Caffe-DeepBinaryCode的安装和使用

参考

https://blog.csdn.net/sun007700/article/details/95305982

https://www.helplib.com/GitHub/article_124433

 

make all -j8

报错

           from ./include/caffe/layer.hpp:8,
                 from src/caffe/layers/multi_label_sigmod_loss_layer.cpp:5:
./include/caffe/util/device_alternate.hpp:15:36: error: no ‘void caffe::MultiLabelSigmoidLossLayer<Dtype>::Forward_gpu(const std::vector<caffe::Blob<Dtype>*>&, const std::vector<caffe::Blob<Dtype>*>&)’ member function declared in class ‘caffe::MultiLabelSigmoidLossLayer<Dtype>’
     const vector<Blob<Dtype>*>& top) { NO_GPU; } \
                                    ^
src/caffe/layers/multi_label_sigmod_loss_layer.cpp:99:1: note: in expansion of macro ‘STUB_GPU’
 STUB_GPU(MultiLabelSigmoidLossLayer);
 ^~~~~~~~
./include/caffe/util/device_alternate.hpp:19:39: error: no ‘void caffe::MultiLabelSigmoidLossLayer<Dtype>::Backward_gpu(const std::vector<caffe::Blob<Dtype>*>&, const std::vector<bool>&, const std::vector<caffe::Blob<Dtype>*>&)’ member function declared in class ‘caffe::MultiLabelSigmoidLossLayer<Dtype>’
     const vector<Blob<Dtype>*>& bottom) { NO_GPU; } \
                                       ^
src/caffe/layers/multi_label_sigmod_loss_layer.cpp:99:1: note: in expansion of macro ‘STUB_GPU’
 STUB_GPU(MultiLabelSigmoidLossLayer);
 

vi src/caffe/layers/multi_label_sigmod_loss_layer.cpp +99

#ifdef CPU_ONLY
//STUB_GPU_BACKWARD(MultiLabelSigmoidLossLayer, Backward);
//STUB_GPU(MultiLabelSigmoidLossLayer);
#endif

 

 

 

上一篇:spring学习之aop(FactoryBean代理)


下一篇:RPC简介及原理介绍