Open otroshi opened 2 years ago
Hi,
Do SwinTransformer based models get the 112 x 112 images as their input (like all other models)? or do they get 224 x 224 images?
SwinTransformer
112 x 112
224 x 224
PS. While in Step1: Prepare the training data images are mentioned to be 112 x 112, there is an argument in training_mode/backbone_conf.yaml and also model logs for img_size which is set 224
img_size
In order to stay consistent with the original setting of SwinTransformer, we just resize the input image from 112112 to 224224.
Hi,
Do
SwinTransformer
based models get the112 x 112
images as their input (like all other models)? or do they get224 x 224
images?PS. While in Step1: Prepare the training data images are mentioned to be
112 x 112
, there is an argument in training_mode/backbone_conf.yaml and also model logs forimg_size
which is set 224