Closed wangchust closed 2 years ago
By the way, the link of maskrcnn trained weights seems to be ldet model. Because it get the same scores as ldet gets in paper
Thanks for reporting the issue on the mask rcnn trained model. I will look into the issue.
First, you should set the number of class as 1 in your config. Also, in the training script, i.e., trainer_plain.py, you need to set the classes of instances as 1, like
for da in data: da['instances'].gt_classes = da['instances'].gt_classes * 0
in line 141.
It is just because we kept the class index of COCO. We just avoided mapping the classes to that of 20. I guess it will not make a large difference in the performance.
Thank you for your reply. I'll close this issue
Hi, I have two simple questions.