Input value scale and resolution

[yjhong89]

Hi. Thanks for sharing works!

Input value scale

• Is it right input values for torch i3d model would be range in [0,1]?

  • Use "rand" (uniform) function in here https://github.com/universome/fvd-comparison/blob/5b88a524a54ba5d685014ed4b35d75148fb66c28/compare_metrics.py#L54

• Meanwhile, It seems input range [-1, 1] used in tensorflow i3d

  • https://github.com/universome/fvd-comparison/blob/5b88a524a54ba5d685014ed4b35d75148fb66c28/their_fvd.py#L67

• If I use FVD with torch, which one is right between [0,1] and [-1,1] ?

Input resolution

• If I set input resolution above 224, this code returns [batch size, 400, feat_h, feat_w]. If I want to use resolution 256, is it right average [batch size, 400, feat_h, feat_w] to have shape of [batch size, 400] (average across spatial dim) ? https://github.com/universome/fvd-comparison/blob/5b88a524a54ba5d685014ed4b35d75148fb66c28/compare_metrics.py#L34