search

HyeongminLEE / AdaCoF-pytorch

Official source code for our paper "AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation" (CVPR 2020)
MIT License
172 stars 27 forks source link

about dataset #7

Closed Heroandzhang closed 3 years ago

Heroandzhang commented 3 years ago

Hello,I see sentences about datasets in your paper. These sentences are'Training Dataset. We use Vimeo90K dataset for training. It contains 51,312 triplets of 256 × 448 video frames.' But when i training with the ‘vimeo_triplet’ folder ,i find it contains 73191 triplets. I want to ask you, if the number of training datasets is different from you, what are the adverse effects？ thank you!

HyeongminLEE commented 3 years ago

There might be a slight difference in PSNR, but probably the gap will be usually not significant. The changes when training AdaCoF on various datasets show the same tendency as when training other general networks.