I’m trying to train detectnet v2. I need to know if TAO supports multilabeling?
Or maybe there are some ways to make the model train for the multilabeling task?
Maybe somehow format the kitty annotations?
Any ideas, thanks
Yes,it can. Please find more detailed info for the multitask classification network in the user guide.
I just found https://docs.nvidia.com/tao/tao-toolkit/text/multitask_image_classification.html but I’m not sure about it. However, the classification instruction is written there, but I have the task of detecting objects using DetectNetV2, I don’t know if it is compatible
There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
Thanks
May I know more details about the multi-labeling with object detection?
Could you share an example image/label ? Thanks.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.