mumuyanyan

I have the same problem. Did you have dealt with the problem?

> it‘s just the segmentation_result, not panoptic result yes, the result is semantic segmentation, do you have the panoptic inference?

@lfdeep [email protected] Thank you very much

> b_batch is fed to true_boxes > true_boxes is used for masks for confidence and class in loss function In the training,there is already true_boxes.Sorry,i just don't get it.

me too

> Maybe you can try > > https://github.com/lerrel/gym-adv/tree/master/gym/monitoring > > copy the fold and make it a module to be called later on. how to do?

i have the same question. why the the labels of the test dataset is different from the labels of the train dataset?

i have the same question

i run the code on mac

> Hello there, which test are you running? > > When you build the system on Mac you need to additionally use `--define build_platform=macos`. My test file is "examples/continuous_env.py" I...