alanzty / kcr-official Goto Github PK

Hello authors! Really great job and inspires me a lot. One of the questions about the code of the article is that if the detection network is to be changed to a single-stage network similar to YOLO, what changes do you need to make to your code, whether you want to delete the loss of the first stage in your code, or what changes are needed elsewhere, I hope to get your answer

Thank you for your great work!
I was wondering if you plan to release your code anytime soon.

How do SAR data sets define the input that I use to report the following error
File "kcrtools/train_kcr_2d.py", line 332, in
main()
File "kcrtools/train_kcr_2d.py", line 321, in main
train_detector(
File "kcrtools/train_kcr_2d.py", line 219, in train_detector
runner.run(data_loaders, cfg.workflow)
File "/root/miniconda3/envs/kcr/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 130, in run
epoch_runner(data_loaders[i], **kwargs)
File "/root/miniconda3/envs/kcr/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 47, in train
for i, data_batch in enumerate(self.data_loader):
File "/root/miniconda3/envs/kcr/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 521, in next
data = self._next_data()
File "/root/miniconda3/envs/kcr/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 561, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "/root/miniconda3/envs/kcr/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/root/miniconda3/envs/kcr/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/root/autodl-tmp/KCR-Official-main/kcr/kcr_datasets.py", line 375, in getitem
aa_data = self.aa_dataset.prepare_train_img(aa_idx)
File "/root/autodl-tmp/KCR-Official-main/mmdet/datasets/custom.py", line 236, in prepare_train_img
ann_info = self.get_ann_info(idx)
File "/root/autodl-tmp/KCR-Official-main/mmdet/datasets/coco.py", line 104, in get_ann_info
return self._parse_ann_info(self.data_infos[idx], ann_info)
File "/root/autodl-tmp/KCR-Official-main/kcr/kcr_datasets.py", line 259, in _parse_ann_info
inter_w = max(0, min(x1 + w, img_info["width"]) - max(x1, 0))
TypeError: '<' not supported between instances of 'str' and 'int'

Hello, I would like to ask why the loss of the target domain in the second stage RCNN does not include the loss of bounding box regression. Is there any reason for this?

Hi @alanzty, thanks for your excellent work. Welcome adding this model to MMRotate1. x to let more people see it and further increase the impact of your work. If you need any assistance, please contact me!

The following is an example of a project:
https://github.com/open-mmlab/mmrotate/tree/dev-1.x/projects/example_project