MichaelRamamonjisoa / SharpNet

SharpNet: Fast and Accurate Recovery of Occluding Contours in Monocular Depth Estimation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

What's the --scale option means when run the demo.py?

LiZhenLiangLee opened this issue · comments

If the size of my input image is not 640x480, can you tell me how to set the --scale option ?an example?

And the --scale set to 1.0 if input image's size is 640x480, right?

Hi, thanks for your interest!
The scale option is a scale factor applied to the original dimensions of the image.
If your input image size is 1280x960, using --scale 0.5 would scale it down to 640x480.
If your input image size is 320x240, using --scale 2 would scale it up to 640x480.

Generally, if you set --scale S, S being a float number, and your original resolution is WxH, the rescaled input (and output) will be of size SW x SH.

Hi, thanks for your interest!
The scale option is a scale factor applied to the original dimensions of the image.
If your input image size is 1280x960, using --scale 0.5 would scale it down to 640x480.
If your input image size is 320x240, using --scale 2 would scale it up to 640x480.

Generally, if you set --scale S, S being a float number, and your original resolution is WxH, the rescaled input (and output) will be of size SW x SH.

thanks for reply