The configuration of the architecture variants is inconsistent with the papers and weights files.

[lartpang]

@tangchuanxin

SPACH/models/registry.py

Line 224 in 497c1d8

model = ShiftViT(embed_dim=96, depths=(3, 3, 24, 4), mlp_ratio=2, drop_path_rate=0.2, n_div=12)

The code is inconsistent with the content of the paper:

and the weight file. The content of this pth file is the same as the architecture variant -S in the figure above, ie, depths=(6, 8, 18, 6).

https://github.com/microsoft/SPACH/releases/download/v1.0/shiftvit_tiny_r2.pth

[wgting96]

Thank you for pointing this error out. The configuration [depths=(6, 8, 18, 6)] is correct. I will fix this bug soon.

The configuration of (3, 3, 24, 4) is another version of ShiftViT-T we have tried. It has the similar number of parameters and FLOPs.

Config	MLP ratio	Num of params. (M)	FLOPs (G)
[6, 8, 18, 6]	2.0	29	4.6
[3, 3, 24, 4]	2.0	27	4.1