Overhaul layer catalogue documentation.

Create scripts/split_caffe_proto.py file for splitting up the
caffe.proto file, so that parts of the file can be included from the
layer help pages.

Create separate pages for each layer and link each page from layers.md.

docs/tutorial/layers/absval.md

@@ -0,0 +1,22 @@
+---
+title: Absolute Value Layer
+---
+
+# Absolute Value Layer
+
+* Layer type: `AbsVal`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1AbsValLayer.html)
+* Header: [`./include/caffe/layers/absval_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/absval_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/absval_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/absval_layer.cpp)
+* CUDA GPU implementation: [`./src/caffe/layers/absval_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/absval_layer.cu)
+
+* Sample
+
+      layer {
+        name: "layer"
+        bottom: "in"
+        top: "out"
+        type: "AbsVal"
+      }
+
+The `AbsVal` layer computes the output as abs(x) for each input element x.

docs/tutorial/layers/accuracy.md

@@ -0,0 +1,21 @@
+---
+title: Accuracy and Top-k
+---
+
+# Accuracy and Top-k
+
+`Accuracy` scores the output as the accuracy of output with respect to target -- it is not actually a loss and has no backward step.
+
+* Layer type: `Accuracy`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1AccuracyLayer.html)
+* Header: [`./include/caffe/layers/accuracy_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/accuracy_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/accuracy_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/accuracy_layer.cpp)
+* CUDA GPU implementation: [`./src/caffe/layers/accuracy_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/accuracy_layer.cu)
+
+## Parameters
+* Parameters (`AccuracyParameter accuracy_param`)
+* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
+
+{% highlight Protobuf %}
+{% include proto/AccuracyParameter.txt %}
+{% endhighlight %}

docs/tutorial/layers/argmax.md

@@ -0,0 +1,19 @@
+---
+title: ArgMax Layer
+---
+
+# ArgMax Layer
+
+* Layer type: `ArgMax`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1ArgMaxLayer.html)
+* Header: [`./include/caffe/layers/argmax_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/argmax_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/argmax_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/argmax_layer.cpp)
+* CUDA GPU implementation: [`./src/caffe/layers/argmax_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/argmax_layer.cu)
+
+## Parameters
+* Parameters (`ArgMaxParameter argmax_param`)
+* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
+
+{% highlight Protobuf %}
+{% include proto/ArgMaxParameter.txt %}
+{% endhighlight %}

docs/tutorial/layers/batchnorm.md

@@ -0,0 +1,20 @@
+---
+title: Batch Norm Layer
+---
+
+# Batch Norm Layer
+
+* Layer type: `BatchNorm`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1BatchNormLayer.html)
+* Header: [`./include/caffe/layers/batch_norm_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/batch_norm_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/batch_norm_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/batch_norm_layer.cpp)
+* CUDA GPU implementation: [`./src/caffe/layers/batch_norm_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/batch_norm_layer.cu)
+
+## Parameters
+
+* Parameters (`BatchNormParameter batch_norm_param`)
+* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto):
+
+{% highlight Protobuf %}
+{% include proto/BatchNormParameter.txt %}
+{% endhighlight %}

docs/tutorial/layers/batchreindex.md

@@ -0,0 +1,16 @@
+---
+title: Batch Reindex Layer
+---
+
+# Batch Reindex Layer
+
+* Layer type: `BatchReindex`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1BatchReindexLayer.html)
+* Header: [`./include/caffe/layers/batch_reindex_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/batch_reindex_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/batch_reindex_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/batch_reindex_layer.cpp)
+* CUDA GPU implementation: [`./src/caffe/layers/batch_reindex_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/batch_reindex_layer.cu)
+
+
+## Parameters
+
+No parameters.

docs/tutorial/layers/bias.md

@@ -0,0 +1,19 @@
+---
+title: Bias Layer
+---
+
+# Bias Layer
+
+* Layer type: `Bias`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1BiasLayer.html)
+* Header: [`./include/caffe/layers/bias_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/bias_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/bias_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/bias_layer.cpp)
+* CUDA GPU implementation: [`./src/caffe/layers/bias_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/bias_layer.cu)
+
+## Parameters
+* Parameters (`BiasParameter bias_param`)
+* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
+
+{% highlight Protobuf %}
+{% include proto/BiasParameter.txt %}
+{% endhighlight %}

docs/tutorial/layers/bnll.md

@@ -0,0 +1,25 @@
+---
+title: BNLL Layer
+---
+
+# BNLL Layer
+
+* Layer type: `BNLL`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1BNLLLayer.html)
+* Header: [`./include/caffe/layers/bnll_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/bnll_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/bnll_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/bnll_layer.cpp)
+* CUDA GPU implementation: [`./src/caffe/layers/bnll_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/bnll_layer.cu)
+
+The `BNLL` (binomial normal log likelihood) layer computes the output as log(1 + exp(x)) for each input element x.
+
+## Parameters
+No parameters.
+
+## Sample
+
+      layer {
+        name: "layer"
+        bottom: "in"
+        top: "out"
+        type: BNLL
+      }

docs/tutorial/layers/concat.md

@@ -0,0 +1,40 @@
+---
+title: Concat Layer
+---
+
+# Concat Layer
+
+* Layer type: `Concat`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1ConcatLayer.html)
+* Header: [`./include/caffe/layers/concat_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/concat_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/concat_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/concat_layer.cpp)
+* CUDA GPU implementation: [`./src/caffe/layers/concat_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/concat_layer.cu)
+* Input
+    - `n_i * c_i * h * w` for each input blob i from 1 to K.
+* Output
+    - if `axis = 0`: `(n_1 + n_2 + ... + n_K) * c_1 * h * w`, and all input `c_i` should be the same.
+    - if `axis = 1`: `n_1 * (c_1 + c_2 + ... + c_K) * h * w`, and all input `n_i` should be the same.
+* Sample
+
+      layer {
+        name: "concat"
+        bottom: "in1"
+        bottom: "in2"
+        top: "out"
+        type: "Concat"
+        concat_param {
+          axis: 1
+        }
+      }
+
+The `Concat` layer is a utility layer that concatenates its multiple input blobs to one single output blob.
+
+## Parameters
+* Parameters (`ConcatParameter concat_param`)
+    - Optional
+        - `axis` [default 1]: 0 for concatenation along num and 1 for channels.
+* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
+
+{% highlight Protobuf %}
+{% include proto/ConcatParameter.txt %}
+{% endhighlight %}

docs/tutorial/layers/contrastiveloss.md

@@ -0,0 +1,20 @@
+---
+title: Contrastive Loss Layer
+---
+
+# Contrastive Loss Layer
+
+* Layer type: `ContrastiveLoss`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1ContrastiveLossLayer.html)
+* Header: [`./include/caffe/layers/contrastive_loss_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/contrastive_loss_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/contrastive_loss_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/contrastive_loss_layer.cpp)
+* CUDA GPU implementation: [`./src/caffe/layers/contrastive_loss_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/contrastive_loss_layer.cu)
+
+## Parameters
+
+* Parameters (`ContrastiveLossParameter contrastive_loss_param`)
+* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
+
+{% highlight Protobuf %}
+{% include proto/ContrastiveLossParameter.txt %}
+{% endhighlight %}

docs/tutorial/layers/convolution.md

@@ -0,0 +1,63 @@
+---
+title: Convolution Layer
+---
+
+# Convolution Layer
+
+* Layer type: `Convolution`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1ConvolutionLayer.html)
+* Header: [`./include/caffe/layers/conv_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/conv_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/conv_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/conv_layer.cpp)
+* CUDA GPU implementation: [`./src/caffe/layers/conv_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/conv_layer.cu)
+* Input
+    - `n * c_i * h_i * w_i`
+* Output
+    - `n * c_o * h_o * w_o`, where `h_o = (h_i + 2 * pad_h - kernel_h) / stride_h + 1` and `w_o` likewise.
+
+The `Convolution` layer convolves the input image with a set of learnable filters, each producing one feature map in the output image.
+
+## Sample
+
+Sample (as seen in [`./models/bvlc_reference_caffenet/train_val.prototxt`](https://github.com/BVLC/caffe/blob/master/models/bvlc_reference_caffenet/train_val.prototxt)):
+
+      layer {
+        name: "conv1"
+        type: "Convolution"
+        bottom: "data"
+        top: "conv1"
+        # learning rate and decay multipliers for the filters
+        param { lr_mult: 1 decay_mult: 1 }
+        # learning rate and decay multipliers for the biases
+        param { lr_mult: 2 decay_mult: 0 }
+        convolution_param {
+          num_output: 96     # learn 96 filters
+          kernel_size: 11    # each filter is 11x11
+          stride: 4          # step 4 pixels between each filter application
+          weight_filler {
+            type: "gaussian" # initialize the filters from a Gaussian
+            std: 0.01        # distribution with stdev 0.01 (default mean: 0)
+          }
+          bias_filler {
+            type: "constant" # initialize the biases to zero (0)
+            value: 0
+          }
+        }
+      }
+
+## Parameters
+* Parameters (`ConvolutionParameter convolution_param`)
+    - Required
+        - `num_output` (`c_o`): the number of filters
+        - `kernel_size` (or `kernel_h` and `kernel_w`): specifies height and width of each filter
+    - Strongly Recommended
+        - `weight_filler` [default `type: 'constant' value: 0`]
+    - Optional
+        - `bias_term` [default `true`]: specifies whether to learn and apply a set of additive biases to the filter outputs
+        - `pad` (or `pad_h` and `pad_w`) [default 0]: specifies the number of pixels to (implicitly) add to each side of the input
+        - `stride` (or `stride_h` and `stride_w`) [default 1]: specifies the intervals at which to apply the filters to the input
+        - `group` (g) [default 1]: If g > 1, we restrict the connectivity of each filter to a subset of the input. Specifically, the input and output channels are separated into g groups, and the $$i$$th output group channels will be only connected to the $$i$$th input group channels.
+* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
+
+{% highlight Protobuf %}
+{% include proto/ConvolutionParameter.txt %}
+{% endhighlight %}

docs/tutorial/layers/crop.md

@@ -0,0 +1,20 @@
+---
+title: Crop Layer
+---
+
+# Crop Layer
+
+* Layer type: `Crop`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1CropLayer.html)
+* Header: [`./include/caffe/layers/crop_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/crop_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/crop_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/crop_layer.cpp)
+* CUDA GPU implementation: [`./src/caffe/layers/crop_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/crop_layer.cu)
+
+## Parameters
+
+* Parameters (`CropParameter crop_param`)
+* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
+
+{% highlight Protobuf %}
+{% include proto/CropParameter.txt %}
+{% endhighlight %}

docs/tutorial/layers/data.md

@@ -0,0 +1,29 @@
+---
+title: Database Layer
+---
+
+# Database Layer
+
+* Layer type: `Data`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1DataLayer.html)
+* Header: [`./include/caffe/layers/data_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/data_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/data_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/data_layer.cpp)
+
+
+## Parameters
+
+* Parameters (`DataParameter data_param`)
+* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
+
+{% highlight Protobuf %}
+{% include proto/DataParameter.txt %}
+{% endhighlight %}
+
+* Parameters
+    - Required
+        - `source`: the name of the directory containing the database
+        - `batch_size`: the number of inputs to process at one time
+    - Optional
+        - `rand_skip`: skip up to this number of inputs at the beginning; useful for asynchronous sgd
+        - `backend` [default `LEVELDB`]: choose whether to use a `LEVELDB` or `LMDB`
+

docs/tutorial/layers/deconvolution.md

@@ -0,0 +1,22 @@
+---
+title: Deconvolution Layer
+---
+
+# Deconvolution Layer
+
+* Layer type: `Deconvolution`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1DeconvolutionLayer.html)
+* Header: [`./include/caffe/layers/deconv_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/deconv_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/deconv_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/deconv_layer.cpp)
+* CUDA GPU implementation: [`./src/caffe/layers/deconv_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/deconv_layer.cu)
+
+## Parameters
+
+Uses the same parameters as the Convolution layer.
+
+* Parameters (`ConvolutionParameter convolution_param`)
+* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
+
+{% highlight Protobuf %}
+{% include proto/ConvolutionParameter.txt %}
+{% endhighlight %}

docs/tutorial/layers/dropout.md

@@ -0,0 +1,20 @@
+---
+title: Dropout Layer
+---
+
+# Dropout Layer
+
+* Layer type: `Dropout`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1DropoutLayer.html)
+* Header: [`./include/caffe/layers/dropout_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/dropout_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/dropout_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/dropout_layer.cpp)
+* CUDA GPU implementation: [`./src/caffe/layers/dropout_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/dropout_layer.cu)
+
+## Parameters
+
+* Parameters (`DropoutParameter dropout_param`)
+* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
+
+{% highlight Protobuf %}
+{% include proto/DropoutParameter.txt %}
+{% endhighlight %}

docs/tutorial/layers/dummydata.md

@@ -0,0 +1,20 @@
+---
+title: Dummy Data Layer
+---
+
+# Dummy Data Layer
+
+* Layer type: `DummyData`
+* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1DummyDataLayer.html)
+* Header: [`./include/caffe/layers/dummy_data_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/dummy_data_layer.hpp)
+* CPU implementation: [`./src/caffe/layers/dummy_data_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/dummy_data_layer.cpp)
+
+
+## Parameters
+
+* Parameters (`DummyDataParameter dummy_data_param`)
+* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
+
+{% highlight Protobuf %}
+{% include proto/DummyDataParameter.txt %}
+{% endhighlight %}