SeaRecluse

此外，按UP的使用指南编译openmp ,则是i386/x86_64正常，而arm*会提示以下错误： 执行命令 ``` cd sed -i'' -e '/.size __kmp_unnamed_critical_addr/d' runtime/src/z_Linux_asm.S sed -i'' -e 's/__kmp_unnamed_critical_addr/___kmp_unnamed_critical_addr/g' runtime/src/z_Linux_asm.S mdkir -p build_arm cd build_arm cmake -DCMAKE_TOOLCHAIN_FILE=../ios.toolchain.cmake -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=install \ -DIOS_PLATFORM=OS -DENABLE_BITCODE=0 -DENABLE_ARC=0 -DENABLE_VISIBILITY=0...

更换为112x112之后，重新测试，emmm，是我哪里的姿势不对吗？ 

PS C:\Users\SEARECLUSE\Desktop\testFace106\x64\Debug> .\testFace106.exe ./model/mobilefacene t-res2-6-10-2-dim128.zqparams ./model/mobilefacenet-res2-6-10-2-dim128-emore.nchwbin fc5 C:/U sers/SEARECLUSE/Desktop/lfw/pairs.txt C:/Users/SEARECLUSE/Desktop/lfw/dataClone >> load arcface done! feat_dim = 128, real_dim = 256 parse list file C:/Users/SEARECLUSE/Desktop/lfw/pairs.txt done! 100 handled 200 handled 300...

嗯，是的

原来也是先通过MTCNN裁剪出然后归一化的吗，我之前以为直接是一种“端对端”的方式😂，谢谢你，现在我明白了

需要的话我可以上传一下模型文件，包含原始onnx以及caffe

> https://github.com/SoftwareGift/FeatherNets_Face-Anti-spoofing-Attack-Detection-Challenge-CVPR2019/blob/77d27c0f3237419030bc0073c951792b5588704d/models/mobilenetv2.py#L109 Great Nihui.Thank you so much😂 I still don't know how to change it.I just learned the pytorch API doc.

I change the code like this. But It doesn't work. ```python self.avg_pool = nn.AdaptiveAvgPool2d(1) def forward(self, x): x = self.features(x) b, c, _, _ = x.size() y = self.avg_pool(x).view(b, c)...