Closed optimisticabouthumanity closed 7 months ago
Our code is based on Detectron2, a popular computer vision library developed by Facebook AI Research. To determine the total number of parameters, layers, and FLOPs for the entire network, including both the backbone and FlowNet components, you can refer to the relevant documentation provided by Detectron2.
@xjtulyc , how many parameters does only the ultradet.pth have?
33.06 M, 33059164 in total.
Is it possible to know how many parameters, layers and FLOPs (including backbone and flownet) do the network have as a whole?