caffe中添加自定义的layer

有两种方式，一种是使用python layer相对简单，另一种是使用C++。

1.python layer

参考 http://chrischoy.github.io/research/caffe-python-layer/layer {
type: 'Python'
name: 'loss'
top: 'loss'
bottom: 'ipx'
bottom: 'ipy'
python_param {
# the module name -- usually the filename -- that needs to be in $PYTHONPATH
module: 'pyloss'
# the layer name -- the class name in the module
layer: 'EuclideanLossLayer'
}
# set loss weight so Caffe knows this is a loss layer
loss_weight: 1
}module的名字就是自定义的layer的python文件的文件名，比如上面的新文件就是pyloss.py，文件需在$PYTHONPAT路径下。layer的名字就是新定义的类名，比如上面的类名就是EuclideanLossLayer。该类一般必须包含四个函数，分别是setup、reshape、forword、backword。
下面是示例，解释python层该怎么写。创建pyloss.py，并定义EuclideanLossLayer。import caffe
import numpy as np
class EuclideadLossLayer(caffe.Layer):#EuclideadLossLayer没有权值，反向传播过程中不需要进行权值的更新。如果需要定义需要更新自身权值的层，最好还是使用C++
def setup(self,bottom,top):
#在网络运行之前根据相关参数参数进行layer的初始化
if len(bottom) !=2:
raise exception("Need two inputs to compute distance")
def reshape(self,bottom,top):
#在forward之前调用，根据bottom blob的尺寸调整中间变量和top blob的尺寸
if bottom[0].count !=bottom[1].count:
raise exception("Inputs must have the same dimension.")
self.diff=np.zeros_like(bottom[0].date,dtype=np.float32)
top[0].reshape(1)
def forward(self,bottom,top):
#网络的前向传播
self.diff[...]=bottom[0].data-bottom[1].data
top[0].data[...]=np.sum(self.diff**2)/bottom[0].num/2.
def backward(self,top,propagate_down,bootm):
#网络的前向传播
for i in range(2):
if not propagate_down[i]:
continue
if i==0:
sign=1
else:
sign=-1
bottom[i].diff[...]=sign*self.diff/bottom[i].num

2.C++方式

参考

https://github.com/BVLC/caffe/issues/684 

https://chrischoy.github.io/research/making-caffe-layer/

Here's roughly the process I follow.

Add a class declaration for your layer to the appropriate one of 

common_layers.hpp

, 

data_layers.hpp

,

loss_layers.hpp

, 

neuron_layers.hpp

, or 

vision_layers.hpp

. Include an inline implementation of

type

 and the 

*Blobs()

 methods to specify blob number requirements. Omit the 

*_gpu

 declarations if you'll only be implementing CPU code.
Implement your layer in 

layers/your_layer.cpp

.

SetUp

 for initialization: reading parameters, allocating buffers, etc.

Forward_cpu

 for the function your layer computes

Backward_cpu

 for its gradient

(Optional) Implement the GPU versions 

Forward_gpu

 and 

Backward_gpu

 in 

layers/your_layer.cu

.
Add your layer to 

proto/caffe.proto

, updating the next available ID. Also declare parameters, if needed, in this file.
Make your layer createable by adding it to 

layer_factory.cpp

.
Write tests in 

test/test_your_layer.cpp

. Use 

test/test_gradient_check_util.hpp

 to check that your Forward and Backward implementations are in numerical agreement.