search

samaonline / Hierarchical-Model-for-Long-term-Video-Prediction

Given the previous frames of the video as input, we want to get the long-term frame prediction.
Apache License 2.0
31 stars 7 forks source link

analogy network imread #3

Closed kikyou123 closed 7 years ago

kikyou123 commented 7 years ago

image the network input is [224,224,3],should the imread images imresize [224,224,3]？ and the network input should scale [0,1], or just [0, 255]?

samaonline commented 7 years ago

Thanks for asking. Yes, you should resize the image size so that it matches the input size. For scaling, we use [0, 255].