Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

复现问题。按照README.md构建了环境及数据集,但是在训练时出现了以下问题,是在是找不出是什么原因了.....。生成的DOTA1_5_trin1024.json的样式也在下面进行了展示 #18

Open
cc0616 opened this issue May 8, 2022 · 1 comment

Comments

@cc0616
Copy link

cc0616 commented May 8, 2022

2022-05-06 20:30:29,371 - mmdet - INFO - Start running, host: pc@zcc-Precision-7920-Tower, work_dir: /home/pc/cengxu/NO.9/DARDet-master/workdir/DARDet_r50_2080base
2022-05-06 20:30:29,371 - mmdet - INFO - workflow: [('train', 1)], max: 36 epochs
Traceback (most recent call last):
File "tools/train.py", line 190, in
main()
File "tools/train.py", line 187, in main
meta=meta)
File "/home/pc/cengxu/NO.9/DARDet-master/mmdet/apis/train.py", line 175, in train_detector
runner.run(data_loaders, cfg.workflow)
File "/home/pc/anaconda3/envs/dar/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 125, in run
epoch_runner(data_loaders[i], **kwargs)
File "/home/pc/anaconda3/envs/dar/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 47, in train
for i, data_batch in enumerate(self.data_loader):
File "/home/pc/anaconda3/envs/dar/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 345, in next
data = self._next_data()
File "/home/pc/anaconda3/envs/dar/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 856, in _next_data
return self._process_data(data)
File "/home/pc/anaconda3/envs/dar/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 881, in _process_data
data.reraise()
File "/home/pc/anaconda3/envs/dar/lib/python3.7/site-packages/torch/utils.py", line 395, in reraise
raise self.exc_type(msg)
TypeError: init() missing 4 required positional arguments: 'casting', 'from
', 'to', and 'i'

DORA1_5train1024.json
{"images": [{"file_name": "296__1__0___0.JPG", "id": 1, "width": 800, "height": 800}, {"file_name": "55__1__0___0.JPG", "id": 2, "width": 800, "height": 800}, {"file_name": "196__1__0___0.JPG", "id": 3, "width": 800, "height": 800}, {"file_name": "306__1__0___0.JPG", "id": 4, "width": 800, "height": 800},..............{"category_id": 1, "segmentation": [[347, 200, 473, 219, 468, 250, 343, 231]], "iscrowd": 0, "bbox": [343, 200, 130, 50], "area": 6500, "image_id": 203, "id": 557}, {"category_id": 1, "segmentation": [[382, 343, 409, 346, 405, 381, 378, 378]], "iscrowd": 0, "bbox": [378, 343, 31, 38], "area": 1178, "image_id": 203, "id": 558}, {"category_id": 1, "segmentation": [[370, 484, 395, 487, 391, 519, 366, 516]], "iscrowd": 0, "bbox": [366, 484, 29, 35], "area": 1015, "image_id": 203, "id": 559}]}

@Lg955
Copy link

Lg955 commented May 18, 2022

@cc0616 参考这个 #6 (comment)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants