Our target is to convert the pre-trained pytorch weight to tf2 not training the model. So do we need to initialise the model using inflated swin2d weights? Won't initialising the models using the converted pre-trained weight be enough?
If initialising the model with inflated swin 2d weights needed, then should we use the original pytorch weights of swin2d models or the converted tf2 weights available on tf-hub?
@sayakpaul Please have a look.
The Video Swin Transformer (swin3d) initialises weights in two ways-
Code Link: https://github.com/SwinTransformer/Video-Swin-Transformer/blob/master/mmaction/models/backbones/swin_transformer.py#L563
Our target is to convert the pre-trained pytorch weight to tf2 not training the model. So do we need to initialise the model using inflated swin2d weights? Won't initialising the models using the converted pre-trained weight be enough?
If initialising the model with inflated swin 2d weights needed, then should we use the original pytorch weights of swin2d models or the converted tf2 weights available on tf-hub?