最近看了densenet这篇论文,论文作者给了基于caffe的源码,自己在电脑上跑了下,但是出现了Message type “caffe.PoolingParameter” has no field named “ceil_mode”.的错误,现将解决办法记载如下。主要是参考
(https://github.com/BVLC/caffe/pull/3057/files)。错误原因:由于caffe的版本的原因,现用的caffe的源码中的pooling层没有ceil_mode
这个函数,因此解决办法也是在现在的源码中网pooling层中添加这个参数以及相关的代码,并重新编译caffe即可。
1、修改pooling_layer.hpp文件PoolingLayer类
在pooling_layer.hpp中往PoolingLayer类中添加ceil_mode_这个参数,修改如下:
int height_, width_;
int pooled_height_, pooled_width_;
bool global_pooling_;
bool ceil_mode_; //添加的类成员变量 Blob<Dtype> rand_idx_; Blob<int> max_idx_;
2、修改pooling_layer.cpp文件中相关参数
主要涉及到LayerSetUp函数和Reshape函数。LayerSetUp函数修改如下:
|| (!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(); ceil_mode_ = pool_param.ceil_mode(); //添加的代码,主要作用是从参数文件中获取ceil_mode_的参数数值。 if (global_pooling_) { kernel_h_ = bottom[0]->height(); kernel_w_ = bottom[0]->width(); 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_); .......
Reshape函数修改如下:
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(); } - 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; + // Specify the structure by ceil or floor mode + + // 添加的代码----------------------------------- + if (ceil_mode_) { + 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; + } else { + pooled_height_ = static_cast<int>(floor(static_cast<float>( + height_ + 2 * pad_h_ - kernel_h_) / stride_h_)) + 1; + pooled_width_ = static_cast<int>(floor(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.
3、修改caffe.proto文件中PoolingParameter的定义
因为添加了pooling层的参数,因此需要修改caffe.proto文件中PoolingParameter中的定义,需要增加参数的声明。
// If global_pooling then it will pool over the size of the bottom by doing
// kernel_h = bottom->height and kernel_w = bottom->width
optional bool global_pooling = 12 [default = false]; + // Specify floor/ceil mode + optional bool ceil_mode = 13 [default = true];// 为pooling层添加参数,这样可以在net.prototxt文件中为pooling层设置该参数,注意后面需要给其设置一个ID,同时设置一个默认值。 }
4、重新编译caffe
返回到caffe的根目录,使用make指令,即可。
make -j32 // 这里j后面的数字与电脑配置有关系,可以加速编译