You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
ZJUTER0126 9fff213da6 [add] add ConvNext run on openi 1 year ago
scripts first commit 1 year ago
src [add] add ConvNext run on openi 1 year ago
README.md [add] add ConvNext run on openi 1 year ago
__init__.py first commit 1 year ago
eval.py first commit 1 year ago
export.py first commit 1 year ago
requriments.txt first commit 1 year ago
train.py first commit 1 year ago

自从ViT提出之后,在过去的一年里(2021年),基于transformer的模型在计算机视觉各个领域全面超越CNN模型。然而,这很大程度上都归功于Local Vision Transformer模型,Swin Transformer是其中重要代表。原生的ViT模型其计算量与图像大小的平方成正比,而Local Vision Transformer模型由于采用local attention(eg. window attention),其计算量大幅度降低,除此之外,Local Vision Transform

Python Shell

Contributors (2)