WW2401
WW2401
> ``` > root@5b1e58e4ea08:~/.cache/Detect/py-faster-rcnn/caffe-fast-rcnn# make > PROTOC src/caffe/proto/caffe.proto > make: protoc: Command not found > Makefile:620: recipe for target '.build_release/src/caffe/proto/caffe.pb.cc' failed > make: *** [.build_release/src/caffe/proto/caffe.pb.cc] Error 127 > ``` I...
> @wavelet2008 你们说的acc是fc6层作为输入的acc么？请问训练过程中AdaCosAddmScale的acc大概能到多少 同问~
> @Rashomon5487 是的，为了让多卡从不同位置读取数据，可以加速收敛 rand_skip参数根据什么设置？您为什么设置为10000？
hi,你知道使用caffe-augmentation时怎么修改original caffe吗?需要修改哪些？ @Rashomon5487
> 应该是显卡不支持CUDA，或者安装的CUDA版本不支持，在Makefile.config里取消 `# CPU_ONLY := 1` 的注释，再 `make clean` 、 `make all` 试试。（如果取消过 `# USE_CUDNN := 1` 的注释，也许还需要加上，没试过） CUDA版本不支持什么意思？我的cuda是9.0，编译通过了，但make C++程序时出现了类似问题： /usr/bin/ld: warning: libcudart.so.9.0, needed by caffe/build/lib/libcaffe.so, not found (try using...
> (1) Yeah, when the backbone network is resnet, OctaveConv only needs OctaveUpsampleLayer. OctaveConv does not change the way the convolution is done. Convolution will only differ depending on the...
@bixiwen Hi, when I met the error No such file or directory: 'data/facebank/facebank.pth', I ran python face_verify.py --update, I met another problem as follows. Do you know the reason? ir_se_50...
> Thank you very much. I have solved it. Thanks Hi, how do you solve it?
@we0091234 你解决了吗？ 能提供一下你的face_list_lfw.txt以及face_list_lfw_gt.txt吗？@lippman1125