object_localization_network icon indicating copy to clipboard operation
object_localization_network copied to clipboard

Learning Open-World Object Proposals without Learning to Classify

Results 11 object_localization_network issues
Sort by recently updated
recently updated
newest added

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:...

![image](https://user-images.githubusercontent.com/55774463/189183512-e61a58f2-f3e8-4728-930a-4186c83e9c1f.png) 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 ![image](https://user-images.githubusercontent.com/55774463/189202882-ee3993fc-7025-46c4-bfa3-2abd611ada11.png)

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...

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!