Li-Chi Huang comments

Results 6 comments of


                                            Li-Chi Huang

Are pretrained model damaged?

got it Thanks

Have question about the decision network

I thought the ultimate goal is producing a good segmentation mask, so I am wondering what the purpose of the decision network in this scenario. Maybe I missed something in...

Have question about the decision network

That's where the question is, the decision network is trained with segmentation network's weight frozen. So how training the decision network would improve segmentation result in this way.

Multiple Vimba installations found. Can't decide which to select

Hello, I followed the python manual [Vimba Python Manual.pdf](https://github.com/alliedvision/VimbaPython/blob/master/Documentation/Vimba%20Python%20Manual.pdf) and Vimba under linux https://cdn.alliedvision.com/fileadmin/content/documents/products/software/software/Vimba/appnote/Vimba_installation_under_Linux.pdf My environmental variables related to Vimba `printenv | grep Vimba` are the same as the following...

Multiple Vimba installations found. Can't decide which to select

I have tried uninstall.sh script before and it raised the following error : `vimba.error.VimbaSystemError: Failed to load library '/opt/Vimba_6_0/VimbaGigETL/VimbaC/DynamicLib/x86_64bit/libVimbaC.so'. Please verify Vimba installation.` Looks like the issue is that it...

No improvemenmt in Faster R-CNN after optimizing it with TF-TRT

I also have this issue. I converted my own faster rcnn model to tensorRT but notice that it is actually 2 times slower than non-optimized model. I'm using tf1.14 as...