You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@Tylersuard,
If you are pre-processing the images to resize all of them to fixed size then yes, you can use asymmetrical images as inputs while training.
For more information, you can check this example from Tensorflow, which uses images of different sizes for training.
For instance, an image of 500x3000 pixels.
The text was updated successfully, but these errors were encountered: