I have tried your test.py. but still have one question about the RPN process?

[yypeng9468]

I finally added the roi pooling and normalize layers into the official version of caffe, and compile it with success, and get the features of query and dataset, together with 55 queries' rank. But after I read your code -- test.py, it appeares that I found nowhere RPN is applied when generating rois for afterwards process, such as feature extraction, instead I saw the r-mac operation. So I'm wondering if you generated the rois using r-mac, instead of what the authors written in his paper that the rois were generated by RPN. Thanks!

[lanma901106]

I finally added the roi pooling and normalize layers into the official version of caffe, and compile it with success, and get the features of query and dataset, together with 55 queries' rank. But after I read your code -- test.py, it appeares that I found nowhere RPN is applied when generating rois for afterwards process, such as feature extraction, instead I saw the r-mac operation. So I'm wondering if you generated the rois using r-mac, instead of what the authors written in his paper that the rois were generated by RPN. Thanks!

@yypeng9468 Could you tell me how to add the roi pooling and normalize layers, since I am not familiar with Caffe. Thanks in advance.

[willard-yuan]

@lanma901106 Just follow this: pull/4163/files, and add roi layer, normalize layer is not necessary. Recompile the caffe and This's all.

[hetianle]

@lanma901106 Just follow this: pull/4163/files, and add roi layer, normalize layer is not necessary. Recompile the caffe and This's all.

Can't figure out how to deal with it. Could I directly compile the [caffe/fast-rcnn] branch? (https://github.com/Austriker/caffe/tree/fast-rcnn) But there is a lot of mistakes here? Like this: CXX .build_release/src/caffe/proto/caffe.pb.cc CXX src/caffe/util/db_lmdb.cpp In file included from ./include/caffe/util/device_alternate.hpp:40:0, from ./include/caffe/common.hpp:19, from ./include/caffe/util/db.hpp:6, from ./include/caffe/util/db_lmdb.hpp:10, from src/caffe/util/db_lmdb.cpp:2: ./include/caffe/util/cudnn.hpp: In function 'const char* cudnnGetErrorString(cudnnStatus_t)': ./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value 'CUDNN_STATUS_RUNTIME_PREREQUISITE_MISSING' not handled in switch [-Wswitch] switch (status) { ^ ./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value 'CUDNN_STATUS_RUNTIME_IN_PROGRESS' not handled in switch [-Wswitch] ./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value 'CUDNN_STATUS_RUNTIME_FP_OVERFLOW' not handled in switch [-Wswitch] ./include/caffe/util/cudnn.hpp: In function 'void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)': ./include/caffe/util/cudnn.hpp:113:70: error: too few arguments to function 'cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)' pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION)); ^ ./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro 'CUDNN_CHECK' cudnnStatus_t status = condition; \ ^ In file included from ./include/caffe/util/cudnn.hpp:5:0, from ./include/caffe/util/device_alternate.hpp:40, from ./include/caffe/common.hpp:19, from ./include/caffe/util/db.hpp:6, from ./include/caffe/util/db_lmdb.hpp:10, from src/caffe/util/db_lmdb.cpp:2: /usr/local/cuda/include/cudnn.h:518:1: note: declared here cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t convDesc, ^ Makefile:572: recipe for target '.build_release/src/caffe/util/db_lmdb.o' failed make: *** [.build_release/src/caffe/util/db_lmdb.o] Error 1