lh

@17759205390 thankyou very much. I just saw it . I'm done.

@Tim5Tang 你将layers文件夹下文件拷贝到caffe目录下编译出现的jfda_loss_param()未定义错误是怎么解决的？

@Tim5Tang 谢谢你及时的回答，非常感谢。但我很确定按照作者提供的copy.sh将损失函数层jfda放到caffe对应的位置了 jfda_loss_param()确实未定义 因为根本搜索不到jfda_loss_param()的实现。可以在帮忙确定下吗

proto文件中是有用jfda_loss_param的 如下： jfda_loss_param { drop_loss_rate: 0.3 } 但这不是关键 ，关键是layers/jfda_loss_layer.cpp中jfda_loss_param()函数未实现 会不会是作者故意删除掉了...

@waquey hello have you freeze the graph and save three net .ckpt to .pb file ? I have the same need, could you give me some advice

I have the same question. Can you answer it

@junedgar Did you solve the problem? give me some advices thankyou

hi, @Keysmis @tensorboy train shuffleNetv2 error ImportError: No module named 'training.datasets' where training/datasets ?

@szad670401 how to convert tensorflow model to caffemodel? could you please provide the method? Thank you very much.