TangChangcheng
TangChangcheng
I compiled [gst-kaldi-nnet2-online](https://github.com/alumae/gst-kaldi-nnet2-online) successful outside the docker, and then got correct result using gst-inspect-1.0 kaldinnet2onlinedecoder. However, I copied the .so file to /media/kaldi-models/ and then added its path to GST_PLUGIN_PATH,...
docker内部是可以用ssh登录服务器的,但是外部加proxycommand的ssh无法登陆,并没有可用的网络
It will be more convenient if command-line is supported
Cannot create a tensor proto whose content is larger than 2GB. The problem occured where word token matrix feed into a tensor: File "/SentenceMatchModelGraph.py", line 35,
mAP能达到多少?