zhanghx
zhanghx
@hugos94 hi sorry to bother you .how you solve the problem numpy.linalg.linalg.LinAlgError: singular matrix
the protobuf . i have two version protobuf in my linux.
你好,感谢你的回复,我分为4类:0:性感女性。1:赤裸男。2.普通女。3.其他(不包含人像)。我感觉网络学习到的东西可能有些偏差: **热图,训练集性感女:** **热图,训练集普通女:** 等会我再跑几个误识别的图传上来
下边的是一些误召的,都预测为性感女,尤其最后一个的热图关注点不在胸部:       11d968b31678.jpg)   
你说的对,还是要对数据有深刻的理解,感谢
火鸡 有试过使用检测的方法做吗?
maybe you should change the yolo_v4_tiny.json classes num
I find the depth loss is inf.
I find the question. because I use my own data. and the data has some zero value .So when I use the torch.log function. it will produce the inf value.
@NikitaDurasov do you solve the problem?