How to train a custom dataset and visualize test results?

danfenghong / IEEE_TIP_UIU-Net

Xin Wu, Danfeng Hong, Jocelyn Chanussot. UIU-Net: U-Net in U-Net for Infrared Small Object Detection, IEEE Trans. Image. Process., 2022, 32: 364-376.

Apache License 2.0

136 stars 15 forks source link

How to train a custom dataset and visualize test results? #19

Open Aq114 opened 4 months ago

Aq114 commented 4 months ago

If I currently have a large number of raw infrared small target images and annotated txt files, but no mask files, how can I obtain mask labels? And try this dataset during training? Can the final test results be visualized?

xjyisok commented 2 months ago

you can first get the box of target then label the pixel in the box based on its gray level