Open Zealoe opened 5 years ago
The flownet2.0 has an ensemble mechanism in the end while pwcnet upsamples the final prediction, therefore the flownet2.0 sometimes produces sharper results. Moreover, it may require finetuning on the new dataset you are using before benchmarking different algorithms.
hi do can I ensemble PWC-Net and flownetS and flownetC using bagging method? i mean Ensemble learning can be used for Above CNN Models that estimating river flow velocity?
I found the flow produced by pwcnet is more blurry than that of flownet2.0. Is it supposed to perform worse? Image:
Flow by Flownet2.0:
Image warped by Flownet2.0:
Flow by PWCnet:
Image warped by PWCnet: