Closed zshn25 closed 3 years ago
You can try with smaller values for the velocity supervision weight, 0.1
is at the upper limit and sometimes stops proper convergence. Another option is to start from a pre-trained self-supervised model and fine-tune with the velocity supervision, that usually works better and converges faster.
Strangely, reducing the batch size worked.
I have managed to train the SelfSupModel on KITTI and the result looks quite good. Although, it tends overfits after epoch 16. But, when I train with VelSupModel, inference on the trained model gives constant flat output. My config is as below