Skip to content

D
dlib
Commit b4b9376a authored by Davis King's avatar Davis King
Browse files
Options

updated docs

parent f698b85d
Hide whitespace changes
Inline Side-by-side
Showing with 497 additions and 17 deletions
docs/docs/index.xml
View file @ b4b9376a
......@@ -65,6 +65,7 @@
</li>
<li><b>Machine Learning Algorithms</b>
<ul>
<li><a href="ml.html#add_layer">Deep Learning</a></li>
<li>Conventional SMO based Support Vector Machines for <a href="ml.html#svm_nu_trainer">classification</a>
and <a href="ml.html#svr_trainer">regression</a> </li>
<li>Reduced-rank methods for large-scale <a href="ml.html#svm_c_ekm_trainer">classification</a>
......
docs/docs/main_menu.xml
View file @ b4b9376a
......@@ -186,6 +186,18 @@
<item nolink="true">
<name>Examples: C++</name>
<sub>
<item>
<name>Deep Learning</name>
<link>dnn_mnist_ex.cpp.html</link>
</item>
<item>
<name>Deep Learning Advanced</name>
<link>dnn_mnist_advanced_ex.cpp.html</link>
</item>
<item>
<name>Deep Learning Inception</name>
<link>dnn_inception_ex.cpp.html</link>
</item>
<item>
<name>Linear Model Predictive Control</name>
<link>mpc_ex.cpp.html</link>
......
docs/docs/ml.xml
View file @ b4b9376a
......@@ -9,22 +9,16 @@
<body>
<a href="ml_guide.svg"><img src="ml_guide.svg" width="100%"/></a>
<p>
A major design goal of this portion of the library is to provide a highly modular and
simple architecture for dealing with kernel algorithms. Towards this end, dlib takes a generic
programming approach using C++ templates. In particular, each algorithm is parameterized
to allow a user to supply either one of the predefined dlib kernels (e.g. <a
href="#radial_basis_kernel">RBF</a> operating
on <a href="linear_algebra.html#matrix">column vectors</a>), or a new
<a href="using_custom_kernels_ex.cpp.html">user defined kernel</a>.
Moreover, the implementations of the algorithms are totally separated from the data on
which they operate. This makes the dlib implementation generic enough to operate on
any kind of data, be it column vectors, images, or some other form of structured data.
All that is necessary is an appropriate kernel.
</p>
<h3>Paper Describing dlib Machine Learning</h3>
<br/>
<br/>
<p><font style='font-size:1.4em;line-height:1.1em'>
Dlib contains a wide range of machine learning algorithms. All
designed to be highly modular, quick to execute, and simple to use
via a clean and modern C++ API. It is used in a wide range of
applications including robotics, embedded devices, mobile phones, and large
high performance computing environments. If you use dlib in your
research please cite:
</font></p>
<pre>
Davis E. King. <a href="http://jmlr.csail.mit.edu/papers/volume10/king09a/king09a.pdf">Dlib-ml: A Machine Learning Toolkit</a>.
<i>Journal of Machine Learning Research</i>, 2009
......@@ -105,6 +99,147 @@ Davis E. King. <a href="http://jmlr.csail.mit.edu/papers/volume10/king09a/king09
<item>svm_rank_trainer</item>
<item>shape_predictor_trainer</item>
</section>
<section>
<name>Deep Learning</name>
<item nolink="true">
<name>Core Tools</name>
<sub>
<item>add_layer</item>
<item>add_loss_layer</item>
<item>repeat</item>
<item>add_tag_layer</item>
<item>add_skip_layer</item>
<item>layer</item>
<item>test_layer</item>
<item>resizable_tensor</item>
<item>alias_tensor</item>
</sub>
</item>
<item nolink="true">
<name>Input Layers</name>
<sub>
<item>input</item>
<item>input_rgb_image</item>
<item>
<name>EXAMPLE_INPUT_LAYER</name>
<link>dlib/dnn/input_abstract.h.html#EXAMPLE_INPUT_LAYER</link>
</item>
</sub>
</item>
<item nolink="true">
<name>Computational Layers</name>
<sub>
<item>
<name>EXAMPLE_COMPUTATIONAL_LAYER</name>
<link>dlib/dnn/layers_abstract.h.html#EXAMPLE_COMPUTATIONAL_LAYER_</link>
</item>
<item>
<name>fc</name>
<link>dlib/dnn/layers_abstract.h.html#fc_</link>
</item>
<item>
<name>con</name>
<link>dlib/dnn/layers_abstract.h.html#con_</link>
</item>
<item>
<name>dropout</name>
<link>dlib/dnn/layers_abstract.h.html#dropout_</link>
</item>
<item>
<name>multiply</name>
<link>dlib/dnn/layers_abstract.h.html#multiply_</link>
</item>
<item>
<name>bn</name>
<link>dlib/dnn/layers_abstract.h.html#bn_</link>
</item>
<item>
<name>affine</name>
<link>dlib/dnn/layers_abstract.h.html#affine_</link>
</item>
<item>
<name>max_pool</name>
<link>dlib/dnn/layers_abstract.h.html#max_pool_</link>
</item>
<item>
<name>avg_pool</name>
<link>dlib/dnn/layers_abstract.h.html#avg_pool_</link>
</item>
<item>
<name>relu</name>
<link>dlib/dnn/layers_abstract.h.html#relu_</link>
</item>
<item>
<name>concat</name>
<link>dlib/dnn/layers_abstract.h.html#concat_</link>
</item>
<item>
<name>prelu</name>
<link>dlib/dnn/layers_abstract.h.html#prelu_</link>
</item>
<item>
<name>sig</name>
<link>dlib/dnn/layers_abstract.h.html#sig_</link>
</item>
<item>
<name>htan</name>
<link>dlib/dnn/layers_abstract.h.html#htan_</link>
</item>
<item>
<name>softmax</name>
<link>dlib/dnn/layers_abstract.h.html#softmax_</link>
</item>
<item>
<name>add_prev</name>
<link>dlib/dnn/layers_abstract.h.html#add_prev_</link>
</item>
<item>
<name>inception</name>
<link>dlib/dnn/layers_abstract.h.html#inception</link>
</item>
</sub>
</item>
<item nolink="true">
<name>Loss Layers</name>
<sub>
<item>
<name>EXAMPLE_LOSS_LAYER</name>
<link>dlib/dnn/loss_abstract.h.html#EXAMPLE_LOSS_LAYER_</link>
</item>
<item>
<name>loss_binary_hinge</name>
<link>dlib/dnn/loss_abstract.h.html#loss_binary_hinge_</link>
</item>
<item>
<name>loss_binary_log</name>
<link>dlib/dnn/loss_abstract.h.html#loss_binary_log_</link>
</item>
<item>
<name>loss_multiclass_log</name>
<link>dlib/dnn/loss_abstract.h.html#loss_multiclass_log_</link>
</item>
</sub>
</item>
<item nolink="true">
<name>Solvers</name>
<sub>
<item>
<name>EXAMPLE_SOLVER</name>
<link>dlib/dnn/solvers_abstract.h.html#EXAMPLE_SOLVER</link>
</item>
<item>
<name>sgd</name>
<link>dlib/dnn/solvers_abstract.h.html#sgd</link>
</item>
<item>
<name>adam</name>
<link>dlib/dnn/solvers_abstract.h.html#adam</link>
</item>
</sub>
</item>
</section>
<section>
<name>Clustering</name>
<item>pick_initial_centers</item>
......@@ -273,6 +408,233 @@ Davis E. King. <a href="http://jmlr.csail.mit.edu/papers/volume10/king09a/king09
<components>
<!-- ************************************************************************* -->
<component cpp11="true">
<name>add_layer</name>
<file>dlib/dnn.h</file>
<spec_file link="true">dlib/dnn/core_abstract.h</spec_file>
<description>
In dlib, a deep neural network is composed of 3 main parts. An
<a href="dlib/dnn/input_abstract.h.html#EXAMPLE_INPUT_LAYER">input layer</a>, a bunch of
<a href="dlib/dnn/layers_abstract.h.html#EXAMPLE_COMPUTATIONAL_LAYER_">computational layers</a>,
and optionally a
<a href="dlib/dnn/loss_abstract.h.html#EXAMPLE_LOSS_LAYER_">loss layer</a>. The add_layer
class is the central object which adds a computational layer onto an
input layer or an entire network. Therefore, deep neural networks are created
by stacking many layers on top of each other using the add_layer class.
<p>
For a tutorial showing how this is accomplished see
<a href="dnn_mnist_ex.cpp.html">this MNIST example</a>.
</p>
</description>
<examples>
<example>dnn_mnist_ex.cpp.html</example>
<example>dnn_mnist_advanced_ex.cpp.html</example>
<example>dnn_inception_ex.cpp.html</example>
</examples>
</component>
<!-- ************************************************************************* -->
<component cpp11="true">
<name>add_loss_layer</name>
<file>dlib/dnn.h</file>
<spec_file link="true">dlib/dnn/core_abstract.h</spec_file>
<description>
This object is a tool for stacking a <a href="dlib/dnn/loss_abstract.h.html#EXAMPLE_LOSS_LAYER_">loss layer</a>
on the top of a deep neural network.
</description>
<examples>
<example>dnn_mnist_ex.cpp.html</example>
<example>dnn_mnist_advanced_ex.cpp.html</example>
<example>dnn_inception_ex.cpp.html</example>
</examples>
</component>
<!-- ************************************************************************* -->
<component cpp11="true">
<name>repeat</name>
<file>dlib/dnn.h</file>
<spec_file link="true">dlib/dnn/core_abstract.h</spec_file>
<description>
This object adds N copies of a computational layer onto a deep neural network.
It is essentially the same as using <a href="#add_layer">add_layer</a> N times,
except that it involves less typing, and for large N, will compile much faster.
</description>
<examples>
<example>dnn_mnist_advanced_ex.cpp.html</example>
</examples>
</component>
<!-- ************************************************************************* -->
<component cpp11="true">
<name>add_tag_layer</name>
<file>dlib/dnn.h</file>
<spec_file link="true">dlib/dnn/core_abstract.h</spec_file>
<description>
This object is a tool for tagging layers in a deep neural network. These tags make it
easy to refer to the tagged layer in other parts of your code.
Specifically, this object adds a new layer onto a deep neural network.
However, this layer simply performs the identity transform.
This means it is a no-op and its presence does not change the
behavior of the network. It exists solely to be used by <a
href="#add_skip_layer">add_skip_layer</a> or <a href="#layer">layer()</a> to reference a
particular part of a network.
<p>
For a tutorial showing how to use tagging see the
<a href="dnn_mnist_advanced_ex.cpp.html">dnn_mnist_advanced_ex.cpp</a>
example program.
</p>
</description>
<examples>
<example>dnn_mnist_advanced_ex.cpp.html</example>
</examples>
</component>
<!-- ************************************************************************* -->
<component cpp11="true">
<name>add_skip_layer</name>
<file>dlib/dnn.h</file>
<spec_file link="true">dlib/dnn/core_abstract.h</spec_file>
<description>
This object adds a new layer to a deep neural network which draws its input
from a <a href="#add_tag_layer">tagged layer</a> rather than from
the immediate predecessor layer as is normally done.
<p>
For a tutorial showing how to use tagging see the
<a href="dnn_mnist_advanced_ex.cpp.html">dnn_mnist_advanced_ex.cpp</a>
example program.
</p>
</description>
</component>
<!-- ************************************************************************* -->
<component cpp11="true">
<name>layer</name>
<file>dlib/dnn.h</file>
<spec_file link="true">dlib/dnn/core_abstract.h</spec_file>
<description>
This global function references a <a href="#add_tag_layer">tagged layer</a>
inside a deep neural network object.
<p>
For a tutorial showing how to use tagging see the
<a href="dnn_mnist_advanced_ex.cpp.html">dnn_mnist_advanced_ex.cpp</a>
example program.
</p>
</description>
<examples>
<example>dnn_mnist_advanced_ex.cpp.html</example>
</examples>
</component>
<!-- ************************************************************************* -->
<component cpp11="true">
<name>input</name>
<file>dlib/dnn.h</file>
<spec_file link="true">dlib/dnn/input_abstract.h</spec_file>
<description>
This is a simple input layer type for use in a deep neural network which
takes some kind of image as input and loads it into a network.
</description>
<examples>
<example>dnn_mnist_ex.cpp.html</example>
<example>dnn_mnist_advanced_ex.cpp.html</example>
<example>dnn_inception_ex.cpp.html</example>
</examples>
</component>
<!-- ************************************************************************* -->
<component cpp11="true">
<name>input_rgb_image</name>
<file>dlib/dnn.h</file>
<spec_file link="true">dlib/dnn/input_abstract.h</spec_file>
<description>
This is a simple input layer type for use in a deep neural network
which takes an RGB image as input and loads it into a network. It
is very similar to the <a href="#input">input layer</a> except that
it allows you to subtract the average color value from each color
channel when converting an image to a tensor.
</description>
</component>
<!-- ************************************************************************* -->
<component cpp11="true">
<name>test_layer</name>
<file>dlib/dnn.h</file>
<spec_file link="true">dlib/dnn/core_abstract.h</spec_file>
<description>
This is a function which tests if a layer object correctly implements
the <a href="dlib/dnn/layers_abstract.h.html#EXAMPLE_COMPUTATIONAL_LAYER_">documented contract</a>
for a computational layer in a deep neural network.
</description>
</component>
<!-- ************************************************************************* -->
<component cpp11="true">
<name>resizable_tensor</name>
<file>dlib/dnn.h</file>
<spec_file link="true">dlib/dnn/tensor_abstract.h</spec_file>
<description>
This object represents a 4D array of float values, all stored contiguously
in memory. Importantly, it keeps two copies of the floats, one on the host
CPU side and another on the GPU device side. It automatically performs the
necessary host/device transfers to keep these two copies of the data in
sync.
<p>
All transfers to the device happen asynchronously with respect to the
default CUDA stream so that CUDA kernel computations can overlap with data
transfers. However, any transfers from the device to the host happen
synchronously in the default CUDA stream. Therefore, you should perform
all your CUDA kernel launches on the default stream so that transfers back
to the host do not happen before the relevant computations have completed.
</p>
<p>
If DLIB_USE_CUDA is not #defined then this object will not use CUDA at all.
Instead, it will simply store one host side memory block of floats.
</p>
<p>
Finally, the convention in dlib code is to interpret the tensor as a set of
num_samples() 3D arrays, each of dimension k() by nr() by nc(). Also,
while this class does not specify a memory layout, the convention is to
assume that indexing into an element at coordinates (sample,k,nr,nc) can be
accomplished via:
<tt>host()[((sample*t.k() + k)*t.nr() + nr)*t.nc() + nc]</tt>
</p>
</description>
</component>
<!-- ************************************************************************* -->
<component cpp11="true">
<name>alias_tensor</name>
<file>dlib/dnn.h</file>
<spec_file link="true">dlib/dnn/tensor_abstract.h</spec_file>
<description>
This object is a <a href="#resizable_tensor">tensor</a> that
aliases another tensor. That is, it doesn't have its own block of
memory but instead simply holds pointers to the memory of another
tensor object. It therefore allows you to efficiently break a tensor
into pieces and pass those pieces into functions.
</description>
</component>
<!-- ************************************************************************* -->
<component>
......
docs/docs/term_index.xml
View file @ b4b9376a
......@@ -34,8 +34,112 @@
<term file="dlib/algs.h.html" name="stack_based_memory_block" include="dlib/algs.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="log1pexp" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="tuple_head" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="tuple_tail" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="get_learning_rate_multiplier" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="get_weight_decay_multiplier" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="randomize_parameters" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="sstack" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="make_sstack" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="repeat_group" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="add_layer" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="add_loss_layer" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="repeat_group" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="repeat" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="add_tag_layer" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="tag1" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="tag2" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="tag3" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="tag4" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="tag5" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="tag6" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="tag7" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="tag8" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="tag9" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="tag10" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="add_skip_layer" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="skip1" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="skip2" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="skip3" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="skip4" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="skip5" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="skip6" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="skip7" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="skip8" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="skip9" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="skip10" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="layer" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="visit_layer_parameters" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="visit_layer_parameter_gradients" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="test_layer" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="layer_test_results" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="dnn_prefer_fastest_algorithms" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="set_dnn_prefer_fastest_algorithms" include="dlib/dnn.h"/>
<term file="dlib/dnn/core_abstract.h.html" name="set_dnn_prefer_smallest_algorithms" include="dlib/dnn.h"/>
<term file="dlib/dnn/cuda_errors.h.html" name="cuda_error" include="dlib/dnn.h"/>
<term file="dlib/dnn/cuda_errors.h.html" name="cudnn_error" include="dlib/dnn.h"/>
<term file="dlib/dnn/cuda_errors.h.html" name="curand_error" include="dlib/dnn.h"/>
<term file="dlib/dnn/cuda_errors.h.html" name="cublas_error" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="fc_bias_mode" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="FC_HAS_BIAS" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="FC_NO_BIAS" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="layer_mode" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="CONV_MODE" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="FC_MODE" include="dlib/dnn.h"/>
<term file="dlib/dnn/tensor_abstract.h.html" name="tensor" include="dlib/dnn.h"/>
<term file="dlib/dnn/tensor_abstract.h.html" name="resizable_tensor" include="dlib/dnn.h"/>
<term file="dlib/dnn/tensor_abstract.h.html" name="alias_tensor_instance" include="dlib/dnn.h"/>
<term file="dlib/dnn/tensor_abstract.h.html" name="alias_tensor" include="dlib/dnn.h"/>
<term file="dlib/dnn/tensor_abstract.h.html" name="image_plane" include="dlib/dnn.h"/>
<term file="dlib/dnn/tensor_abstract.h.html" name="have_same_dimensions" include="dlib/dnn.h"/>
<term file="dlib/dnn/gpu_data_abstract.h.html" name="gpu_data" include="dlib/dnn.h"/>
<term name="memcpy">
<term link="dlib/dnn/tensor_abstract.h.html#memcpy" name="for tensors" include="dlib/dnn.h" />
<term link="dlib/dnn/gpu_data_abstract.h.html#memcpy" name="for gpu_data" include="dlib/dnn.h" />
</term>
<term file="linear_algebra.html" name="mat" include="dlib/matrix.h" />
<term file="dlib/dnn/input_abstract.h.html" name="EXAMPLE_INPUT_LAYER" include="dlib/dnn.h"/>
<term file="dlib/dnn/input_abstract.h.html" name="input" include="dlib/dnn.h"/>
<term file="dlib/dnn/input_abstract.h.html" name="input_rgb_image" include="dlib/dnn.h"/>
<term file="dlib/dnn/trainer_abstract.h.html" name="dnn_trainer" include="dlib/dnn.h"/>
<term file="dlib/dnn/loss_abstract.h.html" name="EXAMPLE_LOSS_LAYER_" include="dlib/dnn.h"/>
<term file="dlib/dnn/loss_abstract.h.html" name="loss_binary_hinge_" include="dlib/dnn.h"/>
<term file="dlib/dnn/loss_abstract.h.html" name="loss_binary_log_" include="dlib/dnn.h"/>
<term file="dlib/dnn/loss_abstract.h.html" name="loss_multiclass_log_" include="dlib/dnn.h"/>
<term file="dlib/dnn/solvers_abstract.h.html" name="EXAMPLE_SOLVER" include="dlib/dnn.h"/>
<term file="dlib/dnn/solvers_abstract.h.html" name="sgd" include="dlib/dnn.h"/>
<term file="dlib/dnn/solvers_abstract.h.html" name="adam" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="num_fc_outputs" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="EXAMPLE_COMPUTATIONAL_LAYER_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="fc_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="con_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="dropout_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="multiply_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="bn_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="affine_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="max_pool_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="avg_pool_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="relu_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="prelu_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="sig_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="htan_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="softmax_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="add_prev_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="concat_" include="dlib/dnn.h"/>
<term file="dlib/dnn/layers_abstract.h.html" name="inception" include="dlib/dnn.h"/>
<term name="mat">
<term link="linear_algebra.html#mat" name="general use" include="dlib/matrix.h" />
<term link="dlib/dnn/tensor_abstract.h.html#mat" name="for tensors" include="dlib/dnn.h" />
</term>
<term file="linear_algebra.html" name="matrix" include="dlib/matrix.h"/>
<term file="linear_algebra.html" name="move_rect" include="dlib/geometry.h"/>
<term file="linear_algebra.html" name="intersect" include="dlib/geometry.h"/>
......@@ -552,6 +656,7 @@
<term name="dot">
<term link="dlib/matrix/matrix_utilities_abstract.h.html#dot" name="for matrix objects" include="dlib/matrix.h"/>
<term link="dlib/svm/sparse_vector_abstract.h.html#dot" name="for sparse vectors" include="dlib/sparse_vector.h"/>
<term link="dlib/dnn/tensor_abstract.h.html#dot" name="for tensors" include="dlib/dnn.h"/>
</term>
<term file="dlib/matrix/matrix_utilities_abstract.h.html" name="lowerm" include="dlib/matrix.h"/>
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment