[Bug] How to infer the trained model on the DOTA-1.0 dataset using the MMrotate dev1.x branch, and generate a compressed file for online submission?

[fadaishaitaiyang]

[Bug] How to infer the trained model on the DOTA-1.0 dataset using the MMrotate dev1.x branch, and generate a compressed file for online submission?

[Atlantisming]

https://github.com/open-mmlab/mmrotate/blob/1.x/configs/_base_/datasets/dota.py

# inference on test dataset and format the output results
# for submission. Note: the test set has no annotation.
# test_dataloader = dict(
#     batch_size=1,
#     num_workers=2,
#     persistent_workers=True,
#     drop_last=False,
#     sampler=dict(type='DefaultSampler', shuffle=False),
#     dataset=dict(
#         type=dataset_type,
#         data_root=data_root,
#         data_prefix=dict(img_path='test/images/'),
#         test_mode=True,
#         pipeline=test_pipeline))
# test_evaluator = dict(
#     type='DOTAMetric',
#     format_only=True,
#     merge_patches=True,
#     outfile_prefix='./work_dirs/dota/Task1')

[fadaishaitaiyang]

thank you