Obtain final action scores of two or four-stream training
anhvu2501 opened this issue · comments
Thank you for your wonderful work!
I would like to ask if you can let me know how you obtained the final action scores (final top-1 accuracy) of the two or four-stream network. As I have read in the MS-AAGCN paper, the author says that the softmax scores of the four streams are fused using weighted summation. Which weights I should assign for each stream to receive an approximate scores as your official implementation?
Hello, have you found a way to fuse the joints and bones?
Hi, I tried by following the author's approach that is the softmax scores of the multi-stream are fused using weighted summation. Then, I just assigned weights for joint and bone modality, based on the benchmark we are evaluating (For instance, if we evaluate on XSub benchmark, I assigned weight for bone modality higher than for joint, vice versa)
Do you think whether this approach is correct or not?
Thank you for your reply, I think this is fine. I am currently allocating on a 1:1 ratio. I will use your suggestion to make adjustments.
It's fine I think. You just need to use the weighted summation of scores for different modalities (joint, bone, etc.) as the fused prediction.
Hello, I would like to ask you a few questions. Can you tell me how to get the two-stream accuracy? Could you please share the code with me? :)
please share the code