小编cur*_*729的帖子

请查看此github页面。我想使用Python PIL，open cv或matplotlib库以这种方式生成热图。有人可以帮我解决吗？

我可以为网络创建一个热图，其大小与输入的大小相同，但无法叠加它们。热图形状为（800,800），基本图像形状为（800,800,3）

我在Windows 8.1上使用cygwin.我使用了以下make文件

  .SUFFIXES : .o .C

  CFLAGS = -g2 
  CC =g++ ${CFLAGS}

  LIBRARIES =   -lm 

  .C.o :
   ${CC} -c  $<

  SOURCE-FILES =   sparsegraph.C myvarious.C pairlist.C graphlist.C peo.graph.C choldc.C copy.C metropolis_fns.C likelihood.C metropolis.C

  OBJECT-FILES =  sparsegraph.o myvarious.o pairlist.o graphlist.o peo.graph.o choldc.o copy.o metropolis_fns.o likelihood.o metropolis.o

  HEADER-FILES = sparsegraph.h pairlist.h graphlist.h myvarious.h chol.h peo.graph.h copy.h likelihood.h metropolis.h

  EXECUTABLES = metropolis

  PROGRAMS = metropolis sparsegraph myvarious pairlist graphlist peo.graph choldc copy likelihood metropolis_fns 

  metropolis: ${OBJECT-FILES}
${CC} -o $@ metropolis.o metropolis_fns.o sparsegraph.o myvarious.o pairlist.o …

void SilenceLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
  for (int i = 0; i < bottom.size(); ++i) {
    if (propagate_down[i]) {
      caffe_set(bottom[i]->count(), Dtype(0),
                bottom[i]->mutable_cpu_diff());
    }
  }
}

它只是将差异设置为零。这层有什么用？