search

FanglinBao / HADAR

This is an LWIR stereo-hyperspectral database to develop HADAR algorithms for thermal navigation. Based on this database, one can develop algorithms for TeX decomposition to generate TeX vision. One can also develop algorithms about object detection, semantic or scene segmentation, optical or scene flow, stereo depth etc. based on TeX vision instead of traditional RGB or thermal vision.
MIT License
166 stars 26 forks source link

RuntimeError #26

Open jjb202 opened 2 months ago

jjb202 commented 2 months ago

I downloaded the Scene 1-Scene 11 dataset and running main.py gives me a dataset size error. 微信图片_20240721150136

RuntimeError: Wrong input shape height=1080, width=1920. Expected image height and width divisible by 16. Consider pad your images to shape (1088, 1920).

I debugged and found that the size of the img in the first batch is （channel=49，256，256）, and in the second batch it becomes （channel=49，1080，1920）.... Is this normal?

yolo799 commented 2 weeks ago

I'd like to know what kind of hardware you use to collect your data, and what you do with that data to use in your code.

jjb202 commented 1 week ago

I'd like to know what kind of hardware you use to collect your data, and what you do with that data to use in your code.

I am training the data with 2080ti. And I changed the name of the 11th scene in order to read the data, otherwise it reports a bug. after changing the name it prompts this error again.