如何给20151230版caffe添加新的层 （一）

由于caffe在一步一步的更新，因此半年前的教程可能不适用于当前版的caffe

因此把这次尝试caffe修改过程记录下来，以饷后人。

首先下载caffe
https://github.com/yjxiong/caffe
这个版本的caffe是multi-gpu支持比较好的，用的是MPI技术，用的显存又少，而且在第一时间段支持了cudnn4，follow起来还是很爽的

关于第一阶段最naive的想法是添加类似conv层功能的Layer，主要参考了
http://blog.csdn.net/kuaitoukid/article/details/41865803
同样的，我们将新的layer明明为wtf layer

修改步骤

1.在 include/caffe/vision_layers.hpp 中添加 wtflayer的定义，由于此处不实现GPU函数，因此注释掉了gpu函数

<span class="hljs-keyword">template</span> <<span class="hljs-keyword">typename</span> Dtype>
<span class="hljs-keyword">class</span> WtfLayer : <span class="hljs-keyword">public</span> BaseConvolutionLayer<Dtype> {
<span class="hljs-keyword">public</span>:

<span class="hljs-function"><span class="hljs-keyword">explicit</span> <span class="hljs-title">WtfLayer</span><span class="hljs-params">(<span class="hljs-keyword">const</span> LayerParameter& param)</span>
: BaseConvolutionLayer<Dtype><span class="hljs-params">(param)</span> </span>{}

<span class="hljs-keyword">virtual</span> <span class="hljs-keyword">inline</span> <span class="hljs-keyword">const</span> <span class="hljs-keyword">char</span>* type() <span class="hljs-keyword">const</span> { <span class="hljs-keyword">return</span> <span class="hljs-string">"Wtf"</span>; }

<span class="hljs-keyword">protected</span>:
<span class="hljs-function"><span class="hljs-keyword">virtual</span> <span class="hljs-keyword">void</span> <span class="hljs-title">Forward_cpu</span><span class="hljs-params">(<span class="hljs-keyword">const</span> <span class="hljs-built_in">vector</span><Blob<Dtype>*>& bottom,
<span class="hljs-keyword">const</span> <span class="hljs-built_in">vector</span><Blob<Dtype>*>& top)</span></span>;
<span class="hljs-comment">//virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,</span>
<span class="hljs-comment">//    const vector<Blob<Dtype>*>& top);</span>
<span class="hljs-function"><span class="hljs-keyword">virtual</span> <span class="hljs-keyword">void</span> <span class="hljs-title">Backward_cpu</span><span class="hljs-params">(<span class="hljs-keyword">const</span> <span class="hljs-built_in">vector</span><Blob<Dtype>*>& top,
<span class="hljs-keyword">const</span> <span class="hljs-built_in">vector</span><<span class="hljs-keyword">bool</span>>& propagate_down, <span class="hljs-keyword">const</span> <span class="hljs-built_in">vector</span><Blob<Dtype>*>& bottom)</span></span>;
<span class="hljs-comment">//virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,</span>
<span class="hljs-comment">//    const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);</span>
<span class="hljs-function"><span class="hljs-keyword">virtual</span> <span class="hljs-keyword">inline</span> <span class="hljs-keyword">bool</span> <span class="hljs-title">reverse_dimensions</span><span class="hljs-params">()</span> </span>{ <span class="hljs-keyword">return</span> <span class="hljs-keyword">false</span>; }
<span class="hljs-function"><span class="hljs-keyword">virtual</span> <span class="hljs-keyword">void</span> <span class="hljs-title">compute_output_shape</span><span class="hljs-params">()</span></span>;
};

2.将Wtf_layer.cpp添加到src\caffe\layers文件夹中，代码内容复制convolutio_layer.cpp即可，注意在最后复制的时候添加 REGISTER_LAYER_CLASS(Wtf); 注册一下Wtf Layer

<span class="hljs-preprocessor">#<span class="hljs-keyword">include</span> <vector></span>

<span class="hljs-preprocessor">#<span class="hljs-keyword">include</span> "caffe/filler.hpp"</span>
<span class="hljs-preprocessor">#<span class="hljs-keyword">include</span> "caffe/layer.hpp"</span>
<span class="hljs-preprocessor">#<span class="hljs-keyword">include</span> "caffe/util/im2col.hpp"</span>
<span class="hljs-preprocessor">#<span class="hljs-keyword">include</span> "caffe/util/math_functions.hpp"</span>
<span class="hljs-preprocessor">#<span class="hljs-keyword">include</span> "caffe/vision_layers.hpp"</span>

<span class="hljs-keyword">namespace</span> caffe {

<span class="hljs-keyword">template</span> <<span class="hljs-keyword">typename</span> Dtype>
<span class="hljs-keyword">void</span> WtfLayer<Dtype>::compute_output_shape() {
<span class="hljs-keyword">this</span>->height_out_ = (<span class="hljs-keyword">this</span>->height_ + <span class="hljs-number">2</span> * <span class="hljs-keyword">this</span>->pad_h_ - <span class="hljs-keyword">this</span>->kernel_h_)
/ <span class="hljs-keyword">this</span>->stride_h_ + <span class="hljs-number">1</span>;
<span class="hljs-keyword">this</span>->width_out_ = (<span class="hljs-keyword">this</span>->width_ + <span class="hljs-number">2</span> * <span class="hljs-keyword">this</span>->pad_w_ - <span class="hljs-keyword">this</span>->kernel_w_)
/ <span class="hljs-keyword">this</span>->stride_w_ + <span class="hljs-number">1</span>;
}

<span class="hljs-keyword">template</span> <<span class="hljs-keyword">typename</span> Dtype>
<span class="hljs-keyword">void</span> WtfLayer<Dtype>::Forward_cpu(<span class="hljs-keyword">const</span> <span class="hljs-stl_container"><span class="hljs-built_in">vector</span><Blob<Dtype></span>*>& bottom,
<span class="hljs-keyword">const</span> <span class="hljs-stl_container"><span class="hljs-built_in">vector</span><Blob<Dtype></span>*>& top) {
<span class="hljs-keyword">const</span> Dtype* weight = <span class="hljs-keyword">this</span>->blobs_[<span class="hljs-number">0</span>]->cpu_data();
<span class="hljs-keyword">for</span> (<span class="hljs-keyword">int</span> i = <span class="hljs-number">0</span>; i < bottom.size(); ++i) {
<span class="hljs-keyword">const</span> Dtype* bottom_data = bottom[i]->cpu_data();
Dtype* top_data = top[i]->mutable_cpu_data();
<span class="hljs-keyword">for</span> (<span class="hljs-keyword">int</span> n = <span class="hljs-number">0</span>; n < <span class="hljs-keyword">this</span>->num_; ++n) {
<span class="hljs-keyword">this</span>->forward_cpu_gemm(bottom_data + bottom[i]->offset(n), weight,
top_data + top[i]->offset(n));
<span class="hljs-keyword">if</span> (<span class="hljs-keyword">this</span>->bias_term_) {
<span class="hljs-keyword">const</span> Dtype* bias = <span class="hljs-keyword">this</span>->blobs_[<span class="hljs-number">1</span>]->cpu_data();
<span class="hljs-keyword">this</span>->forward_cpu_bias(top_data + top[i]->offset(n), bias);
}
}
}
}

<span class="hljs-keyword">template</span> <<span class="hljs-keyword">typename</span> Dtype>
<span class="hljs-keyword">void</span> WtfLayer<Dtype>::Backward_cpu(<span class="hljs-keyword">const</span> <span class="hljs-stl_container"><span class="hljs-built_in">vector</span><Blob<Dtype></span>*>& top,
<span class="hljs-keyword">const</span> <span class="hljs-stl_container"><span class="hljs-built_in">vector</span><<span class="hljs-keyword">bool</span>></span>& propagate_down, <span class="hljs-keyword">const</span> <span class="hljs-stl_container"><span class="hljs-built_in">vector</span><Blob<Dtype></span>*>& bottom) {
<span class="hljs-keyword">const</span> Dtype* weight = <span class="hljs-keyword">this</span>->blobs_[<span class="hljs-number">0</span>]->cpu_data();
Dtype* weight_diff = <span class="hljs-keyword">this</span>->blobs_[<span class="hljs-number">0</span>]->mutable_cpu_diff();
<span class="hljs-keyword">for</span> (<span class="hljs-keyword">int</span> i = <span class="hljs-number">0</span>; i < top.size(); ++i) {
<span class="hljs-keyword">const</span> Dtype* top_diff = top[i]->cpu_diff();
<span class="hljs-keyword">const</span> Dtype* bottom_data = bottom[i]->cpu_data();
Dtype* bottom_diff = bottom[i]->mutable_cpu_diff();
<span class="hljs-comment">// Bias gradient, if necessary.</span>
<span class="hljs-keyword">if</span> (<span class="hljs-keyword">this</span>->bias_term_ && <span class="hljs-keyword">this</span>->param_propagate_down_[<span class="hljs-number">1</span>]) {
Dtype* bias_diff = <span class="hljs-keyword">this</span>->blobs_[<span class="hljs-number">1</span>]->mutable_cpu_diff();
<span class="hljs-keyword">for</span> (<span class="hljs-keyword">int</span> n = <span class="hljs-number">0</span>; n < <span class="hljs-keyword">this</span>->num_; ++n) {
<span class="hljs-keyword">this</span>->backward_cpu_bias(bias_diff, top_diff + top[i]->offset(n));
}
}
<span class="hljs-keyword">if</span> (<span class="hljs-keyword">this</span>->param_propagate_down_[<span class="hljs-number">0</span>] || propagate_down[i]) {
<span class="hljs-keyword">for</span> (<span class="hljs-keyword">int</span> n = <span class="hljs-number">0</span>; n < <span class="hljs-keyword">this</span>->num_; ++n) {
<span class="hljs-comment">// gradient w.r.t. weight. Note that we will accumulate diffs.</span>
<span class="hljs-keyword">if</span> (<span class="hljs-keyword">this</span>->param_propagate_down_[<span class="hljs-number">0</span>]) {
<span class="hljs-keyword">this</span>->weight_cpu_gemm(bottom_data + bottom[i]->offset(n),
top_diff + top[i]->offset(n), weight_diff);
}
<span class="hljs-comment">// gradient w.r.t. bottom data, if necessary.</span>
<span class="hljs-keyword">if</span> (propagate_down[i]) {
<span class="hljs-keyword">this</span>->backward_cpu_gemm(top_diff + top[i]->offset(n), weight,
bottom_diff + bottom[i]->offset(n));
}
}
}
}
}

<span class="hljs-preprocessor">#ifdef CPU_ONLY</span>
STUB_GPU(WtfLayer);
<span class="hljs-preprocessor">#<span class="hljs-keyword">endif</span></span>

INSTANTIATE_CLASS(WtfLayer);
REGISTER_LAYER_CLASS(Wtf);

}  <span class="hljs-comment">// namespace caffe</span>

3. 修改proto/caffe.proto文件，找到LayerType，添加WTF，并更新ID。假如说Wtf_Layer有参数，比如Convolution肯定是有参数的，那么添加WtfParameter类

具体添加一下几行

optional WtfParameter wtf_param = <span class="hljs-number">141</span>;

以及

message WtfParameter {
optional uint32 num_output = <span class="hljs-number">1</span>; <span class="hljs-comment">// The number of outputs for the layer</span>
optional <span class="hljs-keyword">bool</span> bias_term = <span class="hljs-number">2</span> [<span class="hljs-keyword">default</span> = <span class="hljs-keyword">true</span>]; <span class="hljs-comment">// whether to have bias terms</span>
<span class="hljs-comment">// Pad, kernel size, and stride are all given as a single value for equal</span>
<span class="hljs-comment">// dimensions in height and width or as Y, X pairs.</span>
optional uint32 pad = <span class="hljs-number">3</span> [<span class="hljs-keyword">default</span> = <span class="hljs-number">0</span>]; <span class="hljs-comment">// The padding size (equal in Y, X)</span>
optional uint32 pad_h = <span class="hljs-number">9</span> [<span class="hljs-keyword">default</span> = <span class="hljs-number">0</span>]; <span class="hljs-comment">// The padding height</span>
optional uint32 pad_w = <span class="hljs-number">10</span> [<span class="hljs-keyword">default</span> = <span class="hljs-number">0</span>]; <span class="hljs-comment">// The padding width</span>
optional uint32 kernel_size = <span class="hljs-number">4</span>; <span class="hljs-comment">// The kernel size (square)</span>
optional uint32 kernel_h = <span class="hljs-number">11</span>; <span class="hljs-comment">// The kernel height</span>
optional uint32 kernel_w = <span class="hljs-number">12</span>; <span class="hljs-comment">// The kernel width</span>
optional uint32 group = <span class="hljs-number">5</span> [<span class="hljs-keyword">default</span> = <span class="hljs-number">1</span>]; <span class="hljs-comment">// The group size for group conv</span>
optional uint32 stride = <span class="hljs-number">6</span> [<span class="hljs-keyword">default</span> = <span class="hljs-number">1</span>]; <span class="hljs-comment">// The stride (equal in Y, X)</span>
optional uint32 stride_h = <span class="hljs-number">13</span>; <span class="hljs-comment">// The stride height</span>
optional uint32 stride_w = <span class="hljs-number">14</span>; <span class="hljs-comment">// The stride width</span>
optional FillerParameter weight_filler = <span class="hljs-number">7</span>; <span class="hljs-comment">// The filler for the weight</span>
optional FillerParameter bias_filler = <span class="hljs-number">8</span>; <span class="hljs-comment">// The filler for the bias</span>
<span class="hljs-keyword">enum</span> Engine {
DEFAULT = <span class="hljs-number">0</span>;
CAFFE = <span class="hljs-number">1</span>;
CUDNN = <span class="hljs-number">2</span>;
}
optional Engine engine = <span class="hljs-number">15</span> [<span class="hljs-keyword">default</span> = DEFAULT];
}

以及

WTF = 52;

以及

optional WtfParameter wtf_param = 53;

接下来编译通过
如何测试我们写的layer的正确性呢？

1.将某些层的type: "Convolution" 转化为type: "Wtf" 测试Wtf的loss情况下降的和Convolution是否一样

2.有了训练好的model和prototxt，用matlab和python接口测试一下是否达到了卷积的效果。

暂时到这里~等待后来继续添加层