fujingling

Hi! did you solve this problem? I get the same error with you, if you solved it, can you tell me how did you do?Thank you very much

> 大帅您好，我发现这个模型在P40上大概要15ms才能搞定一张图片，CPU上就慢的简直不能接受，一张图推理时间2-3s。您测试时快吗？ 我说的是PFPLD

> 一个mobilenet的结构，还是112x112的输入，2-3s怕是过分了，我在2080ti上的速度是10ms左右，这个模型本身是可以再优化的，换一下backbone重新训练下，我试过了mobilenet0.25，精度上也差不了多少 您有在CPU上测试过吗？

> 是的，如果按照channel pruning的思想来看，其实完全不用那么大个网络做这个任务 Learning Efficient Convolutional Networks through Network Slimming > […](#) > ---原始邮件--- 发件人: "Kaidi Chen"

do you resolved the problem?@spha-code

thank you very much for@luckydog5 @saicoco I manually compiled opencv3.4，but didn't configure environment library correctly, so I met this error，I solved the problem by: `export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/export/usr/opencv3.4/lib64`

@Chavez-Zhu thank you, its work > Makefile line181: > change > LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_serial_hl hdf5_serial > to > LIBRARIES += glog gflags protobuf boost_system...