Caffe源码：pooling_layer.cpp
来源：互联网 发布：淘宝上卖千岛片真的么 编辑：程序博客网 时间：2024/05/29 04:11
@brief PoolingLayer层反向传播conv2–>pool2
只将梯度传到贡献损失的神经元即
核心代码：
bottom_diff[bottom_index] += top_diff[index];//计算梯度并更新原始bottom_diff主体代码
#include <algorithm>#include <cfloat>#include <vector>#include "caffe/layers/pooling_layer.hpp"#include "caffe/util/math_functions.hpp"namespace caffe {using std::min;using std::max;template <typename Dtype>void PoolingLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) { PoolingParameter pool_param = this->layer_param_.pooling_param(); if (pool_param.global_pooling()) { CHECK(!(pool_param.has_kernel_size() || pool_param.has_kernel_h() || pool_param.has_kernel_w())) << "With Global_pooling: true Filter size cannot specified"; } else { CHECK(!pool_param.has_kernel_size() != !(pool_param.has_kernel_h() && pool_param.has_kernel_w())) << "Filter size is kernel_size OR kernel_h and kernel_w; not both"; CHECK(pool_param.has_kernel_size() || (pool_param.has_kernel_h() && pool_param.has_kernel_w())) << "For non-square filters both kernel_h and kernel_w are required."; } CHECK((!pool_param.has_pad() && pool_param.has_pad_h() && pool_param.has_pad_w()) || (!pool_param.has_pad_h() && !pool_param.has_pad_w())) << "pad is pad OR pad_h and pad_w are required."; CHECK((!pool_param.has_stride() && pool_param.has_stride_h() && pool_param.has_stride_w()) || (!pool_param.has_stride_h() && !pool_param.has_stride_w())) << "Stride is stride OR stride_h and stride_w are required."; global_pooling_ = pool_param.global_pooling(); if (global_pooling_) { kernel_h_ = bottom[0]->height(); kernel_w_ = bottom[0]->width(); } else { if (pool_param.has_kernel_size()) { kernel_h_ = kernel_w_ = pool_param.kernel_size();//如果设置kernelsize则默认为kernel为方的 } else { kernel_h_ = pool_param.kernel_h(); kernel_w_ = pool_param.kernel_w(); } } CHECK_GT(kernel_h_, 0) << "Filter dimensions cannot be zero."; CHECK_GT(kernel_w_, 0) << "Filter dimensions cannot be zero."; if (!pool_param.has_pad_h()) { pad_h_ = pad_w_ = pool_param.pad();//默认为0 } else { pad_h_ = pool_param.pad_h(); pad_w_ = pool_param.pad_w(); } if (!pool_param.has_stride_h()) { stride_h_ = stride_w_ = pool_param.stride();//默认为方的 } else { stride_h_ = pool_param.stride_h(); stride_w_ = pool_param.stride_w(); } if (global_pooling_) { CHECK(pad_h_ == 0 && pad_w_ == 0 && stride_h_ == 1 && stride_w_ == 1) << "With Global_pooling: true; only pad = 0 and stride = 1"; } if (pad_h_ != 0 || pad_w_ != 0) { CHECK(this->layer_param_.pooling_param().pool() == PoolingParameter_PoolMethod_AVE || this->layer_param_.pooling_param().pool() == PoolingParameter_PoolMethod_MAX) << "Padding implemented only for average and max pooling."; CHECK_LT(pad_h_, kernel_h_); CHECK_LT(pad_w_, kernel_w_); }}template <typename Dtype>void PoolingLayer<Dtype>::Reshape(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) { CHECK_EQ(4, bottom[0]->num_axes()) << "Input must have 4 axes, " << "corresponding to (num, channels, height, width)"; channels_ = bottom[0]->channels(); height_ = bottom[0]->height(); width_ = bottom[0]->width(); if (global_pooling_) { kernel_h_ = bottom[0]->height(); kernel_w_ = bottom[0]->width(); } //具体计算pooling后featuremap的2D大小 pooled_height_ = static_cast<int>(ceil(static_cast<float>( height_ + 2 * pad_h_ - kernel_h_) / stride_h_)) + 1; pooled_width_ = static_cast<int>(ceil(static_cast<float>( width_ + 2 * pad_w_ - kernel_w_) / stride_w_)) + 1; if (pad_h_ || pad_w_) { // If we have padding, ensure that the last pooling starts strictly // inside the image (instead of at the padding); otherwise clip the last. if ((pooled_height_ - 1) * stride_h_ >= height_ + pad_h_) { --pooled_height_; } if ((pooled_width_ - 1) * stride_w_ >= width_ + pad_w_) { --pooled_width_; } CHECK_LT((pooled_height_ - 1) * stride_h_, height_ + pad_h_); CHECK_LT((pooled_width_ - 1) * stride_w_, width_ + pad_w_); } top[0]->Reshape(bottom[0]->num(), channels_, pooled_height_, pooled_width_); if (top.size() > 1) { top[1]->ReshapeLike(*top[0]); } // If max pooling, we will initialize the vector index part. if (this->layer_param_.pooling_param().pool() == PoolingParameter_PoolMethod_MAX && top.size() == 1) { max_idx_.Reshape(bottom[0]->num(), channels_, pooled_height_, pooled_width_); } // If stochastic pooling, we will initialize the random index part. if (this->layer_param_.pooling_param().pool() == PoolingParameter_PoolMethod_STOCHASTIC) { rand_idx_.Reshape(bottom[0]->num(), channels_, pooled_height_, pooled_width_); }}// TODO(Yangqing): Is there a faster way to do pooling in the channel-first// case?template <typename Dtype>void PoolingLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) { const Dtype* bottom_data = bottom[0]->cpu_data();//拿到输入数据的const指针 Dtype* top_data = top[0]->mutable_cpu_data();//拿到输出数据的const指针 const int top_count = top[0]->count(); // We'll output the mask to top[1] if it's of size >1. const bool use_top_mask = top.size() > 1;//使用mask是干嘛的 int* mask = NULL; // suppress warnings about uninitalized variables Dtype* top_mask = NULL; // Different pooling methods. We explicitly do the switch outside the for // loop to save time, although this results in more code. switch (this->layer_param_.pooling_param().pool()) { case PoolingParameter_PoolMethod_MAX: // Initialize if (use_top_mask) { top_mask = top[1]->mutable_cpu_data(); caffe_set(top_count, Dtype(-1), top_mask); } else { mask = max_idx_.mutable_cpu_data();//pooling的kernel窗口中最大值的索引 caffe_set(top_count, -1, mask); } caffe_set(top_count, Dtype(-FLT_MAX), top_data);//将所有输出初始化为负无穷大 // The main loop for (int n = 0; n < bottom[0]->num(); ++n) {//batch_size数 for (int c = 0; c < channels_; ++c) {//通道数 for (int ph = 0; ph < pooled_height_; ++ph) {//对原窗口向下扫（竖向）扫输出窗口的宽次 for (int pw = 0; pw < pooled_width_; ++pw) {//对原窗口向右扫（横向）扫输出窗口的高次 int hstart = ph * stride_h_ - pad_h_;//kernel窗口的行头 int wstart = pw * stride_w_ - pad_w_;//kernel窗口的列头 int hend = min(hstart + kernel_h_, height_);//kernel窗口的行尾 hstart加上kernel_h_ int wend = min(wstart + kernel_w_, width_);//kernel窗口的列尾 hstart = max(hstart, 0); wstart = max(wstart, 0);//[hstart,hend][wsatart,wend]标记了kernel窗口 const int pool_index = ph * pooled_width_ + pw;//输出窗口的索引值 for (int h = hstart; h < hend; ++h) {//kernel的窗口行 [h,w]表征了kernel窗口的具体点位置 for (int w = wstart; w < wend; ++w) {//kernel的窗口列 const int index = h * width_ + w;//kernel窗口中的点在输入featuremap的位置 if (bottom_data[index] > top_data[pool_index]) { top_data[pool_index] = bottom_data[index];//输出窗口赋值 if (use_top_mask) { top_mask[pool_index] = static_cast<Dtype>(index); } else { mask[pool_index] = index;//在kernel范围内记录最大的输入值索引 } } } } } } // compute offset 扫完一个通道后 bottom_data += bottom[0]->offset(0, 1);//bottom_data指向一个样本输入featuremap的下一个通道 top_data += top[0]->offset(0, 1);//同理同上 if (use_top_mask) { top_mask += top[0]->offset(0, 1); } else { mask += top[0]->offset(0, 1);//同理同上 } } } break; case PoolingParameter_PoolMethod_AVE: for (int i = 0; i < top_count; ++i) { top_data[i] = 0; } // The main loop for (int n = 0; n < bottom[0]->num(); ++n) { for (int c = 0; c < channels_; ++c) { for (int ph = 0; ph < pooled_height_; ++ph) { for (int pw = 0; pw < pooled_width_; ++pw) { int hstart = ph * stride_h_ - pad_h_; int wstart = pw * stride_w_ - pad_w_; int hend = min(hstart + kernel_h_, height_ + pad_h_); int wend = min(wstart + kernel_w_, width_ + pad_w_); int pool_size = (hend - hstart) * (wend - wstart); hstart = max(hstart, 0); wstart = max(wstart, 0); hend = min(hend, height_); wend = min(wend, width_); for (int h = hstart; h < hend; ++h) { for (int w = wstart; w < wend; ++w) { top_data[ph * pooled_width_ + pw] += bottom_data[h * width_ + w]; } } top_data[ph * pooled_width_ + pw] /= pool_size; } } // compute offset bottom_data += bottom[0]->offset(0, 1); top_data += top[0]->offset(0, 1); } } break; case PoolingParameter_PoolMethod_STOCHASTIC: NOT_IMPLEMENTED; break; default: LOG(FATAL) << "Unknown pooling method."; }}template <typename Dtype>void PoolingLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top, const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) { if (!propagate_down[0]) { return; } const Dtype* top_diff = top[0]->cpu_diff();//拿到该层的输入梯度指针 Dtype* bottom_diff = bottom[0]->mutable_cpu_diff();//拿到要计算的传播到下一层的梯度指针 // Different pooling methods. We explicitly do the switch outside the for // loop to save time, although this results in more codes. caffe_set(bottom[0]->count(), Dtype(0), bottom_diff);//清零 // We'll output the mask to top[1] if it's of size >1. const bool use_top_mask = top.size() > 1; const int* mask = NULL; // suppress warnings about uninitialized variables const Dtype* top_mask = NULL; switch (this->layer_param_.pooling_param().pool()) { case PoolingParameter_PoolMethod_MAX: // The main loop if (use_top_mask) { top_mask = top[1]->cpu_data(); } else { mask = max_idx_.cpu_data();//max索引表征输入featuremap哪一个神经元贡献损失 } for (int n = 0; n < top[0]->num(); ++n) {//batch_size数 for (int c = 0; c < channels_; ++c) {//通道数 for (int ph = 0; ph < pooled_height_; ++ph) { for (int pw = 0; pw < pooled_width_; ++pw) { const int index = ph * pooled_width_ + pw;//定位顶层的输入梯度位置 2D const int bottom_index = use_top_mask ? top_mask[index] : mask[index]; bottom_diff[bottom_index] += top_diff[index];//计算梯度并更新原始bottom_diff } } bottom_diff += bottom[0]->offset(0, 1); top_diff += top[0]->offset(0, 1); if (use_top_mask) { top_mask += top[0]->offset(0, 1); } else { mask += top[0]->offset(0, 1); } } } break; case PoolingParameter_PoolMethod_AVE: // The main loop for (int n = 0; n < top[0]->num(); ++n) { for (int c = 0; c < channels_; ++c) { for (int ph = 0; ph < pooled_height_; ++ph) { for (int pw = 0; pw < pooled_width_; ++pw) { int hstart = ph * stride_h_ - pad_h_; int wstart = pw * stride_w_ - pad_w_; int hend = min(hstart + kernel_h_, height_ + pad_h_); int wend = min(wstart + kernel_w_, width_ + pad_w_); int pool_size = (hend - hstart) * (wend - wstart); hstart = max(hstart, 0); wstart = max(wstart, 0); hend = min(hend, height_); wend = min(wend, width_); for (int h = hstart; h < hend; ++h) { for (int w = wstart; w < wend; ++w) { bottom_diff[h * width_ + w] += top_diff[ph * pooled_width_ + pw] / pool_size; } } } } // offset bottom_diff += bottom[0]->offset(0, 1); top_diff += top[0]->offset(0, 1); } } break; case PoolingParameter_PoolMethod_STOCHASTIC: NOT_IMPLEMENTED; break; default: LOG(FATAL) << "Unknown pooling method."; }}#ifdef CPU_ONLYSTUB_GPU(PoolingLayer);#endifINSTANTIATE_CLASS(PoolingLayer);} // namespace caffe阅读全文
0 0
- Caffe源码：pooling_layer.cpp
- Caffe源码解析7：Pooling_Layer
- Caffe源码解析7：Pooling_Layer
- Caffe源码解析7：Pooling_Layer
- Caffe源码解析7：Pooling_Layer
- 学习笔记: 源码 pooling_layer.cpp 略懂
- Caffe源码（六）: pooling_layer 分析
- CAFFE源码学习笔记之池化层pooling_layer
- Caffe源码解析caffe.cpp
- caffe源码：math_functions.cpp
- Caffe源码:Softmax_loss_layer.cpp
- Caffe源码:inner_product_layer.cpp
- Caffe源码：relu_layer.cpp
- Caffe源码解读：pooling_layer的前向传播与反向传播
- caffe源码分析:softmax_layer.cpp && softmax_loss_layer.cpp
- caffe源码分析--data_layer.cpp
- caffe源码分析--softmax_layer.cpp
- caffe源码分析--poolinger_layer.cpp
- Spring Security
- 用类描述计算机中CPU速度和硬盘容量
- 数据结构试验
- 百练+重要逆序对归并排序，记得要有标记来减少循环扫描
- 小球与盒子（矩阵乘法+快速幂）
- Caffe源码：pooling_layer.cpp
- BOX 判断是否能够形成立方体
- 我的Java之旅
- pom.xml
- linux下查看系统配置参数
- 关于Linux下，文件传输与ftp以及Tomcat配置等
- 实验一 线性表的应用（2学时）
- 用h5和原生js做的漂亮的时钟
- WebService远程调用技术--学习01
