yunmingzhang17 和caffe官网 都有介绍添加层,但是不是很详细,我就简单实现一下这个加层,新手学习,请多多指教。
This is a post outlining the steps you need to take to create your own layer in CAFFE, a popular framework for writing convolutional neural networks. The post focuses on the latest version of CAFE as of Jan 2015.
NOTES:
- I use $CAFFEROOT and /caffe/ interchangeably, this is simply the root directory of the caffe installation.
A general and slightly outdated tutorial can be found here (https://github.com/BVLC/caffe/wiki/Development).
- Create the definition a new class in one of the .hpp files located in $CAFFEROOT/include/caffe/ . In my case, I am writing a customized convolution layer. As a result, I modify thevision_layers.hpp to add a definition of myConvLayer.
- Next we need to create a myConvLayer.cpp file in the following path $CAFFEROOT/src/caffe/myConvLayer.cpp .
- Implement the virtual methods required of the class. In my case, I needed to implement the required “LayerSetUp”, “Reshape”,”ForwardCPU” and “BackwardCPU”.
- Choose a name for your layer and write it in caffe/src/caffe/proto/caffe.proto
- Find a message called LayerParameter
- Find the latest unoccupied number, there should be a comment above the message declaration saying “the next available ID when you create….”, use the smallestUnoccupiedNumber
- Add your layer to the LayerType enum, for example, I add “MYCONVOLUTIONLAYER = 38”
- If you have completed step 1 and step 2, you should be able to just compile the entire CAFFE directory fine. The next steps will require you to actually write a network and run it to get the protobuf set up right. To do this, I recommend simply use an existing network. I chose MNIST LENET and replaced the convolution layer in (/caffe/examples/mnist_modified/lenet_train_test.protxt). To get it to run with my own set up, I
- Created a modified directory(mint_modified) that copies minist in examples.
- Change the lent_solver.prototxt to use my own file. CAFFE used hardcoded path, when it should have used relative path to find the training configuration set up.
- TYPE = MYCONVOLUTION (depending on your declaration in the protobuf file in the previous step)
- Once you are done getting your own layer running within an existing network, it will crash immediately because we haven’t worked on getting
- Dealing with protobuf and layer_factory
- Now you should see an error massage saying “unknown type 38” from a file called “layer_factory.cpp”. You can find the file at caffe/src/caffe/layer_factory.cpp. The error message tells you that currently CAFFE cannot recognize the parameter specified in the protobuf file “myconvolution”. To do this, you simply need to add a new case statement at the end of “layer_factory.cpp” file.
- case LayerParameter_LayerType_MYCONVOLUTION:return new MyConvolutionLayer<Dtype>(param);
- This statement tells the system to use layer_factory to create the class whenever that parameter is being read
- The last part is to make sure that your own layers is using the parameters that you want.
- An interesting note here is that the parameter has no fixed paring. The way it is specified in protobuf file for example, is nesting a parameter type within a layer type. As a result, you can switch the parameters among different layers. That is I could have used the original convolution_parameter inside MyConvolution layer.
- To use my own set of parameter, I went back to caffe/src/caffe/proto/caffe.proto file
- Define a new parameter type
- “myconvolution_param = 42”
- Define a new message class
- MyConvolutionPoolingParameter { optional uint32 num_output =1; …. }
- Then go back to the lenet_train_test.protxt file and set your layer to use the my convolution parameter in myconvolutionpooling layer.
- An example layers { name:’myconv1′ type:MYCONVOLUTION; ….. myconvolution_param { num_output: 20 kernel_size ….}}
- One last step is modifying the $CAFFEROOT/src/caffe/myConvLayer.cpp to use the my convolution_param. You can access the parameters by coding “ConvolutionPoolingParameter convpool_param = this->layer_param_.convolutionpooling_param();”
===============================================================================================================================
先就按照tangwei2014 学习了一下triplet loss。感谢tangwei博主
===============================================================================================================================
【前言】
最近,learning to rank 的思想逐渐被应用到很多领域,比如google用来做人脸识别(faceNet),微软Jingdong Wang 用来做 person-reid 等等。learning to rank中其中重要的一个步骤就是找到一个好的similarity function,而triplet loss是用的非常广泛的一种。
【理解triplet】
![这里写图片描述](https://img-blog.csdn.net/20150707120209693)
如上图所示,triplet是一个三元组,这个三元组是这样构成的:从训练数据集中随机选一个样本,该样本称为Anchor,然后再随机选取一个和Anchor (记为x_a)属于同一类的样本和不同类的样本,这两个样本对应的称为Positive (记为x_p)和Negative (记为x_n),由此构成一个(Anchor,Positive,Negative)三元组。
【理解triplet loss】
有了上面的triplet的概念, triplet loss就好理解了。针对三元组中的每个元素(样本),训练一个参数共享或者不共享的网络,得到三个元素的特征表达,分别记为:
。triplet loss的目的就是通过学习,让x_a和x_p特征表达之间的距离尽可能小,而x_a和x_n的特征表达之间的距离尽可能大,并且要让x_a与x_n之间的距离和x_a与x_p之间的距离之间有一个最小的间隔
。公式化的表示就是:
![这里写图片描述](https://img-blog.csdn.net/20150707122026287)
对应的目标函数也就很清楚了:
这里距离用欧式距离度量,+表示[]内的值大于零的时候,取该值为损失,小于零的时候,损失为零。
由目标函数可以看出:
- 当x_a与x_n之间的距离 < x_a与x_p之间的距离加
时,[]内的值大于零,就会产生损失。 - 当x_a与x_n之间的距离 >= x_a与x_p之间的距离加
时,损失为零。
【triplet loss 梯度推导】
上述目标函数记为L。则当第i个triplet损失大于零的时候,仅就上述公式而言,有:
![这里写图片描述](https://img-blog.csdn.net/20150707124617151)
【算法实现时候的提示】
可以看到,对x_p和x_n特征表达的梯度刚好利用了求损失时候的中间结果,给的启示就是,如果在CNN中实现 triplet loss layer, 如果能够在前向传播中存储着两个中间结果,反向传播的时候就能避免重复计算。这仅仅是算法实现时候的一个Trick。
================================================================================================================
- 1.在~/caffe/src/caffe/proto/caffe.proto中增加triplet loss layer的定义
- 首先在message LayerParameter中追加 optional TripletLossParameter triplet_loss_param = 138;
- 其次添加message TripletLossParameter类:
-
- message TripletLossParameter {
-
- optional float margin = 1 [default = 1.0];
- }
-
- 2.在./include/caffe/loss_layers.hpp中增加triplet loss layer的类的声明
-
-
-
-
- template <typename Dtype>
- class TripletLossLayer : public LossLayer<Dtype> {
- public:
- explicit TripletLossLayer(const LayerParameter& param)
- : LossLayer<Dtype>(param){}
- virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
- const vector<Blob<Dtype>*>& top);
-
- virtual inline int ExactNumBottomBlobs() const { return 4; }
- virtual inline const char* type() const { return "TripletLoss"; }
-
-
-
-
- virtual inline bool AllowForceBackward(const int bottom_index) const {
- return bottom_index != 3;
- }
-
- protected:
- virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
- const vector<Blob<Dtype>*>& top);
- virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,
- const vector<Blob<Dtype>*>& top);
-
- virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
- const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
- virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
- const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
-
- Blob<Dtype> diff_ap_;
- Blob<Dtype> diff_an_;
- Blob<Dtype> diff_pn_;
-
- Blob<Dtype> diff_sq_ap_;
- Blob<Dtype> diff_sq_an_;
-
- Blob<Dtype> dist_sq_ap_;
- Blob<Dtype> dist_sq_an_;
-
- Blob<Dtype> summer_vec_;
- Blob<Dtype> dist_binary_;
- };
-
- 3. 在./src/caffe/layers/目录下新建triplet_loss_layer.cpp,实现类
- 主要实现三个功能:
- LayerSetUp:主要是做一些CHECK工作,然后根据bottom和top对类中的数据成员初始化。
- Forward_cpu:前传,计算loss
- Backward_cpu:反传,计算梯度。
-
-
-
-
-
-
-
-
- #include <algorithm>
- #include <vector>
-
- #include "caffe/layer.hpp"
- #include "caffe/loss_layers.hpp"
- #include "caffe/util/io.hpp"
- #include "caffe/util/math_functions.hpp"
-
- namespace caffe {
-
- template <typename Dtype>
- void TripletLossLayer<Dtype>::LayerSetUp(
- const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
- LossLayer<Dtype>::LayerSetUp(bottom, top);
- CHECK_EQ(bottom[0]->num(), bottom[1]->num());
- CHECK_EQ(bottom[1]->num(), bottom[2]->num());
- CHECK_EQ(bottom[0]->channels(), bottom[1]->channels());
- CHECK_EQ(bottom[1]->channels(), bottom[2]->channels());
- CHECK_EQ(bottom[0]->height(), 1);
- CHECK_EQ(bottom[0]->width(), 1);
- CHECK_EQ(bottom[1]->height(), 1);
- CHECK_EQ(bottom[1]->width(), 1);
- CHECK_EQ(bottom[2]->height(), 1);
- CHECK_EQ(bottom[2]->width(), 1);
-
- CHECK_EQ(bottom[3]->channels(),1);
- CHECK_EQ(bottom[3]->height(), 1);
- CHECK_EQ(bottom[3]->width(), 1);
-
- diff_ap_.Reshape(bottom[0]->num(), bottom[0]->channels(), 1, 1);
- diff_an_.Reshape(bottom[0]->num(), bottom[0]->channels(), 1, 1);
- diff_pn_.Reshape(bottom[0]->num(), bottom[0]->channels(), 1, 1);
-
- diff_sq_ap_.Reshape(bottom[0]->num(), bottom[0]->channels(), 1, 1);
- diff_sq_an_.Reshape(bottom[0]->num(), bottom[0]->channels(), 1, 1);
- dist_sq_ap_.Reshape(bottom[0]->num(), 1, 1, 1);
- dist_sq_an_.Reshape(bottom[0]->num(), 1, 1, 1);
-
- summer_vec_.Reshape(bottom[0]->channels(), 1, 1, 1);
- for (int i = 0; i < bottom[0]->channels(); ++i)
- summer_vec_.mutable_cpu_data()[i] = Dtype(1);
- dist_binary_.Reshape(bottom[0]->num(), 1, 1, 1);
- for (int i = 0; i < bottom[0]->num(); ++i)
- dist_binary_.mutable_cpu_data()[i] = Dtype(1);
- }
-
- template <typename Dtype>
- void TripletLossLayer<Dtype>::Forward_cpu(
- const vector<Blob<Dtype>*>& bottom,
- const vector<Blob<Dtype>*>& top) {
- int count = bottom[0]->count();
- const Dtype* sampleW = bottom[3]->cpu_data();
- caffe_sub(
- count,
- bottom[0]->cpu_data(),
- bottom[1]->cpu_data(),
- diff_ap_.mutable_cpu_data());
- caffe_sub(
- count,
- bottom[0]->cpu_data(),
- bottom[2]->cpu_data(),
- diff_an_.mutable_cpu_data());
- caffe_sub(
- count,
- bottom[1]->cpu_data(),
- bottom[2]->cpu_data(),
- diff_pn_.mutable_cpu_data());
- const int channels = bottom[0]->channels();
- Dtype margin = this->layer_param_.triplet_loss_param().margin();
-
- Dtype loss(0.0);
- for (int i = 0; i < bottom[0]->num(); ++i) {
- dist_sq_ap_.mutable_cpu_data()[i] = caffe_cpu_dot(channels,
- diff_ap_.cpu_data() + (i*channels), diff_ap_.cpu_data() + (i*channels));
- dist_sq_an_.mutable_cpu_data()[i] = caffe_cpu_dot(channels,
- diff_an_.cpu_data() + (i*channels), diff_an_.cpu_data() + (i*channels));
- Dtype mdist = sampleW[i]*std::max(margin + dist_sq_ap_.cpu_data()[i] - dist_sq_an_.cpu_data()[i], Dtype(0.0));
- loss += mdist;
- if(mdist==Dtype(0)){
-
-
- caffe_set(channels, Dtype(0), diff_ap_.mutable_cpu_data() + (i*channels));
- caffe_set(channels, Dtype(0), diff_an_.mutable_cpu_data() + (i*channels));
- caffe_set(channels, Dtype(0), diff_pn_.mutable_cpu_data() + (i*channels));
- }
- }
- loss = loss / static_cast<Dtype>(bottom[0]->num()) / Dtype(2);
- top[0]->mutable_cpu_data()[0] = loss;
- }
-
- template <typename Dtype>
- void TripletLossLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
- const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
-
- const Dtype* sampleW = bottom[3]->cpu_data();
- for (int i = 0; i < 3; ++i) {
- if (propagate_down[i]) {
- const Dtype sign = (i < 2) ? -1 : 1;
- const Dtype alpha = sign * top[0]->cpu_diff()[0] /
- static_cast<Dtype>(bottom[i]->num());
- int num = bottom[i]->num();
- int channels = bottom[i]->channels();
- for (int j = 0; j < num; ++j) {
- Dtype* bout = bottom[i]->mutable_cpu_diff();
- if (i==0) {
-
- caffe_cpu_axpby(
- channels,
- alpha*sampleW[j],
- diff_pn_.cpu_data() + (j*channels),
- Dtype(0.0),
- bout + (j*channels));
-
-
-
- } else if (i==1) {
-
- caffe_cpu_axpby(
- channels,
- alpha*sampleW[j],
- diff_ap_.cpu_data() + (j*channels),
- Dtype(0.0),
- bout + (j*channels));
-
-
-
- } else if (i==2) {
-
- caffe_cpu_axpby(
- channels,
- alpha*sampleW[j],
- diff_an_.cpu_data() + (j*channels),
- Dtype(0.0),
- bout + (j*channels));
-
-
-
- }
- }
- }
- }
- }
-
- #ifdef CPU_ONLY
- STUB_GPU(TripletLossLayer);
- #endif
-
- INSTANTIATE_CLASS(TripletLossLayer);
- REGISTER_LAYER_CLASS(TripletLoss);
-
- }
-
- 4.在./src/caffe/layers/目录下新建triplet_loss_layer.cu,实现GPU下的前传和反传
-
-
-
-
-
-
-
-
- #include <algorithm>
- #include <vector>
-
- #include "caffe/layer.hpp"
- #include "caffe/util/io.hpp"
- #include "caffe/util/math_functions.hpp"
- #include "caffe/vision_layers.hpp"
-
- namespace caffe {
-
- template <typename Dtype>
- void TripletLossLayer<Dtype>::Forward_gpu(
- const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
- const int count = bottom[0]->count();
- caffe_gpu_sub(
- count,
- bottom[0]->gpu_data(),
- bottom[1]->gpu_data(),
- diff_ap_.mutable_gpu_data());
- caffe_gpu_sub(
- count,
- bottom[0]->gpu_data(),
- bottom[2]->gpu_data(),
- diff_an_.mutable_gpu_data());
- caffe_gpu_sub(
- count,
- bottom[1]->gpu_data(),
- bottom[2]->gpu_data(),
- diff_pn_.mutable_gpu_data());
-
- caffe_gpu_powx(
- count,
- diff_ap_.mutable_gpu_data(),
- Dtype(2),
- diff_sq_ap_.mutable_gpu_data());
- caffe_gpu_gemv(
- CblasNoTrans,
- bottom[0]->num(),
- bottom[0]->channels(),
- Dtype(1.0),
- diff_sq_ap_.gpu_data(),
- summer_vec_.gpu_data(),
- Dtype(0.0),
- dist_sq_ap_.mutable_gpu_data());
-
- caffe_gpu_powx(
- count,
- diff_an_.mutable_gpu_data(),
- Dtype(2),
- diff_sq_an_.mutable_gpu_data());
- caffe_gpu_gemv(
- CblasNoTrans,
- bottom[0]->num(),
- bottom[0]->channels(),
- Dtype(1.0),
- diff_sq_an_.gpu_data(),
- summer_vec_.gpu_data(),
- Dtype(0.0),
- dist_sq_an_.mutable_gpu_data());
-
- Dtype margin = this->layer_param_.triplet_loss_param().margin();
- Dtype loss(0.0);
- const Dtype* sampleW = bottom[3]->cpu_data();
- for (int i = 0; i < bottom[0]->num(); ++i) {
- loss += sampleW[i]*std::max(margin +dist_sq_ap_.cpu_data()[i]- dist_sq_an_.cpu_data()[i], Dtype(0.0));
- }
- loss = loss / static_cast<Dtype>(bottom[0]->num()) / Dtype(2);
- top[0]->mutable_cpu_data()[0] = loss;
- }
-
- template <typename Dtype>
- __global__ void CLLBackward(const int count, const int channels,
- const Dtype margin, const Dtype alpha, const Dtype* sampleW,
- const Dtype* diff, const Dtype* dist_sq_ap_, const Dtype* dist_sq_an_,
- Dtype *bottom_diff) {
- CUDA_KERNEL_LOOP(i, count) {
- int n = i / channels;
- Dtype mdist(0.0);
- mdist = margin +dist_sq_ap_[n] - dist_sq_an_[n];
- if (mdist > 0.0) {
- bottom_diff[i] = alpha*sampleW[n]*diff[i];
- } else {
- bottom_diff[i] = 0;
- }
- }
- }
-
- template <typename Dtype>
- void TripletLossLayer<Dtype>::Backward_gpu(const vector<Blob<Dtype>*>& top,
- const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
- Dtype margin = this->layer_param_.triplet_loss_param().margin();
- const int count = bottom[0]->count();
- const int channels = bottom[0]->channels();
-
- for (int i = 0; i < 3; ++i) {
- if (propagate_down[i]) {
- const Dtype sign = (i < 2) ? -1 : 1;
- const Dtype alpha = sign * top[0]->cpu_diff()[0] /
- static_cast<Dtype>(bottom[0]->num());
- if(i==0){
-
- CLLBackward<Dtype><<<CAFFE_GET_BLOCKS(count), CAFFE_CUDA_NUM_THREADS>>>(
- count, channels, margin, alpha,
- bottom[3]->gpu_data(),
- diff_pn_.gpu_data(),
- dist_sq_ap_.gpu_data(),
- dist_sq_an_.gpu_data(),
- bottom[i]->mutable_gpu_diff());
- CUDA_POST_KERNEL_CHECK;
- }else if(i==1){
-
- CLLBackward<Dtype><<<CAFFE_GET_BLOCKS(count), CAFFE_CUDA_NUM_THREADS>>>(
- count, channels, margin, alpha,
- bottom[3]->gpu_data(),
- diff_ap_.gpu_data(),
- dist_sq_ap_.gpu_data(),
- dist_sq_an_.gpu_data(),
- bottom[i]->mutable_gpu_diff());
- CUDA_POST_KERNEL_CHECK;
- }else if(i==2){
-
- CLLBackward<Dtype><<<CAFFE_GET_BLOCKS(count), CAFFE_CUDA_NUM_THREADS>>>(
- count, channels, margin, alpha,
- bottom[3]->gpu_data(),
- diff_an_.gpu_data(),
- dist_sq_ap_.gpu_data(),
- dist_sq_an_.gpu_data(),
- bottom[i]->mutable_gpu_diff());
- CUDA_POST_KERNEL_CHECK;
-
- }
- }
- }
- }
-
- INSTANTIATE_LAYER_GPU_FUNCS(TripletLossLayer);
-
- }
-
- 5. 在./src/caffe/test/目录下增加test_triplet_loss_layer.cpp
-
-
-
-
-
-
-
-
- #include <algorithm>
- #include <cmath>
- #include <cstdlib>
- #include <cstring>
- #include <vector>
-
- #include "gtest/gtest.h"
-
- #include "caffe/blob.hpp"
- #include "caffe/common.hpp"
- #include "caffe/filler.hpp"
- #include "caffe/vision_layers.hpp"
-
- #include "caffe/test/test_caffe_main.hpp"
- #include "caffe/test/test_gradient_check_util.hpp"
-
- namespace caffe {
-
- template <typename TypeParam>
- class TripletLossLayerTest : public MultiDeviceTest<TypeParam> {
- typedef typename TypeParam::Dtype Dtype;
-
- protected:
- TripletLossLayerTest()
- : blob_bottom_data_i_(new Blob<Dtype>(512, 2, 1, 1)),
- blob_bottom_data_j_(new Blob<Dtype>(512, 2, 1, 1)),
- blob_bottom_data_k_(new Blob<Dtype>(512, 2, 1, 1)),
- blob_bottom_y_(new Blob<Dtype>(512, 1, 1, 1)),
- blob_top_loss_(new Blob<Dtype>()) {
-
- FillerParameter filler_param;
- filler_param.set_min(-1.0);
- filler_param.set_max(1.0);
- UniformFiller<Dtype> filler(filler_param);
- filler.Fill(this->blob_bottom_data_i_);
- blob_bottom_vec_.push_back(blob_bottom_data_i_);
- filler.Fill(this->blob_bottom_data_j_);
- blob_bottom_vec_.push_back(blob_bottom_data_j_);
- filler.Fill(this->blob_bottom_data_k_);
- blob_bottom_vec_.push_back(blob_bottom_data_k_);
- for (int i = 0; i < blob_bottom_y_->count(); ++i) {
- blob_bottom_y_->mutable_cpu_data()[i] = caffe_rng_rand() % 2;
- }
- blob_bottom_vec_.push_back(blob_bottom_y_);
- blob_top_vec_.push_back(blob_top_loss_);
- }
- virtual ~TripletLossLayerTest() {
- delete blob_bottom_data_i_;
- delete blob_bottom_data_j_;
- delete blob_bottom_data_k_;
- delete blob_top_loss_;
- }
-
- Blob<Dtype>* const blob_bottom_data_i_;
- Blob<Dtype>* const blob_bottom_data_j_;
- Blob<Dtype>* const blob_bottom_data_k_;
- Blob<Dtype>* const blob_bottom_y_;
- Blob<Dtype>* const blob_top_loss_;
- vector<Blob<Dtype>*> blob_bottom_vec_;
- vector<Blob<Dtype>*> blob_top_vec_;
- };
-
- TYPED_TEST_CASE(TripletLossLayerTest, TestDtypesAndDevices);
-
- TYPED_TEST(TripletLossLayerTest, TestForward) {
- typedef typename TypeParam::Dtype Dtype;
- LayerParameter layer_param;
- TripletLossLayer<Dtype> layer(layer_param);
- layer.SetUp(this->blob_bottom_vec_, this->blob_top_vec_);
- layer.Forward(this->blob_bottom_vec_, this->blob_top_vec_);
-
- const Dtype margin = layer_param.triplet_loss_param().margin();
- const int num = this->blob_bottom_data_i_->num();
- const int channels = this->blob_bottom_data_i_->channels();
- const Dtype *sampleW = this->blob_bottom_y_->cpu_data();
-
- Dtype loss(0);
- for (int i = 0; i < num; ++i) {
- Dtype dist_sq_ij(0);
- Dtype dist_sq_ik(0);
- for (int j = 0; j < channels; ++j) {
- Dtype diff_ij = this->blob_bottom_data_i_->cpu_data()[i*channels+j] -
- this->blob_bottom_data_j_->cpu_data()[i*channels+j];
- dist_sq_ij += diff_ij*diff_ij;
- Dtype diff_ik = this->blob_bottom_data_i_->cpu_data()[i*channels+j] -
- this->blob_bottom_data_k_->cpu_data()[i*channels+j];
- dist_sq_ik += diff_ik*diff_ik;
- }
- loss += sampleW[i]*std::max(Dtype(0.0), margin+dist_sq_ij-dist_sq_ik);
- }
- loss /= static_cast<Dtype>(num) * Dtype(2);
- EXPECT_NEAR(this->blob_top_loss_->cpu_data()[0], loss, 1e-6);
- }
-
- TYPED_TEST(TripletLossLayerTest, TestGradient) {
- typedef typename TypeParam::Dtype Dtype;
- LayerParameter layer_param;
- TripletLossLayer<Dtype> layer(layer_param);
- layer.SetUp(this->blob_bottom_vec_, this->blob_top_vec_);
- GradientChecker<Dtype> checker(1e-2, 1e-2, 1701);
-
- checker.CheckGradientExhaustive(&layer, this->blob_bottom_vec_,
- this->blob_top_vec_, 0);
- checker.CheckGradientExhaustive(&layer, this->blob_bottom_vec_,
- this->blob_top_vec_, 1);
- }
-
- }
-
- 3.编译测试
- 重新 make all 如果出错,检查代码语法错误。
- make test
- make runtest 如果成功,全是绿色的OK 否则会给出红色提示,就得看看是不是实现逻辑上出错了。
==============================================================================================================================
然后是添加PrecisionRecallLosslayer,感谢一位中科院的朋友。
1、首先在caffe.proto文件中添加:
![](https://img-blog.csdn.net/20160325211335254?watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQv/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/Center)
2、然后在所属层loss_layer.hpp中添加定义:
![](https://img-blog.csdn.net/20160325211559538?watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQv/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/Center)
3、然后添加改层~/caffe-add/src/caffe/layers/precision_recall_loss_layer.cpp的实现:
- #include <algorithm>
- #include <cfloat>
- #include <cmath>
- #include <vector>
- #include <opencv2/opencv.hpp>
-
- #include "caffe/layer.hpp"
- #include "caffe/util/io.hpp"
- #include "caffe/util/math_functions.hpp"
- #include "caffe/vision_layers.hpp"
-
- namespace caffe {
-
- template <typename Dtype>
- void PrecisionRecallLossLayer<Dtype>::LayerSetUp(
- const vector<Blob<Dtype>*> &bottom, const vector<Blob<Dtype>*> &top) {
- LossLayer<Dtype>::LayerSetUp(bottom, top);
- }
-
- template <typename Dtype>
- void PrecisionRecallLossLayer<Dtype>::Reshape(
- const vector<Blob<Dtype>*> &bottom,
- const vector<Blob<Dtype>*> &top) {
- LossLayer<Dtype>::Reshape(bottom, top);
- loss_.Reshape(bottom[0]->num(), bottom[0]->channels(),
- bottom[0]->height(), bottom[0]->width());
-
-
- CHECK_EQ(bottom[0]->num(), bottom[1]->num())
- << "The number of num of data and label should be same.";
- CHECK_EQ(bottom[0]->channels(), bottom[1]->channels())
- << "The number of channels of data and label should be same.";
- CHECK_EQ(bottom[0]->height(), bottom[1]->height())
- << "The heights of data and label should be same.";
- CHECK_EQ(bottom[0]->width(), bottom[1]->width())
- << "The width of data and label should be same.";
- }
-
- template <typename Dtype>
- void PrecisionRecallLossLayer<Dtype>::Forward_cpu(
- const vector<Blob<Dtype>*> &bottom, const vector<Blob<Dtype>*> &top) {
- const Dtype *data = bottom[0]->cpu_data();
- const Dtype *label = bottom[1]->cpu_data();
- const int num = bottom[0]->num();
- const int dim = bottom[0]->count() / num;
- const int channels = bottom[0]->channels();
- const int spatial_dim = bottom[0]->height() * bottom[0]->width();
- const int pnum =
- this->layer_param_.precision_recall_loss_param().point_num();
- top[0]->mutable_cpu_data()[0] = 0;
- for (int c = 0; c < channels; ++c) {
- Dtype breakeven = 0.0;
- Dtype prec_diff = 1.0;
- for (int p = 0; p <= pnum; ++p) {
- int true_positive = 0;
- int false_positive = 0;
- int false_negative = 0;
- int true_negative = 0;
- for (int i = 0; i < num; ++i) {
- const Dtype thresh = 1.0 / pnum * p;
- for (int j = 0; j < spatial_dim; ++j) {
- const Dtype data_value = data[i * dim + c * spatial_dim + j];
- const int label_value = (int)label[i * dim + c * spatial_dim + j];
- if (label_value == 1 && data_value >= thresh) {
- ++true_positive;
- }
- if (label_value == 0 && data_value >= thresh) {
- ++false_positive;
- }
- if (label_value == 1 && data_value < thresh) {
- ++false_negative;
- }
- if (label_value == 0 && data_value < thresh) {
- ++true_negative;
- }
- }
- }
- Dtype precision = 0.0;
- Dtype recall = 0.0;
- if (true_positive + false_positive > 0) {
- precision =
- (Dtype)true_positive / (Dtype)(true_positive + false_positive);
- } else if (true_positive == 0) {
- precision = 1.0;
- }
- if (true_positive + false_negative > 0) {
- recall =
- (Dtype)true_positive / (Dtype)(true_positive + false_negative);
- } else if (true_positive == 0) {
- recall = 1.0;
- }
- if (prec_diff > fabs(precision - recall)
- && precision > 0 && precision < 1
- && recall > 0 && recall < 1) {
- breakeven = precision;
- prec_diff = fabs(precision - recall);
- }
- }
- top[0]->mutable_cpu_data()[0] += 1.0 - breakeven;
- }
- top[0]->mutable_cpu_data()[0] /= channels;
- }
-
- template <typename Dtype>
- void PrecisionRecallLossLayer<Dtype>::Backward_cpu(
- const vector<Blob<Dtype>*> &top,
- const vector<bool> &propagate_down,
- const vector<Blob<Dtype>*> &bottom) {
- for (int i = 0; i < propagate_down.size(); ++i) {
- if (propagate_down[i]) { NOT_IMPLEMENTED; }
- }
- }
-
- #ifdef CPU_ONLY
- STUB_GPU(PrecisionRecallLossLayer);
- #endif
- INSTANTIATE_CLASS(PrecisionRecallLossLayer);
- REGISTER_LAYER_CLASS(PrecisionRecallLoss);
-
- }
4、继续添加gpu的设置~/caffe-add/src/caffe/layers/precision_recall_loss_layer.cu:
- #include <algorithm>
- #include <cfloat>
- #include <vector>
-
- #include "thrust/device_vector.h"
-
- #include "caffe/layer.hpp"
- #include "caffe/util/math_functions.hpp"
- #include "caffe/vision_layers.hpp"
-
- namespace caffe {
-
- template <typename Dtype>
- void PrecisionRecallLossLayer<Dtype>::Forward_gpu(
- const vector<Blob<Dtype>*> &bottom, const vector<Blob<Dtype>*> &top) {
- Forward_cpu(bottom, top);
- }
- template <typename Dtype>
- void PrecisionRecallLossLayer<Dtype>::Backward_gpu(
- const vector<Blob<Dtype>*> &top,
- const vector<bool> &propagate_down,
- const vector<Blob<Dtype>*> &bottom) {
- if (propagate_down[1]) {
- LOG(FATAL) << this->type()
- << " Layer cannot backpropagate to label inputs.";
- }
- if (propagate_down[0]) {
- Backward_cpu(top, propagate_down, bottom);
- }
- }
-
- INSTANTIATE_LAYER_GPU_FUNCS(PrecisionRecallLossLayer);
-
- }
5、通过简单的minst测试,修改训练配置文件:
- ............
- layer {
- name: "loss"
- type: "SoftmaxWithLoss"
- bottom: "ip2"
- bottom: "label"
- top: "loss"
- }
- layer {
- name: "precision_recall_loss"
- type: "PrecisionRecallLoss"
- bottom: "ip2"
- bottom: "label"
- top: "error_rate"
- include {
- phase: TEST
- }
- }
6、然后训练
![](https://img-blog.csdn.net/20160325223512328?watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQv/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/Center)