Harsh Maheshwari comments

Repositories
Issues
Comments

Results 4 comments of


                                            Harsh Maheshwari

after filtering, there are 0 images

There must be some formatting error in the annotation files or how annotation is done. Kindly recheck them once.

Your implementation of domain adaptive faster rcnn performs better than paper values, what might be the reason?

Hey, It should not be the case. There must be some bug in the your code leading to this issue.

How can I add custom new class labels, lets say-x classes to a SCL trained model( which is already trained on y classes). So I do not replace those y classes and in total I have x+y class labels.

So far it's not integrated in the code base. You will have to look for few shot object detection techniques for that.

About the trained model.

Hey, It might be the case that by mistake I have uploaded the checkpoint of pretrained model of earlier codebase (which was then cleaned and made public). An easy and...