open-mmlab / mmrotate

OpenMMLab Rotated Object Detection Toolbox and Benchmark
https://mmrotate.readthedocs.io/en/latest/
Apache License 2.0
1.84k stars 540 forks source link

[Docs] The image results on inference show #841

Open pphgood opened 1 year ago

pphgood commented 1 year ago

Branch

master branch https://mmrotate.readthedocs.io/en/latest/

📚 The doc issue

I want the inferred test image to show only the test box without the category and confidence level. Because of the close proximity of objects in DOTA results in too much clutter all together.But I don't know how to implement it, I didn't find any documentation on it in the documentation.Would like to know which file function to change this configuration.

Suggest a potential alternative/fix

No response

zytx121 commented 1 year ago

@pphgood you can modify this file https://github.com/open-mmlab/mmrotate/blob/main/mmrotate/core/visualization/image.py Delete the code that displays the category and confidence score.

jiubie89 commented 2 months ago

Branch

master branch https://mmrotate.readthedocs.io/en/latest/

📚 The doc issue

I want the inferred test image to show only the test box without the category and confidence level. Because of the close proximity of objects in DOTA results in too much clutter all together.But I don't know how to implement it, I didn't find any documentation on it in the documentation.Would like to know which file function to change this configuration.

Suggest a potential alternative/fix

No response

May I ask whether your test picture is the original one? The test picture of my test.py is the segmented one. May I ask how to visualize the label box on the original picture

jiubie89 commented 2 months ago

@pphgood you can modify this file https://github.com/open-mmlab/mmrotate/blob/main/mmrotate/core/visualization/image.py Delete the code that displays the category and confidence score.

May I ask whether your test picture is the original one? The test picture of my test.py is the segmented one. May I ask how to visualize the label box on the original picture