mmrotate icon indicating copy to clipboard operation
mmrotate copied to clipboard

OpenMMLab Rotated Object Detection Toolbox and Benchmark

Results 309 mmrotate issues
Sort by recently updated
recently updated
newest added

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

dev-1.x

Where can we set the epoch?

- [x] refactor `DOTADataset` - [x] add UT - [x] modify files which may cause UT to fail. - [x] refactor `FakeRotatedAnchorGenerator` - [x] refactor `DOTAMetric` Reviewer: @RangiLyu

dev-1.x

Thanks for your wonderful work! I have a question about the model output, for many rotated object detection works you have reimplemented in this project, but different works tend to...

During the test of DOTA dataset, the checkpoint was loaded successfully, but it got stuck in Mutiple processing. I tried many times but couldn't solve it load checkpoint from local...

bug

**Describe the bug** I am trying to train and test the clf model which using the configs of rotated_reppoints_r50_fpn_1x_dota_oc, it is successed to finished the train process, but an error...

bug

AssertionError: CosineRestartLrUpdaterHook I set lr_config as follows: lr_config = dict( policy='CosineRestart', periods=[3000, 3000, 3000, 3000], restart_weights=[1, 1, 1, 1], warmup='linear', warmup_iters=500, warmup_ratio=1.0 / 3) What's wrong?

How to set img_norm_cfg if I want train my dataset? or how to calculate it? img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...