Add T2T_ViT

Author: brianhou0208

tests/test_models.py

@@ -53,13 +53,13 @@
     'vision_transformer', 'vision_transformer_sam', 'vision_transformer_hybrid', 'vision_transformer_relpos',
     'beit', 'mvitv2', 'eva', 'cait', 'xcit', 'volo', 'twins', 'deit', 'swin_transformer', 'swin_transformer_v2',
     'swin_transformer_v2_cr', 'maxxvit', 'efficientnet', 'mobilenetv3', 'levit', 'efficientformer', 'resnet',
-    'regnet', 'byobnet', 'byoanet', 'mlp_mixer', 'hiera', 'fastvit', 'hieradet_sam2', 'aimv2*'
+    'regnet', 'byobnet', 'byoanet', 'mlp_mixer', 'hiera', 'fastvit', 'hieradet_sam2', 'aimv2*', 't2t_vit',
 ]
 
 # transformer / hybrid models don't support full set of spatial / feature APIs and/or have spatial output.
 NON_STD_FILTERS = [
     'vit_*', 'tnt_*', 'pit_*', 'coat_*', 'cait_*', '*mixer_*', 'gmlp_*', 'resmlp_*', 'twins_*',
-    'convit_*', 'levit*', 'visformer*', 'deit*', 'xcit_*', 'crossvit_*', 'beit*', 'aimv2*',
+    'convit_*', 'levit*', 'visformer*', 'deit*', 'xcit_*', 'crossvit_*', 'beit*', 'aimv2*', 't2t_vit*',
     'poolformer_*', 'volo_*', 'sequencer2d_*', 'mvitv2*', 'gcvit*', 'efficientformer*', 'sam_hiera*',
     'eva_*', 'flexivit*', 'eva02*', 'samvit_*', 'efficientvit_m*', 'tiny_vit_*', 'hiera_*', 'vitamin*', 'test_vit*',
 ]

timm/models/__init__.py

@@ -64,6 +64,7 @@
 from .swin_transformer import *
 from .swin_transformer_v2 import *
 from .swin_transformer_v2_cr import *
+from .t2t_vit import *
 from .tiny_vit import *
 from .tnt import *
 from .tresnet import *