If I input four-channel data, how should I modify the parameters? Because my four-channel data is spliced from four single-channel 2D images, if i want The training input data is four channels, because my six-channel data is spliced from six single-channel 2D images. How should I modify the code? I do not have a mask annotation file. Can I use this code?

jqtangust / IUF

[ECCV 2024] Official Implementation of An Incremental Unified Framework for Small Defect Inspection

https://jqt.me/_IUF_/

29 stars 0 forks source link

If I input four-channel data, how should I modify the parameters? Because my four-channel data is spliced from four single-channel 2D images, if i want The training input data is four channels, because my six-channel data is spliced from six single-channel 2D images. How should I modify the code? I do not have a mask annotation file. Can I use this code? #4

Open watertianyi opened 3 weeks ago

jqtangust commented 3 weeks ago

I am not sure the four-channel image format can detect anomalies by reconstruction-based anomaly detection method or not. If it can be used, you can edit the dataloader to support this image format.