abhigoku10

@songhengyang THanks for the response . Below are few queries 1. I want to train on 128x128 input image , where all should i make the changes in the code...

@songhengyang sure i shall fork this repo and see if can make some changes . Just wanted to knw the tentative timeline for the next release

@songhengyang thanks for the update and response . If you could give me some pointers on changing the image size during training it would be helpful

@fnzhan can you pls share the cocostuff repo so that we can download the model and test it Thanks in adavnce

@zhanghang1989 thanks for sharing the split attention module implementation, can we integrate this with FPN module instead of Resnet backbone ??

@zhanghang1989 any example references which you can point out

@sure thanks for response , it would be helpful you could upload the files from into ur repos and use that as clone repo and run the colabe

@abhigoku10 wokay for architectures like retina net how to obtain the CAM output or mask rcnn based architecture

@yizt please do let me knw once done it

@yizt thanks for sharing the source code , in your codes both faster rcnn and retina net you have a variable called indices can you let me knw how to...