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
In SigLIP preprocess, the transform flow is defined in: link
For to_channel_dimension_format, the argument channel_dim and input_channel_dim are both set as self.data_format, so no matter it's set as channel_first or channel_last, it always returns the original image. Not sure if this is the correct behavior also.
Please correct me if I was wrong.
Thanks.
YC
The text was updated successfully, but these errors were encountered:
Greetings.
In SigLIP preprocess, the transform flow is defined in: link
For to_channel_dimension_format, the argument channel_dim and input_channel_dim are both set as self.data_format, so no matter it's set as channel_first or channel_last, it always returns the original image. Not sure if this is the correct behavior also.
Please correct me if I was wrong.
Thanks.
YC
The text was updated successfully, but these errors were encountered: