chinhsuanwu/mobilevit-pytorch
A PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer"
PythonMIT
Issues
- 0
- 0
License of pretrained weights
#17 opened by alzaia - 4
Can you share the weight file of the model? I want to use it for transfer learning
#5 opened by tuchuanle159 - 0
question
#16 opened by Michael-Chao - 0
Could someone help with pointers/code to visualize the attention maps generated by mobilevit?
#15 opened by arunsubk - 3
- 0
- 0
Inference speed is very slow on CPU
#13 opened by rnwang04 - 3
einops.EinopsError: Error while processing rearrange-reduction pattern "b d (h ph) (w pw) -> b (ph pw) (h w) d".
#8 opened by JiangMei0201 - 0
Error in sequence of steps in the model
#12 opened by hungryGeek16 - 0
mobilevit_xs occured CUDA out of memory?
#10 opened by HTCho1 - 4
If I want to use Mobilevit in Cifar10, how should I set the parameters?
#9 opened by learningelectric - 2
Headnum=1 ?
#6 opened by hkzhang-git - 2
请问下 您这个实现版本跟原文的模型参数 有对比吗 性能方面呢
#1 opened by fakerhbj - 0
The inference speed is slow
#4 opened by ZhangLei999 - 4
- 0
#Params and Accuracy?
#2 opened by nightsnack