luluvi

> hello, @liuzhuang13 @Eric-mingjie ,have you ever do the pruning of mobilenetV2? > I try to prune mobilenetV2 with several methods, it seems hard to train the pruned model to...

> The value of the loss function cannot be lowered，When I execute to the 50th epoch, this value is still 12.137....，It is similar to the previous epoch. > I listed...

> > 应该是你的硬件平台不支持Int8量化，我的显卡是2080ti > > 哦哦，多谢了。这个跟cuda版本有关系吗？我对底层的不太懂。。。我也换到2080上看看。 > 还有一个问题，就是用python生成engine和用$TensorRTDIR/bin/trtexec 生成的engine有什么区别吗？为什么用脚本生成的engine总是失败，报错 > [TensorRT] ERROR: Network must have at least one output > [TensorRT] ERROR: Network validation failed. 这个博客可以解决你的这个报错问题 https://blog.csdn.net/weixin_43953045/article/details/103937295