bouncybunny

@Zhou-Yuen Hey sorry for being late. Unfortunately I couldn't get the visualization codes.

@yanxp can you elaborate a little more?

@bitwangdan Have you solved the problem?

Hey have you solved the problem? I'm having a same issue here :(

I'm also experiencing CUDA out of memory issue with non-local block. I'm trying to use non-local block at the top of my network, which is for bbox regression conv head...

@zl1994 Or at least can you share the log file? I want to track my loss compared to the accurate one.

I meant SimCLR episodes