relu),
|
||||
Dense(64, 10),
|
||||
BatchNorm(10),
|
||||
softmax)</code></pre></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/normalise.jl#L99-L127">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Dropout" href="#Flux.Dropout"><code>Flux.Dropout</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Dropout(p)</code></pre><p>A Dropout layer. For each input, either sets that input to <code>0</code> (with probability <code>p</code>) or scales it by <code>1/(1-p)</code>. This is used as a regularisation, i.e. it reduces overfitting during training.</p><p>Does nothing to the input once in <a href="#Flux.testmode!"><code>testmode!</code></a>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/normalise.jl#L15-L23">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.LayerNorm" href="#Flux.LayerNorm"><code>Flux.LayerNorm</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">LayerNorm(h::Integer)</code></pre><p>A <a href="https://arxiv.org/pdf/1607.06450.pdf">normalisation layer</a> designed to be used with recurrent hidden states of size <code>h</code>. Normalises the mean/stddev of each input before applying a per-neuron gain/bias.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/layers/normalise.jl#L77-L83">source</a></section><h2><a class="nav-anchor" id="Activation-Functions-1" href="#Activation-Functions-1">Activation Functions</a></h2><p>Non-linearities that go between layers of your model. Most of these functions are defined in <a href="https://github.com/FluxML/NNlib.jl">NNlib</a> but are available by default in Flux.</p><p>Note that, unless otherwise stated, activation functions operate on scalars. To apply them to an array you can call <code>σ.(xs)</code>, <code>relu.(xs)</code> and so on.</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.σ" href="#NNlib.σ"><code>NNlib.σ</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">σ(x) = 1 / (1 + exp(-x))</code></pre><p>Classic <a href="https://en.wikipedia.org/wiki/Sigmoid_function">sigmoid</a> activation function.</p></div></div></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.relu" href="#NNlib.relu"><code>NNlib.relu</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">relu(x) = max(0, x)</code></pre><p><a href="https://en.wikipedia.org/wiki/Rectifier_(neural_networks)">Rectified Linear Unit</a> activation function.</p></div></div></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.leakyrelu" href="#NNlib.leakyrelu"><code>NNlib.leakyrelu</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">leakyrelu(x) = max(0.01x, x)</code></pre><p>Leaky <a href="https://en.wikipedia.org/wiki/Rectifier_(neural_networks)">Rectified Linear Unit</a> activation function. You can also specify the coefficient explicitly, e.g. <code>leakyrelu(x, 0.01)</code>.</p></div></div></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.elu" href="#NNlib.elu"><code>NNlib.elu</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">elu(x, α = 1) =
|
||||
softmax)</code></pre></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/normalise.jl#L99-L127">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Dropout" href="#Flux.Dropout"><code>Flux.Dropout</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Dropout(p)</code></pre><p>A Dropout layer. For each input, either sets that input to <code>0</code> (with probability <code>p</code>) or scales it by <code>1/(1-p)</code>. This is used as a regularisation, i.e. it reduces overfitting during training.</p><p>Does nothing to the input once in <a href="#Flux.testmode!"><code>testmode!</code></a>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/normalise.jl#L15-L23">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.LayerNorm" href="#Flux.LayerNorm"><code>Flux.LayerNorm</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">LayerNorm(h::Integer)</code></pre><p>A <a href="https://arxiv.org/pdf/1607.06450.pdf">normalisation layer</a> designed to be used with recurrent hidden states of size <code>h</code>. Normalises the mean/stddev of each input before applying a per-neuron gain/bias.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/layers/normalise.jl#L77-L83">source</a></section><h2><a class="nav-anchor" id="Activation-Functions-1" href="#Activation-Functions-1">Activation Functions</a></h2><p>Non-linearities that go between layers of your model. Most of these functions are defined in <a href="https://github.com/FluxML/NNlib.jl">NNlib</a> but are available by default in Flux.</p><p>Note that, unless otherwise stated, activation functions operate on scalars. To apply them to an array you can call <code>σ.(xs)</code>, <code>relu.(xs)</code> and so on.</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.σ" href="#NNlib.σ"><code>NNlib.σ</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">σ(x) = 1 / (1 + exp(-x))</code></pre><p>Classic <a href="https://en.wikipedia.org/wiki/Sigmoid_function">sigmoid</a> activation function.</p></div></div></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.relu" href="#NNlib.relu"><code>NNlib.relu</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">relu(x) = max(0, x)</code></pre><p><a href="https://en.wikipedia.org/wiki/Rectifier_(neural_networks)">Rectified Linear Unit</a> activation function.</p></div></div></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.leakyrelu" href="#NNlib.leakyrelu"><code>NNlib.leakyrelu</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">leakyrelu(x) = max(0.01x, x)</code></pre><p>Leaky <a href="https://en.wikipedia.org/wiki/Rectifier_(neural_networks)">Rectified Linear Unit</a> activation function. You can also specify the coefficient explicitly, e.g. <code>leakyrelu(x, 0.01)</code>.</p></div></div></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.elu" href="#NNlib.elu"><code>NNlib.elu</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">elu(x, α = 1) =
|
||||
x > 0 ? x : α * (exp(x) - 1)</code></pre><p>Exponential Linear Unit activation function. See <a href="https://arxiv.org/abs/1511.07289">Fast and Accurate Deep Network Learning by Exponential Linear Units</a>. You can also specify the coefficient explicitly, e.g. <code>elu(x, 1)</code>.</p></div></div></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="NNlib.swish" href="#NNlib.swish"><code>NNlib.swish</code></a> — <span class="docstring-category">Function</span>.</div><div><div><pre><code class="language-none">swish(x) = x * σ(x)</code></pre><p>Self-gated actvation function. See <a href="https://arxiv.org/pdf/1710.05941.pdf">Swish: a Self-Gated Activation Function</a>.</p></div></div></section><h2><a class="nav-anchor" id="Normalisation-and-Regularisation-2" href="#Normalisation-and-Regularisation-2">Normalisation & Regularisation</a></h2><p>These layers don't affect the structure of the network but may improve training times or reduce overfitting.</p><pre><code class="language-none">Flux.testmode!
|
||||
BatchNorm
|
||||
Dropout
|
||||
|
@ -39,4 +39,8 @@ m = Flux.Recur(rnn, h)
|
||||
|
||||
y = m(x)</code></pre><p>The <code>Recur</code> wrapper stores the state between runs in the <code>m.state</code> field.</p><p>If you use the <code>RNN(10, 5)</code> constructor – as opposed to <code>RNNCell</code> – you'll see that it's simply a wrapped cell.</p><pre><code class="language-julia">julia> RNN(10, 5)
|
||||
Recur(RNNCell(Dense(15, 5)))</code></pre><h2><a class="nav-anchor" id="Sequences-1" href="#Sequences-1">Sequences</a></h2><p>Often we want to work with sequences of inputs, rather than individual <code>x</code>s.</p><pre><code class="language-julia">seq = [rand(10) for i = 1:10]</code></pre><p>With <code>Recur</code>, applying our model to each element of a sequence is trivial:</p><pre><code class="language-julia">m.(seq) # returns a list of 5-element vectors</code></pre><p>This works even when we've chain recurrent layers into a larger model.</p><pre><code class="language-julia">m = Chain(LSTM(10, 15), Dense(15, 5))
|
||||
m.(seq)</code></pre><h2><a class="nav-anchor" id="Truncating-Gradients-1" href="#Truncating-Gradients-1">Truncating Gradients</a></h2><p>By default, calculating the gradients in a recurrent layer involves its entire history. For example, if we call the model on 100 inputs, we'll have to calculate the gradient for those 100 calls. If we then calculate another 10 inputs we have to calculate 110 gradients – this accumulates and quickly becomes expensive.</p><p>To avoid this we can <em>truncate</em> the gradient calculation, forgetting the history.</p><pre><code class="language-julia">truncate!(m)</code></pre><p>Calling <code>truncate!</code> wipes the slate clean, so we can call the model with more inputs without building up an expensive gradient computation.</p><p><code>truncate!</code> makes sense when you are working with multiple chunks of a large sequence, but we may also want to work with a set of independent sequences. In this case the hidden state should be completely reset to its original value, throwing away any accumulated information. <code>reset!</code> does this for you.</p><footer><hr/><a class="previous" href="../basics/"><span class="direction">Previous</span><span class="title">Basics</span></a><a class="next" href="../regularisation/"><span class="direction">Next</span><span class="title">Regularisation</span></a></footer></article></body></html>
|
||||
m.(seq)</code></pre><h2><a class="nav-anchor" id="Truncating-Gradients-1" href="#Truncating-Gradients-1">Truncating Gradients</a></h2><p>By default, calculating the gradients in a recurrent layer involves its entire history. For example, if we call the model on 100 inputs, we'll have to calculate the gradient for those 100 calls. If we then calculate another 10 inputs we have to calculate 110 gradients – this accumulates and quickly becomes expensive.</p><p>To avoid this we can <em>truncate</em> the gradient calculation, forgetting the history.</p><pre><code class="language-julia">truncate!(m)</code></pre><p>Calling <code>truncate!</code> wipes the slate clean, so we can call the model with more inputs without building up an expensive gradient computation.</p><p><code>truncate!</code> makes sense when you are working with multiple chunks of a large sequence, but we may also want to work with a set of independent sequences. In this case the hidden state should be completely reset to its original value, throwing away any accumulated information. <code>reset!</code> does this for you.</p><p>In general, when training with recurrent layers in your model, you'll want to call <code>reset!</code> or <code>truncate!</code> for each loss calculation:</p><pre><code class="language-julia">function loss(x,y)
|
||||
l = Flux.mse(m(x), y)
|
||||
Flux.reset!(m)
|
||||
return l
|
||||
end</code></pre><footer><hr/><a class="previous" href="../basics/"><span class="direction">Previous</span><span class="title">Basics</span></a><a class="next" href="../regularisation/"><span class="direction">Next</span><span class="title">Regularisation</span></a></footer></article></body></html>
|
||||
|
@ -133,7 +133,7 @@ var documenterSearchIndex = {"docs": [
|
||||
"page": "Recurrence",
|
||||
"title": "Truncating Gradients",
|
||||
"category": "section",
|
||||
"text": "By default, calculating the gradients in a recurrent layer involves its entire history. For example, if we call the model on 100 inputs, we\'ll have to calculate the gradient for those 100 calls. If we then calculate another 10 inputs we have to calculate 110 gradients – this accumulates and quickly becomes expensive.To avoid this we can truncate the gradient calculation, forgetting the history.truncate!(m)Calling truncate! wipes the slate clean, so we can call the model with more inputs without building up an expensive gradient computation.truncate! makes sense when you are working with multiple chunks of a large sequence, but we may also want to work with a set of independent sequences. In this case the hidden state should be completely reset to its original value, throwing away any accumulated information. reset! does this for you."
|
||||
"text": "By default, calculating the gradients in a recurrent layer involves its entire history. For example, if we call the model on 100 inputs, we\'ll have to calculate the gradient for those 100 calls. If we then calculate another 10 inputs we have to calculate 110 gradients – this accumulates and quickly becomes expensive.To avoid this we can truncate the gradient calculation, forgetting the history.truncate!(m)Calling truncate! wipes the slate clean, so we can call the model with more inputs without building up an expensive gradient computation.truncate! makes sense when you are working with multiple chunks of a large sequence, but we may also want to work with a set of independent sequences. In this case the hidden state should be completely reset to its original value, throwing away any accumulated information. reset! does this for you.In general, when training with recurrent layers in your model, you\'ll want to call reset! or truncate! for each loss calculation:function loss(x,y)\n l = Flux.mse(m(x), y)\n Flux.reset!(m)\n return l\nend"
|
||||
},
|
||||
|
||||
{
|
||||
|
@ -27,4 +27,4 @@ end</code></pre><p>Running this will alter the parameters <code>W</code> and <co
|
||||
|
||||
for p in (W, b)
|
||||
update!(opt, p, grads[p])
|
||||
end</code></pre><p>An optimiser <code>update!</code> accepts a parameter and a gradient, and updates the parameter according to the chosen rule. We can also pass <code>opt</code> to our <a href="../training/">training loop</a>, which will update all parameters of the model in a loop. However, we can now easily replace <code>Descent</code> with a more advanced optimiser such as <code>ADAM</code>.</p><h2><a class="nav-anchor" id="Optimiser-Reference-1" href="#Optimiser-Reference-1">Optimiser Reference</a></h2><p>All optimisers return an object that, when passed to <code>train!</code>, will update the parameters passed to it.</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.Descent" href="#Flux.Optimise.Descent"><code>Flux.Optimise.Descent</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Descent(η)</code></pre><p>Classic gradient descent optimiser with learning rate <code>η</code>. For each parameter <code>p</code> and its gradient <code>δp</code>, this runs <code>p -= η*δp</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/optimise/optimisers.jl#L9-L14">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.Momentum" href="#Flux.Optimise.Momentum"><code>Flux.Optimise.Momentum</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Momentum(params, η = 0.01; ρ = 0.9)</code></pre><p>Gradient descent with learning rate <code>η</code> and momentum <code>ρ</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/optimise/optimisers.jl#L25-L29">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.Nesterov" href="#Flux.Optimise.Nesterov"><code>Flux.Optimise.Nesterov</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Nesterov(eta, ρ = 0.9)</code></pre><p>Gradient descent with learning rate <code>η</code> and Nesterov momentum <code>ρ</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/optimise/optimisers.jl#L45-L49">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.ADAM" href="#Flux.Optimise.ADAM"><code>Flux.Optimise.ADAM</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">ADAM(η = 0.001, β = (0.9, 0.999))</code></pre><p><a href="https://arxiv.org/abs/1412.6980v8">ADAM</a> optimiser.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/b5a6207350fc0be7526c741316050bb30486af0b/src/optimise/optimisers.jl#L88-L92">source</a></section><footer><hr/><a class="previous" href="../../models/layers/"><span class="direction">Previous</span><span class="title">Model Reference</span></a><a class="next" href="../training/"><span class="direction">Next</span><span class="title">Training</span></a></footer></article></body></html>
|
||||
end</code></pre><p>An optimiser <code>update!</code> accepts a parameter and a gradient, and updates the parameter according to the chosen rule. We can also pass <code>opt</code> to our <a href="../training/">training loop</a>, which will update all parameters of the model in a loop. However, we can now easily replace <code>Descent</code> with a more advanced optimiser such as <code>ADAM</code>.</p><h2><a class="nav-anchor" id="Optimiser-Reference-1" href="#Optimiser-Reference-1">Optimiser Reference</a></h2><p>All optimisers return an object that, when passed to <code>train!</code>, will update the parameters passed to it.</p><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.Descent" href="#Flux.Optimise.Descent"><code>Flux.Optimise.Descent</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Descent(η)</code></pre><p>Classic gradient descent optimiser with learning rate <code>η</code>. For each parameter <code>p</code> and its gradient <code>δp</code>, this runs <code>p -= η*δp</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/optimise/optimisers.jl#L9-L14">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.Momentum" href="#Flux.Optimise.Momentum"><code>Flux.Optimise.Momentum</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Momentum(params, η = 0.01; ρ = 0.9)</code></pre><p>Gradient descent with learning rate <code>η</code> and momentum <code>ρ</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/optimise/optimisers.jl#L25-L29">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.Nesterov" href="#Flux.Optimise.Nesterov"><code>Flux.Optimise.Nesterov</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">Nesterov(eta, ρ = 0.9)</code></pre><p>Gradient descent with learning rate <code>η</code> and Nesterov momentum <code>ρ</code>.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/optimise/optimisers.jl#L45-L49">source</a></section><section class="docstring"><div class="docstring-header"><a class="docstring-binding" id="Flux.Optimise.ADAM" href="#Flux.Optimise.ADAM"><code>Flux.Optimise.ADAM</code></a> — <span class="docstring-category">Type</span>.</div><div><div><pre><code class="language-none">ADAM(η = 0.001, β = (0.9, 0.999))</code></pre><p><a href="https://arxiv.org/abs/1412.6980v8">ADAM</a> optimiser.</p></div></div><a class="source-link" target="_blank" href="https://github.com/FluxML/Flux.jl/blob/ab46da11c7344d8ed38ab66aeb74e690e25c1a76/src/optimise/optimisers.jl#L88-L92">source</a></section><footer><hr/><a class="previous" href="../../models/layers/"><span class="direction">Previous</span><span class="title">Model Reference</span></a><a class="next" href="../training/"><span class="direction">Next</span><span class="title">Training</span></a></footer></article></body></html>
|
||||
|
Loading…
Reference in New Issue
Block a user