issues with linear attention mode when running the main

[ChenQian9104]

Get errors below when running the main function:

constructing SpatialTransformer_ of depth 1 w/ 512 channels and 16 heads
Attention mode 'linear' is not available. Falling back to native attention. This is not a problem in Pytorch >= 2.0. FYI, you are running with PyTorch version 2.4.0

[ALEEEHU]

Same issue!

Here are more detailed information:
constructing SpatialTransformer_ of depth 1 w/ 512 channels and 16 heads
Attention mode 'linear' is not available. Falling back to native attention. This is not a problem in Pytorch >= 2.0. FYI, you are running with PyTorch version 2.0.1+cu118

[WindVChen]

@ChenQian9104 @ALEEEHU Hi Guys,

Seems figured out. Install the xformers package and it works for me.