msvar模型介绍（【Timm】create_model所提供的ViT模型概览）

 ⚪查看代码：python xxx.py 

import timm if __name__ == __main__: model_vit = timm.list_models(*vit*) print(len(model_vit),model_vit[:])

⚪结合vision transformer理解

7 ResNets:

R50x1, R50x2 R101x1, R152x1, R152x2, pre-trained for 7 epochs, plus R152x2 and R200x3 pre-trained for 14 epochs;

6 Vision Transformers: 

ViT-B/32, B/16, L/32, L/16, pre-trained for 7 epochs, plus L/16 and H/14 pre-trained for 14 epochs;

5 hybrids,

R50+ViT-B/32, B/16, L/32, L/16 pretrained for 7 epochs, plus R50+ViT-L/16 pre-trained for 14 epochs

参数解读：

以ViT-L/16为例
    
    
    
    
，表示ViT Large模型     


     


     


     


   ，对应patch_size为16    
    
    
    
   。 但是 




 




 




 




 

，混合模型的数值不是对应patch_size

   

   

   

   

，而是ResNet的总取样率 


     


     


     


     

。 采样：模拟信号进行取样时的快慢次数 这里就能对Timm库所提供的预训练模型有所理解

 




 




 




 




。

⚪ViT_model概览-28个

vit_base_patch16_224, vit_base_patch16_224_in21k, vit_base_patch16_384, vit_base_patch32_224, vit_base_patch32_224_in21k, vit_base_patch32_384, vit_base_resnet26d_224, vit_base_resnet50_224_in21k, vit_base_resnet50_384, vit_base_resnet50d_224, vit_deit_base_distilled_patch16_224, vit_deit_base_distilled_patch16_384, vit_deit_base_patch16_224, vit_deit_base_patch16_384, vit_deit_small_distilled_patch16_224, vit_deit_small_patch16_224, vit_deit_tiny_distilled_patch16_224, vit_deit_tiny_patch16_224, vit_huge_patch14_224_in21k, vit_large_patch16_224, vit_large_patch16_224_in21k, vit_large_patch16_384, vit_large_patch32_224, vit_large_patch32_224_in21k, vit_large_patch32_384, vit_small_patch16_224, vit_small_resnet26d_224, vit_small_resnet50d_s3_224

文章推荐：

Pytorch视觉模型库--timm_pytorch 模型库 pytorch下的迁移学习模型库·详细使用教程