Will this method work if we train on 4 cameras but test on 3 or 2 cameras?

[mnauf]

Will this method work if we train on 4 cameras but test on 3 or 2 cameras?

As you mentioned in the paper you trained on human3.6m and evaluated on KTH Football 2 dataset, but the details on the number of cameras aren't discussed. I understand human3.6m has 4 synced cameras and KTH has 3. So in order to evaluate FLEX on KTH for checking its generalization, did you train on human3.6m 3 cameras? or trained with 4?

[BrianG13]

Hi @mnauf ,

Yes this method will work if you train on 4 cameras but test on less, just feed 0's tensors on the cameras inputs you are not using