search

Adamdad / ConsistentTeacher

[CVPR2023 Highlight] Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection
Apache License 2.0
291 stars 19 forks source link

Has anyone had this problem and what to do #20

Open mxy0610 opened 1 year ago

mxy0610 commented 1 year ago

image

Adamdad commented 1 year ago

Dear @mxy0610 ,

From your error code, it's unclear what settings you're using for your training. However, it seems you might be encountering issues due to using a single GPU or setting a very low label-to-unlabeled ratio. It's essential that each training batch contains at least one labeled sample for successful SSOD training. If your label-to-unlabeled ratio is set so low that certain batches lack labeled samples, the data loader might not perform as expected. If you could provide more details about your settings and approach, it would be easier for me to assist you further.

Best