Sharhar Zou

I also have this problem, i try to compare 2 different faces in my data, the cosine similarity and distance were very similar. Whether the pre-trained model was error? but...

我也是遇到了这个问题，各种方法都尝试过了都不行，我的环境是cuda10.1+cudnn7.6.5。 .build_release/lib/libcaffe.so：对‘__cudaPushCallConfiguration’未定义的引用 .build_release/lib/libcaffe.so：对‘__cudaRegisterFatBinaryEnd’未定义的引用 .build_release/lib/libcaffe.so：对‘__cudaPopCallConfiguration’未定义的引用 collect2: error: ld returned 1 exit status Makefile:635: recipe for target '.build_release/tools/upgrade_net_proto_text.bin' failed make: *** [.build_release/tools/upgrade_net_proto_text.bin] Error 1 make: *** 正在等待未完成的任务.... .build_release/lib/libcaffe.so：对‘__cudaPushCallConfiguration’未定义的引用 .build_release/lib/libcaffe.so：对‘__cudaRegisterFatBinaryEnd’未定义的引用 .build_release/lib/libcaffe.so：对‘__cudaPopCallConfiguration’未定义的引用 collect2: error:...

@yl-1993 Thanks for your reply! Whetheri use generate_proposal.py extract features and use dsgcn/main.py to cluster? Can you supported your pretrained model in Baidu Yun? How many images supported in code,...

@yl-1993 Thank you! I'm sorry that maybe I didn't describe it clearly. I mean the pretrained model of hfsoftmax.I analysised the code and download your data. I am no sure...

@yl-1993 thank you very much!