object_localization_network
object_localization_network copied to clipboard
Learning Open-World Object Proposals without Learning to Classify
Following the installation steps, while running `pip install mmcv-full==1.2.7` leads to this error: ``` Collecting mmcv-full==1.2.7 Using cached mmcv-full-1.2.7.tar.gz (231 kB) ERROR: Command errored out with exit status 1: command:...
 but the code of OlnRPNHead shows that the iou sample is not used, as the function get_target return to the objectness_targets_list and objectness_weights_list without sample 
Could you provide the coco class list in objects365?
(1) How can I generate the result image as Fig 3/ Fig 5/ Fig6 in your paper? (2) I've noticed that in the test_cfg, rcnn=dict(score_thr=0.0, ......), why set score_thr=0.0?
Hello, I have a few questions to ask. 1. How are the effects shown in Figure 5 and Figure 6 generated in the paper? 2. If you want to generalize...
Hi, Are you planning to release the config files you use for LVIS long-tail recognition?
Could you provide the config of OLN-RPN? I remove the part of rcnn in "configs/oln_box/oln_box.py", but the results are worse than the results in the paper.
Hi, thanks for the inspiring work. When I retrained the model with the config /oln_box, i received this: "AssertionError: The `num_classes` (1) in Shared2FCBBoxScoreHead of MMDataParallel does not matches the...
OLN-Mask
Thanks for this nice piece of research. It would be very helpful, if you could provide some script for training/testing OLN-Mask on COCO.
Thanks for the excellent work. Do you have any plan to publicly release **annotated bounding boxes** for the RoboNet images? Thanks!