Jim0530
Jim0530
使用1.14的時候我也依樣沒問題 但使用新版的tf 2.2 evaluate的時候precision 會一直都是1 recall是0 loss 會降不下來
I saw ur update this morning How should I set the Explicit Batch? Thank you
Thanks a lot!
I got an error Attribute error "tensorrt.tensorrt.Builder" has no attribute "build serialized network" I guess that's due to the different version of tensorrt am I right? (I am using Tensorrt...
Works for me thanks
Did anyone know how to solve it? Thanks
i find out that i am using the newest image for git-sync which those variables are not allowed to use