Unofficial PyTorch implementation of MobileViT
Overview
This is a PyTorch implementation of MobileViT specified in “MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer“, arXiv 2021.
Usage
import torch
from mobilevit import mobilevit_xxs
net = mobilevit_xxs()
img = torch.randn(1, 3, 256, 256)
out = net(img)
Credits
Code adapted from MobileNetV2 and ViT.
GitHub