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.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Can you generate a traced model using pytorch jit for users to test?

shockwaveHe opened this issue · comments

Hi Dr. Bao, I am interested in your work and want to apply HADAR to some tasks. However, it looks like the documentation and packages are not fully developed, causing a big issue in testing and evaluating your work quickly. Is it possible for you to generate a traced model using the torch.jit.trace() method so that I can quickly test HADAR inference? Thanks! And also the configuration of mainTeX.m is not clear. There are no files with 's_EnvObj.mat' and '_wn' in the dataset you provide.

Hi shockwaveHe,
Thanks for your interest in our work. I've updated the TeX code package. Please re-download and test. Also, please check issue #6 for some of the clarifications. Thanks.