search

Luo-Z13 / pointobb

[CVPR2024] PointOBB: Learning Oriented Object Detection via Single Point Supervision
MIT License
55 stars 3 forks source link

How to visualize the results? #18

Closed yaosx425 closed 1 month ago

yaosx425 commented 2 months ago

I use my own dataset for training, and the format of the dataset is the same as the format of DOTA. After training 24 epochs, how can I visualize it? I want to test an image

Luo-Z13 commented 1 month ago

Hello, after completing the inference and obtaining pseudo rbox labels in DOTA format, you can use the browse_dataset.py in mmrotate (tools/misc/browse_dataset.py) to visualize the pseudo-labels generated by the PointOBB inference.

yaosx425 commented 1 month ago

Hello, after completing the inference and obtaining pseudo rbox labels in DOTA format, you can use the browse_dataset.py in mmrotate (tools/misc/browse_dataset.py) to visualize the pseudo-labels generated by the PointOBB inference.

但是我在completing the inference and obtaining pseudo rbox labels in DOTA format的时候，代码报错，显示我缺少一些东西，这是怎么回事？麻烦作者看下我最新问的那个问题，您有遇到过吗？