search

SJTU-LuHe / TransVOD

The repository is the code for the paper "End-to-End Video Object Detection with Spatial-TemporalTransformers"
Apache License 2.0
203 stars 28 forks source link

Very low precision on custom dataset #28

Closed zzzbzzz closed 1 year ago

zzzbzzz commented 1 year ago

Very nice work and thank you for sharing the code. However, when I used the multi-frame model on my own dataset, I got very low precision near zero, while the single-frame deformable DETR obtained 20 to 30 mAP, which is normal for my dataset. I followed the default settings in my implementation. I wonder what might be the reason and can you upload the training logs for reference?

fisal-ITS commented 1 year ago

Hi, Have you solved the problem? I also get very small precision close to zero when using my own dataset. Could you please provide information on how you solved it?

bharathikannann commented 2 months ago

Hey there,

I would also like to know, how you have solved the problem.